Merge remote-tracking branch 'origin/iccv' into new_model

aaa_helpers.txt

@@ -1,7 +1,7 @@
-nohup python cvae.py --name="lhunor_abl_all_10p_curv_10_r2" > nohup/review/abl_all_10p_curv_10_r2.out 2>&1 &
-nohup python auto_encoder_curv.py --name="lhunor_ae_curv_1_orig_curv_10_10p_r2" > nohup/review/curv_1_orig_curv_10_10p_r2.out 2>&1 &
-nohup python auto_encoder_curv.py --name="lhunor_ae_curv_1_orig_curv_25_10p_r2" > nohup/review/curv_1_orig_curv_25_10p_r2.out 2>&1 &
-nohup python auto_encoder_curv.py --name="lhunor_ae_curv_1_orig_curv_100_10p_r2" > nohup/review/curv_1_orig_curv_100_10p_r2.out 2>&1 &
+nohup python cvae.py --name="lhunor_weights_test_6" > nohup/iccv/weights_test_6.out 2>&1 &
+nohup python evaluate_ae.py --name iccv_weights_test_6 > nohup/iccv/evaluate_iccv_weights_test_6.out 2>&1 &
+nohup python calculate_error.py --name iccv_weights_test_6 > nohup/iccv/error_iccv_weights_test_6.out 2>&1 &
+
 
 one final convolutional layer for smoothing, on the final coordinates
 

compare_models_saved.py

@@ -0,0 +1,188 @@
+import os
+import sys
+from configs.config_abl_all_post import config as config_a
+
+os.environ["CUDA_VISIBLE_DEVICES"] = '5'
+import tensorflow as tf
+
+gpus = tf.config.experimental.list_physical_devices('GPU')
+if gpus:
+    try:
+        # Currently, memory growth needs to be the same across GPUs
+        for gpu in gpus:
+            tf.config.experimental.set_memory_growth(gpu, True)
+        logical_gpus = tf.config.experimental.list_logical_devices('GPU')
+        print(len(gpus), "Physical GPUs,", len(logical_gpus), "Logical GPUs")
+    except RuntimeError as e:
+        # Memory growth must be set before GPUs have been initialized
+        print(e)
+
+import glob
+import time
+import argparse
+import wandb
+import tqdm
+import random
+import numpy as np
+import plotly.graph_objects as go
+import plotly.express as ex
+from PIL import Image
+from postprocessing import fix_collision
+
+if config_a['is_skirt']:
+    from losses import edge_loss_skirt as edge_loss
+else:
+    from losses import edge_loss
+
+
+
+from losses import collision_ratio, kl_loss #, concept_loss
+# from losses import collision_penalty as collision_penalty
+from losses import collision_loss as collision_penalty
+from custom_utils.custom_utils import batch_to_dict, load_model, plot_3d, UV2Mesh, get_summary_html, maskFacesBatch, _maskFaces, plot_3d_collision
+from dataset import DatasetFactory, StaticDataset
+from custom_utils.smpl import SMPL
+from models.cvae_model import CVAE
+from custom_utils.supersmpl_io import writeOBJ
+from plotly.subplots import make_subplots
+
+
+# uv2mesh = UV2Mesh(res=256, is_skirt=config_a['is_skirt'], is_adaptive=False)
+
+
+
+def plot(mesh_gt, pred_a, pred_b, body, mask):
+    fig = make_subplots(rows=1, cols=3, start_cell="top-left", specs = [ [{ 'type': 'scene' } for _ in range(3)] ])
+    
+    _, faces_garment = _maskFaces(np.zeros((14475, 3), np.float32), F, mask)
+    faces = np.concatenate((F, faces_garment + 14475), axis=0)
+    mesh_gt = np.concatenate((body, mesh_gt[mask, :]), axis=0)
+    pred_a = np.concatenate((body, pred_a), axis=0)
+    pred_b = np.concatenate((body, pred_b), axis=0)
+    colors = np.concatenate((np.ones_like(body, dtype=np.int32)*100, np.ones_like(mesh_gt, dtype=np.int32)*230), axis=0)
+    # colors = np.ones_like(mesh_gt, dtype=np.int32)*230
+
+    fig.add_trace(go.Mesh3d(
+            x=mesh_gt[:,0],
+            y=mesh_gt[:,2],
+            z=mesh_gt[:,1],
+            i = faces[:,0],
+            j = faces[:,1],
+            k = faces[:,2],
+            text="Ground Truth",
+            vertexcolor=colors,
+        ),
+        row=1, col=1)
+
+    fig.add_trace(go.Mesh3d(
+            x=pred_a[:,0],
+            y=pred_a[:,2],
+            z=pred_a[:,1],
+            i = faces[:,0],
+            j = faces[:,1],
+            k = faces[:,2],
+            text="Pred A",
+            vertexcolor=colors,
+        ),
+        row=1, col=2)
+
+    fig.add_trace(go.Mesh3d(
+            x=pred_b[:,0],
+            y=pred_b[:,2],
+            z=pred_b[:,1],
+            i = faces[:,0],
+            j = faces[:,1],
+            k = faces[:,2],
+            text="Pred B",
+            vertexcolor=colors,
+        ),
+        row=1, col=3)
+
+
+
+    fig.update_layout(scene_aspectmode='manual', scene_aspectratio=dict(x=1, y=1, z=1), 
+                    scene2_aspectmode='manual', scene2_aspectratio=dict(x=1, y=1, z=1), 
+                    scene3_aspectmode='manual', scene3_aspectratio=dict(x=1, y=1, z=1), 
+                    )
+    helper = dict(xaxis = dict(nticks=4, range=[-1,1],),
+                yaxis = dict(nticks=4, range=[-1,1],),
+                zaxis = dict(nticks=4, range=[-1,1],),)
+    fig.update_layout(scene = helper,
+                        scene2 = helper,
+                        scene3 = helper,
+                        )
+
+    return fig
+
+
+
+if __name__ == '__main__':
+    run = wandb.init(project='plots', name=config_a['name'], notes=config_a['notes'], dir='/wandb')
+
+    parser = argparse.ArgumentParser(description='')
+    parser.add_argument('--name', type=str)
+    args = vars(parser.parse_args())
+
+    skirt_modifier = '_skirt' if config_a['is_skirt'] else ''
+
+    folder = config_a['test_dir']
+    # smpl = SMPL(use_one_hot=False)
+
+    F = np.load("custom_utils/smpl_faces" + skirt_modifier + ".npy").astype(np.int32)
+
+    iteration = ''
+
+    # load_model(model, 'checkpoints/' + 'abl_all_120k')
+
+
+    factory = DatasetFactory()
+    dataset_a = factory.get_dataset(folder=config_a['test_dir'], 
+                                       batch_size=config_a['batch_size'], 
+                                       signature=config_a['signature_dynamic'], 
+                                       resolutions=[config_a['resolution']], 
+                                       in_memory=False, 
+                                       do_repeat=False,
+                                       use_one_hot=config_a['use_one_hot'],
+                                       use_no_orient=config_a['remove_global_orientation'],
+                                       shuffle=False,
+                                       testing=True,
+                                    #    frames_file='frames_abl.txt',
+                                       )
+    static_dataset_a = StaticDataset(folder=config_a['test_dir'], 
+                                        signature=config_a['signature_static'], 
+                                        resolutions=[config_a['resolution']], 
+                                        in_memory=True)
+
+    iterator_a = iter(dataset_a)
+    
+
+    faces_folder = '/home/workspace/data/results/support/faces' + ('_skirt' if config_a['is_skirt'] else '')
+    ids = os.listdir(faces_folder)
+    ids = [id.split('.')[0] for id in ids]
+    faces = {id : np.load(faces_folder + '/' + id + '.npy') for id in ids }
+
+    results_folder = '/home/workspace/data/results/post'
+
+    count = 0
+    while True:
+        batch = iterator_a.get_next()
+
+        batch = static_dataset_a.expand_batch(batch_to_dict(batch, config_a['signature_dynamic']))
+
+        mask = batch['mesh_mask'].numpy().astype(bool)
+        gt = batch['mesh_posed'].numpy()
+        body = batch['mesh_body_posed'].numpy()
+
+        for i in range(mask.shape[0]):
+            id, frame_nr = batch['id'][i].numpy().decode("utf-8"), batch['frame_nr'][i].numpy().decode("utf-8")
+            pred_a = np.load(results_folder + '/al_all_post-/' + id + '_' + frame_nr + '.npy')
+            pred_b = np.load(results_folder + '/iccv_weights_test_6-/' + id + '_' + frame_nr + '.npy')
+            # pred_c = np.load(results_folder + '/iccv_weights_test_6-/' + id + '_' + frame_nr + '.npy')
+
+            fig = plot(gt[i], pred_a, pred_b, body[i], mask[i])
+
+            wandb.log({f'{id}_{frame_nr}': fig}, step = count)
+            count += 1
+
+            print(count)
+

configs/config_abl_all_post.py

@@ -7,7 +7,7 @@ config = dict()
 # DON'T FORGET TO LOAD FINAL UPSCALER UNLESS HAVE LEVEL 512
 # DON'T FORGET TO CHECK AVG GARMENT USED
 
-config['use_skinning'] =              True # and deshaping
+config['use_skinning'] =              False # and deshaping
 config['remove_global_orientation'] = True
 config['use_curvature'] =             True
 config['use_extra_losses'] =          True # edge, collision, 3d mesh
@@ -19,9 +19,9 @@ config['only_curvatures'] =           False
 ablation_count = [config['use_skinning'], config['remove_global_orientation'], config['use_curvature'], config['use_extra_losses'], config['use_offsets']].count(False)
 assert ablation_count == 1 or ablation_count == 0
 
-config['gpu'] = '1'
-config['name'] = 'al_all_post'
-config['notes'] = ''
+config['gpu'] = '5'
+config['name'] = 'iccv_weights_test_8'
+config['notes'] = 'smaller weight loss coeff, 1e-6, convolutional weight learning, changed convnext reverse'
 
 config['avg_garment_path'] = 'custom_data/train_no_shape_avg_uv.npy' #custom_data/train_no_shape_avg_uv.npy # train_no_shape_avg_uv  train_no_shape_one_hot_avg_uv
 if config['use_skinning']:
@@ -86,14 +86,15 @@ config['use_one_hot'] = False
 config['cvae'] = dict()
 config['cvae']['is_label'] = False
 config['cvae']['add_noise'] = True
-config['cvae']['noise_amount'] = 0.001
+config['cvae']['noise_amount'] = 0.00001
 
 config['cvae']['kernel_size'] = 7
 config['cvae']['encoder_depths'] = [3, 3, 3, 9, 3]
 config['cvae']['encoder_dims'] = [32, 64, 128, 256, 64]
-config['cvae']['decoder_depths'] = config['cvae']['encoder_depths']
-config['cvae']['decoder_dims'] = config['cvae']['encoder_dims']
-
+config['cvae']['decoder_depths'] = [3, 9, 3, 3, 3, 3]
+config['cvae']['decoder_dims'] = [3, 32, 128, 128, 256, 512]
+config['cvae']['decoder_weights_depths'] = [3, 9, 3, 3, 3]
+config['cvae']['decoder_weights_dims'] = [24, 32, 64, 128, 256]
 
 config['cond_ae_static'] = dict()
 config['cond_ae_static']['is_label'] = False

configs/config_abl_pyr_32.py

@@ -1,7 +1,7 @@
 config = dict()
 
 config['gpu'] = '0'
-config['name'] = 'pyr_abl_32_r1'
+config['name'] = 'pyr_abl_32'
 config['notes'] = ''
 
 # DON'T FORGET TO RESET SSIM LOSS USAGE

configs/config_abl_pyr_32_skirt.py

@@ -1,8 +1,8 @@
 config = dict()
 
 config['gpu'] = '3'
-config['name'] = 'pyr_abl_32_skirt_r1'
-config['notes'] = ''
+config['name'] = 'pyr_abl_32_skirt_2'
+config['notes'] = 'continued from pyr_abl_32_skirt-180k'
 
 # DON'T FORGET TO RESET SSIM LOSS USAGE
 # DON'T FORGET TO CHECK MODEL LOADING
@@ -24,10 +24,7 @@ config['pyramid']['resolutions'] = [32]
 config['pyramid']['pretrained_pyramid'] = ''
 config['pyramid']['final_upscale_enhancer'] = 'checkpoints/32_512_skirt'
 
-config['pretrained_model'] = ''
-config['pretrained_model_iteration'] = ''
-
-config['train_dir'] = '/home/workspace/data/dataset/local-cache/train_skirt'
+config['train_dir'] = '/home/workspace/local-data/train_skirt'
 config['valid_dir'] = '/home/workspace/local-data/valid_skirt'
 config['test_dir'] = '/home/workspace/data/dataset/test_skirt_ready_2'
 config['batch_size'] = 4
@@ -38,7 +35,7 @@ config['pyramid']['static_model'] = 'checkpoints/static_1_skirt'
 config['pyramid']['body_model'] = 'checkpoints/body_1_skirt_2_2'
 config['pyramid']['curvature_model'] = 'checkpoints/curv_1_skirt'
 
-config['dataset_in_memory'] = True
+config['dataset_in_memory'] = False
 config['resolution'] = None
 config['latent_dim'] = 128
 
@@ -68,7 +65,6 @@ config['signature_static'] = { 'uv_static': (512, 256, 3),
 config['pyramid']['is_label'] = False
 config['pyramid']['latent_dim'] = config['latent_dim']
 config['pyramid']['add_noise'] = True
-config['pyramid']['noise_amount'] = 0.001
 
 config['pyramid']['loss_weights'] = [1,1,1,1,1]
 

convert_to_uv_local_single.py

@@ -384,9 +384,9 @@ def test(verts, faces, values):
 
 if __name__ == '__main__':
     parser = argparse.ArgumentParser()
-    parser.add_argument("-f", "--folder", help = "end of range", default='/home/workspace/data/dataset/test_skirt_ready_2')
+    parser.add_argument("-f", "--folder", help = "end of range", default='/home/workspace/local-data/valid')
     parser.add_argument("-s", "--start", help = "start of range", default=0)
-    parser.add_argument("-e", "--end", help = "end of range", default=30000)
+    parser.add_argument("-e", "--end", help = "end of range", default=1500)
     parser.add_argument("-n", "--name", help = "end of range", default='lhunor')
     parser.add_argument("-sk", "--skirt", help = "end of range", default=1)
     args = parser.parse_args()
@@ -408,7 +408,7 @@ if __name__ == '__main__':
     m2uv = np.load('custom_utils/m2uv' + ("_skirt" if args.skirt == 1 else "") + '.npy', allow_pickle=True).item()
     m2uv = m2uv_array(m2uv)
     uv_mask = np.load('custom_utils/mask_256x512' + ("_skirt" if args.skirt == 1 else "") + '.npy')
-    curvature_label_type = '6_25 '
+    curvature_label_type = '6_25'
 
     uv_res = 256
     uv_mask = (cv2.resize(uv_mask * 255.0, (uv_res, uv_res * 2)) / 255).astype(bool)[:, :, np.newaxis]
@@ -436,23 +436,6 @@ if __name__ == '__main__':
 
     # ids = os.listdir(os.path.join(local_folder, 'mesh_static'))[int(args.start):int(args.end)]
     # ids = [id.split('.')[0] for id in ids]
-
-    is_skirt = True if args.skirt == 1 else False
-    skirt_modifier = '_skirt' if is_skirt else ''
-
-    folder = args.folder
-    frames_file = 'frames' + skirt_modifier + '_10p.txt'
-    neighbourhood = 10
-
-    # frames = []
-    # with open(os.path.join(folder, frames_file), 'r') as f:
-    #     lines = f.readlines()
-    #     lines = [line.strip() for line in lines]
-    # frames = lines#[int(args.start):int(args.end)]
-    # ids = [frame.split('_')[0] for frame in frames]
-
-    print(f'params: -f {args.folder} -s {args.start} -e {args.end} -n {args.name} -skirt {args.skirt} -neigh {neighbourhood}')
-
     ids = os.listdir(os.path.join(local_folder, 'pose_shape'))
     ids = [id.split('_')[0] for id in ids]
     ids = sorted(list(set(ids)))[int(args.start):int(args.end)]
@@ -469,16 +452,16 @@ if __name__ == '__main__':
         # plt.show()
         # pass
 
-        frames_len = glob.glob(os.path.join(local_folder, 'pose_shape', id + '_*'))
-        frames_len = len(frames_len)
-        assert frames_len <= 300
+        frames = glob.glob(os.path.join(local_folder, 'pose_shape', id + '_*'))
+        frames = len(frames)
+        assert frames <= 300
 
         # offsets = sio.loadmat(os.path.join(folder, id, garment + '_offsets_static.mat'))['label'][:,:3]
         verts_static = np.load(os.path.join(local_folder, 'mesh_static', id + '.npz'))['mesh_static']
         mask = np.load(os.path.join(local_folder, 'mesh_mask', id + '.npy')).astype(bool)
         # body = readPC2(os.path.join(folder, id, 'Body_posed.pc16'),  True)['V']
         # gt = readPC2(os.path.join(folder, id, garment + '_registered.pc16'),  True)['V']
-        curvature = np.stack([np.load(os.path.join(local_folder, f'mesh_curvature_{neighbourhood}_2',  f'{id}_{i}.npz'))['mesh_curvature'] for i in range(frames_len)])
+        # curvature = np.load(os.path.join(folder, id, 'curvature_label_' + curvature_label_type + '.npy'))
         # mesh_unposed = [np.load(os.path.join(folder, id, 'mesh_unposed',  id + '_' + str(i) + '.npz')) for i in range(gt.shape[0])]
         # mesh_unposed = np.stack([mesh_unposed[i]['mesh_unposed'] for i in range(gt.shape[0])])
         # mesh_unposed_no_shape = [np.load(os.path.join(folder, id, 'mesh_unposed_no_shape',  id + '_' + str(i) + '.npz')) for i in range(gt.shape[0])]
@@ -487,8 +470,8 @@ if __name__ == '__main__':
         # body_no_orient = np.stack([body_no_orient[i]['mesh_posed_body_no_orient'] for i in range(gt.shape[0])])
         # mesh_unposed_no_shape_one_hot = [np.load(os.path.join(local_folder, 'mesh_unposed_no_shape_one_hot',  id + '_' + str(i) + '.npz')) for i in range(frames)]
         # mesh_unposed_no_shape_one_hot = [mesh_unposed_no_shape_one_hot[i]['mesh_unposed_no_shape'] for i in range(frames)]
-        # mesh_posed_no_orient = [np.load(os.path.join(local_folder, 'mesh_posed_no_orient',  id + '_' + str(i) + '.npz')) for i in range(frames)]
-        # mesh_posed_no_orient = [mesh_posed_no_orient[i]['mesh_posed_no_orient'] for i in range(frames)]
+        mesh_posed_no_orient = [np.load(os.path.join(local_folder, 'mesh_posed_no_orient',  id + '_' + str(i) + '.npz')) for i in range(frames)]
+        mesh_posed_no_orient = [mesh_posed_no_orient[i]['mesh_posed_no_orient'] for i in range(frames)]
 
 
         # verts_dynamic = gt
@@ -508,11 +491,11 @@ if __name__ == '__main__':
         # uv_body = convert_to_uv_batch(uv_res, m2uv, uv_map, body[:, :, :], neighbours=3, mask=None, method='rbf', garment_uv_mask=None, garment_uv_mask_border=garment_uv_mask_border).astype(np.float32)
         # uv_posed_body_no_orient = convert_to_uv_batch(uv_res, m2uv, uv_map, body_no_orient[:, :, :], neighbours=3, mask=None, method='rbf', garment_uv_mask=None, garment_uv_mask_border=garment_uv_mask_border).astype(np.float32)
         # uv_gt = convert_to_uv_batch(uv_res, m2uv, uv_map, gt[:, :, :], neighbours=3, mask=mask, method='rbf', garment_uv_mask=garment_uv_mask, garment_uv_mask_border=garment_uv_mask_border).astype(np.float32)
-        uv_curvature = convert_to_uv_batch_label(uv_res, m2uv, uv_map, curvature[:, :], neighbours=3, mask=mask, method='nearest', garment_uv_mask=garment_uv_mask, garment_uv_mask_border=garment_uv_mask_border).astype(np.float32)
+        # uv_curvature = convert_to_uv_batch_label(uv_res, m2uv, uv_map, curvature[:, :], neighbours=3, mask=mask, method='nearest', garment_uv_mask=garment_uv_mask, garment_uv_mask_border=garment_uv_mask_border).astype(np.float32)
         # uv_unposed = convert_to_uv_batch(uv_res, m2uv, uv_map, mesh_unposed[:, :, :], neighbours=3, mask=mask, method='rbf', garment_uv_mask=garment_uv_mask, garment_uv_mask_border=garment_uv_mask_border).astype(np.float32)
         # uv_unposed_no_shape = convert_to_uv_batch(uv_res, m2uv, uv_map, mesh_unposed_no_shape[:, :, :], neighbours=3, mask=mask, method='rbf', garment_uv_mask=garment_uv_mask, garment_uv_mask_border=garment_uv_mask_border).astype(np.float32)
         # uv_unposed_no_shape_one_hot = convert_to_uv_batch(uv_res, m2uv, uv_map, mesh_unposed_no_shape_one_hot, neighbours=3, mask=mask, method='rbf', garment_uv_mask=garment_uv_mask, garment_uv_mask_border=garment_uv_mask_border, id=id)
-        # uv_posed_no_orient = convert_to_uv_batch(uv_res, m2uv, uv_map, mesh_posed_no_orient, neighbours=3, mask=mask, method='rbf', garment_uv_mask=garment_uv_mask, garment_uv_mask_border=garment_uv_mask_border, id=id)
+        uv_posed_no_orient = convert_to_uv_batch(uv_res, m2uv, uv_map, mesh_posed_no_orient, neighbours=3, mask=mask, method='rbf', garment_uv_mask=garment_uv_mask, garment_uv_mask_border=garment_uv_mask_border, id=id)
         # uv_shaped_body = convert_to_uv(uv_res, m2uv, uv_map, shaped_body, neighbours=3, mask=None, method='rbf', garment_uv_mask=None).astype(np.float32)
         print(time.perf_counter() - start)
 
@@ -533,9 +516,9 @@ if __name__ == '__main__':
         # for i in range(uv_gt.shape[0]):
         #     np.savez_compressed(os.path.join(folder, id, 'gt_uv', garment + '_' + str(i) + '.npz'), uv_gt=uv_gt[i, :, :, :])
 
-        os.makedirs(os.path.join(folder, f'uv_curvature_{neighbourhood}_2'), exist_ok=True)
-        for i in range(uv_curvature.shape[0]):
-            np.savez_compressed(os.path.join(folder, f'uv_curvature_{neighbourhood}_2', id + '_' + str(i) + '.npz'), curvature_uv=uv_curvature[i, :, :])
+        # os.makedirs(os.path.join(folder, id, 'curvature_uv'), exist_ok=True)
+        # for i in range(uv_curvature.shape[0]):
+        #     np.savez_compressed(os.path.join(folder, id, 'curvature_uv', garment + '_' + str(i) + '.npz'), curvature_uv=uv_curvature[i, :, :])
 
         # os.makedirs(os.path.join(folder, id, 'uv_unposed'), exist_ok=True)
         # for i in range(uv_unposed.shape[0]):

convnext/models/convnext_tf.py

@@ -2,7 +2,7 @@ from unittest import skip
 import numpy as np
 import tensorflow as tf
 from tensorflow.keras.layers import (Conv2D, Conv2DTranspose, Dense, DepthwiseConv2D,
-                                     GlobalAveragePooling2D, Layer,
+                                     GlobalAveragePooling2D, Layer, Activation, Lambda,
                                      LayerNormalization, Flatten, Reshape, UpSampling2D)
 
 def drop_path(inputs, drop_prob, is_training):
@@ -222,29 +222,31 @@ class ConvNeXtReverse(tf.keras.Model):
 
     def __init__(self, 
                  depths=[3, 3, 9, 3], dims=[96, 192, 384, 768], kernel_size=7,
-                 drop_path_rate=0., layer_scale_init_value=1e-6, head_init_scale=1.,
+                 drop_path_rate=0., layer_scale_init_value=1e-6, head_init_scale=1., learn_weights=False,
                  ):
         super().__init__()
-        self.upsample_layers = []  # stem and 3 intermediate downsampling conv layers
+        self.upsample_layers = [] 
+
         stem = tf.keras.Sequential([
-            Conv2DTranspose(dims[0], kernel_size=4, strides=4, padding='same'),
-            # UpSampling2D((4, 4), interpolation='nearest'),
-            # Conv2D(dims[0], kernel_size=4, strides=1, padding='same'),
-            # Dense(dims[0]),
-            LayerNormalization(epsilon=1e-6)]
-        )
+            LayerNormalization(epsilon=1e-6),
+            Conv2DTranspose(dims[0], kernel_size=2, strides=2, padding='same'),
+        ])
         self.upsample_layers.append(stem)
-        for i in range(len(depths) - 1):
+
+        for i in range(len(depths) - 2):
             downsample_layer = tf.keras.Sequential([
                 LayerNormalization(epsilon=1e-6),
-                Conv2DTranspose(dims[i+1], kernel_size=2, strides=2, padding='same')
-                # UpSampling2D((2,2), interpolation='nearest'),
-                # Conv2D(dims[i+1], kernel_size=2, strides=1, padding='same'),
-                # Dense(dims[i+1]),
+                Conv2DTranspose(dims[i+1], kernel_size=2, strides=2, padding='same'),
             ])
             self.upsample_layers.append(downsample_layer)
 
-        self.stages = []  # 4 feature resolution stages, each consisting of multiple residual blocks
+        downsample_layer = tf.keras.Sequential([
+            Conv2DTranspose(dims[i+2], kernel_size=2, strides=2, padding='same'),
+            LayerNormalization(epsilon=1e-6),
+        ])
+        self.upsample_layers.append(downsample_layer)
+
+        self.stages = []  
         dp_rates = [x for x in np.linspace(0, drop_path_rate, sum(depths))]
         cur = 0
         for i in range(len(depths)):
@@ -255,12 +257,19 @@ class ConvNeXtReverse(tf.keras.Model):
             self.stages.append(stage)
             cur += depths[i]
 
-        self.last = Dense(3, activation='tanh')
+        if not learn_weights:
+            self.last = Dense(3, activation='tanh')
+            # self.last = Activation('tanh')
+        else:
+            self.last = Activation('softmax')
+            # self.last = Dense(24, activation='softmax')
+
 
     def call(self, x, training):
         for i in reversed(range(len(self.upsample_layers))):
             x = self.upsample_layers[i](x, training=training)
             x = self.stages[i](x, training=training)
+
         x = self.last(x, training=training)
         return x
 

curvature_analysis.py

@@ -1,235 +0,0 @@
-import os
-import sys
-import tqdm
-import argparse
-import random
-import string
-import time
-import numpy as np
-import trimesh as tm
-import cmapy as cm
-import scipy as sp
-import scipy.io as sio
-import plotly.graph_objects as go
-from pyntcloud import PyntCloud
-from scipy.sparse import csr_matrix, coo_matrix
-from scipy.sparse.csgraph import floyd_warshall, dijkstra
-from plotly.subplots import make_subplots
-from custom_utils.custom_utils import _maskFaces
-
-from custom_utils.supersmpl_io import readPC2, readPC2Frame, writePC2, readOBJ
-from custom_utils.custom_utils import _maskFaces
-
-def export_to_ply(mesh, file):
-    ply = tm.exchange.ply.export_ply(mesh, encoding='binary', vertex_normal=True, include_attributes=True)
-    output_file = open(file, "wb+")
-    output_file.write(ply)
-    output_file.close()
-
-
-def get_closest_n_points(verts, idx, n):
-    dist = sp.spatial.distance.cdist(verts[idx, :], verts)
-    dist[dist == 0] = 1e9
-    idx_sort = np.argsort(dist, axis=-1)
-    closest = idx_sort[:, :n]
-    return closest
-
-
-def calculate_dist(folder, neighbourhood):
-    out = dict()
-    frames = sorted(os.listdir(os.path.join(folder, 'mesh_posed')))[int(args.start):int(args.end)]
-
-    for frame in tqdm.tqdm(frames):
-        id = frame.split('_')[0]
-        if id in out.keys():
-            continue
-
-        mask = np.load(os.path.join(folder, 'mesh_mask', f'{id}.npy')).astype(bool)
-        k_neighbors = np.argsort(dist[mask, :][:, mask], axis=-1)[:, :neighbourhood] #cloud.get_neighbors(k=neighbourhood)
-        out[id] = k_neighbors
-
-    return out
-
-
-def histedges_equalN(x, nbin):
-    npt = len(x)
-    return np.interp(np.linspace(0, npt, nbin + 1),
-                     np.arange(npt),
-                     np.sort(x))
-
-
-def get_bins(values, nr_of_bins):
-    flattened = []
-    for c in values:
-        flattened.extend(c.flatten())
-    flattened = np.array(flattened)
-    bins = histedges_equalN(flattened, nr_of_bins)
-    return bins
-
-
-def generate_curvatures(folder, frame, bins, neighbourhoods=[25], nr_of_labels=[6]):
-    id = frame.split('_')[0]
-    frame_nr = int(frame.split('_')[1].split('.')[0])
-
-    mask = np.load(os.path.join(folder, 'mesh_mask', f'{id}.npy')).astype(bool)
-    _, faces = _maskFaces(np.zeros((14475,3)), F, mask)
-    v = np.load(os.path.join(folder, 'mesh_posed', f'{id}_{frame_nr}.npz'))['mesh_posed'][mask,:]
-    
-    m = tm.Trimesh(v, faces, process=False, validate=False)
-
-    outliers = np.array([len(v) for v in m.vertex_neighbors]) == 0
-    outliers = np.nonzero(outliers)[0]
-    outliers_n_neighbours = get_closest_n_points(v, outliers, 2)
-    outliers_faces = np.concatenate((outliers[:, np.newaxis], outliers_n_neighbours), axis=-1)
-    faces = np.concatenate((faces, outliers_faces), axis=0)
-
-    verts = v
-
-    m = tm.Trimesh(verts, faces, process=False, validate=False)
-    export_to_ply(m, temp_file)
-
-    cloud = PyntCloud.from_file(temp_file)
-
-    curvatures = []
-    for neighbourhood, nr_labels in zip(neighbourhoods, nr_of_labels):
-        k_neighbors = np.argsort(dist[mask, :][:, mask], axis=-1)[:, :neighbourhood] #cloud.get_neighbors(k=neighbourhood)
-        #k_neighbors = k_neighbors_cache[id] # np.argsort(dist[mask, :][:, mask], axis=-1)[:, :neighbourhood] #cloud.get_neighbors(k=neighbourhood)
-        ev = cloud.add_scalar_field("eigen_values", k_neighbors=k_neighbors)
-        cloud.add_scalar_field("curvature", ev=ev)
-        curvature = np.array(cloud.points["curvature(" + str(neighbourhood+1) + ")"])
-        
-        bins_local = bins[neighbourhood] if bins is not None else get_bins(curvature, nr_labels)
-        labels = np.linspace(0, bins_local.shape[0] - 2, bins_local.shape[0] - 1)
-
-        frame_labels = np.zeros((curvature.shape[0]), dtype=np.float32)
-        for j in range(bins_local.shape[0] - 2):
-            frame_labels[(curvature >= bins_local[j]) * (curvature < bins_local[j+1])] = labels[j]
-        frame_labels[curvature >= bins_local[-2]] = labels[-1]
-
-        curvatures.append(frame_labels)
-        
-    return curvatures
-
-
-def visualize_curvature_labels(folder, frame, bins, neighbourhoods, nr_of_labels):
-    id = frame.split('_')[0]
-    frame_nr = frame.split('_')[1].split('.')[0]
-
-    mask = np.load(os.path.join(folder, 'mesh_mask', f'{id}.npy')).astype(bool)
-    _, faces = _maskFaces(np.zeros((14475,3)), F, mask)
-    verts = np.load(os.path.join(folder, 'mesh_posed', f'{id}_{frame_nr}.npz'))['mesh_posed'][mask,:]
-    
-    curvature_labels_all = generate_curvatures(folder, frame, bins, neighbourhoods, nr_of_labels)
-    colors_binned_all = []
-
-    for curvature_labels in curvature_labels_all:
-        colors = np.array([cm.color('jet', 1 - i) for i in np.linspace(0, 1, int(curvature_labels.max()+1))])
-        colors_binned = np.zeros((curvature_labels.shape[0], 3))
-        for i in range(int(curvature_labels.max())+1):
-            # print(np.count_nonzero(curvature_labels == i))
-            colors_binned[curvature_labels == i, :] = colors[i]
-        colors_binned_all.append(colors_binned)
-
-
-    fig = make_subplots(rows=1, cols=len(colors_binned_all)+1, start_cell="top-left", specs = [ [{ 'type': 'scene' } for _ in range(len(colors_binned_all)+1)] ])
-
-    colors = np.ones((verts.shape[0],3))*np.array([255,200,200])[None,:]
-
-    fig.add_trace(go.Mesh3d(
-                # 8 vertices of a cube
-                x=verts[:,0],
-                y=verts[:,1],
-                z=verts[:,2],
-                # i, j and k give the vertices of triangles
-                i = faces[:,0],
-                j = faces[:,1],
-                k = faces[:,2],
-                vertexcolor=colors,
-                lighting={ 'ambient':0.9, 'diffuse':0.5, 'roughness':0.5 }
-            ),
-            row=1, col=1)
-
-    for i, colors_binned in enumerate(colors_binned_all):
-        fig.add_trace(go.Mesh3d(
-                    # 8 vertices of a cube
-                    x=verts[:,0],
-                    y=verts[:,1],
-                    z=verts[:,2],
-                    # i, j and k give the vertices of triangles
-                    i = faces[:,0],
-                    j = faces[:,1],
-                    k = faces[:,2],
-                    vertexcolor=colors_binned,
-                    # lighting={ 'ambient':0.8, 'diffuse':0.5, 'roughness':0.5 }
-                ),
-                row=1, col=i+2)
-    
-
-
-    fig.update_layout(scene_aspectmode='manual', scene_aspectratio=dict(x=1, y=1, z=1),
-                    scene2_aspectmode='manual', scene2_aspectratio=dict(x=1, y=1, z=1),
-                    scene3_aspectmode='manual', scene3_aspectratio=dict(x=1, y=1, z=1),
-                    scene4_aspectmode='manual', scene4_aspectratio=dict(x=1, y=1, z=1),
-                    # scene5_aspectmode='manual', scene5_aspectratio=dict(x=1, y=1, z=1),
-                    )
-    helper = dict(xaxis = dict(range=[-1,1], showbackground=False, showticklabels=False, showaxeslabels=False, showspikes=False, visible=False),
-                yaxis = dict(range=[-1,1], showbackground=False, showticklabels=False, showaxeslabels=False, showspikes=False, visible=False),
-                zaxis = dict(range=[-1,1], showbackground=False, showticklabels=False, showaxeslabels=False, showspikes=False, visible=False),)
-        
-    fig.update_layout(scene = helper,
-                        scene2 = helper,
-                        scene3 = helper,
-                        scene4 = helper,
-                        # scene5 = helper,
-                        )
-
-
-    # meshes = [go.Mesh3d(
-    #             x=x[:,0],
-    #             y=x[:,1],
-    #             z=x[:,2],
-    #             i = faces[:,0],
-    #             j = faces[:,1],
-    #             k = faces[:,2],
-    #             vertexcolor=colors_binned
-    #             )]
-
-    # fig = go.Figure(data=meshes)
-    # fig.update_layout(scene_aspectmode='manual', scene_aspectratio=dict(x=1, y=1, z=1))
-    # fig.update_layout(
-    #     scene = dict(
-    #         xaxis = dict(nticks=4, range=[-1,1],),
-    #                     yaxis = dict(nticks=4, range=[-1,1],),
-    #                     zaxis = dict(nticks=4, range=[-1,1],),)
-    #                     )
-
-    fig.show()
-
-    print()
-
-
-if __name__ == '__main__':
-
-    is_skirt = True
-    skirt_modifier = '_skirt' if is_skirt else ''
-    F = np.load("custom_utils/smpl_faces" + skirt_modifier + ".npy").astype(np.int32)
-    # k_neighbours(k=25)
-
-    folder = '/home/workspace/local-data/valid_skirt'
-    bins = dict()
-    bins[10] = np.load(f'custom_data/train_bins_skirt_10.npy')
-    bins[25] = np.load(f'custom_data/train_bins_skirt.npy')
-    bins[100] = np.load(f'custom_data/train_bins_skirt_100.npy')
-
-    bins = None
-
-
-    nr_of_labels = 6
-    neighbourhood = 50
-    temp_file = '/home/workspace/local-data/temp/' + ''.join(random.choice(string.ascii_lowercase) for i in range(10)) + '.ply'
-    if not is_skirt:
-        dist = np.load('custom_data/dijkstra.npy')
-    else:
-        dist = np.load('custom_data/dijkstra_skirt.npy')
-
-    visualize_curvature_labels(folder, '02572_1', bins, neighbourhoods=[25, 25, 25], nr_of_labels=[3,6,12])

curvature_label_parallel.py

@@ -4,17 +4,15 @@ import os
 
 if __name__ == '__main__':
 
-    # folder = '/home/workspace/data/dataset/test_skirt_ready_2'
-    # folder = '/home/workspace/data/dataset/local-cache/train_skirt'
-    folder = '/home/workspace/local-data/valid_skirt'
-    ids = os.listdir(folder + '/mesh_posed')
+    folder = '/home/workspace/local-data/cape/train/male'
+    out_folder = '/home/workspace/local-data/cape_processed/train/male'
+    ids = os.listdir(folder)
 
     count = 0
-    step = 10000
+    step = 1
 
-    while count < 20*step:
-    # while count < 10000:
+    while count < len(ids):
         # os.system('nohup python MeshUtils/curvature_labels.py -f ' + folder + ' -s ' + str(count) + ' -e ' + str(count + step) + ' -n ' + 'curv_train_' + str(count) + '_' + str(count+step) + ' > curv_train_' + str(count) + '_' + str(count+step) + '.out' + ' 2>&1 &')
-        os.system('nohup python curvature_labels.py -f ' + folder + ' -s ' + str(0) + ' -e ' + str(0 + step) + ' -n ' + 'speed_test_' + str(count) + '_' + str(count+step) + ' > nohup/speed/speed_test_' + str(count) + '_' + str(count+step) + '.out' + ' 2>&1 &')
+        os.system('nohup python curvature_labels_cape.py -if ' + folder + ' -of ' + out_folder + ' -s ' + str(count) + ' -e ' + str(count + step) + ' -n ' + 'curv_gen_2_cape_train_male_' + str(count) + '_' + str(count+step) + ' > nohup/curv_gen_2_cape_train_male_' + str(count) + '_' + str(count+step) + '.out' + ' 2>&1 &')
         # os.system('python Data/convert_to_uv.py -f ' + folder + ' -s ' + str(count) + ' -e ' + str(count + step) + '')
         count += step

curvature_labels.py

@@ -4,7 +4,6 @@ import tqdm
 import argparse
 import random
 import string
-import time
 import numpy as np
 import trimesh as tm
 import cmapy as cm
@@ -41,8 +40,6 @@ def export_to_ply(mesh, file):
     output_file.close()
 
 
-
-
 def get_closest_n_points(verts, idx, n):
     dist = sp.spatial.distance.cdist(verts[idx, :], verts)
     dist[dist == 0] = 1e9
@@ -83,65 +80,67 @@ def k_neighbours(k):
     pass
 
 
-def calculate_dist(folder, neighbourhood, frames):
-    out = dict()
-    # frames = frames[int(args.start):int(args.end)]
+def generate_curvatures(folder, neighbourhood):
 
-    for frame in tqdm.tqdm(frames):
-        id = frame.split('_')[0]
-        if id in out.keys():
+    ids = os.listdir(folder)[int(args.start):int(args.end)]
+
+    curvatures_all = []
+
+    for id in tqdm.tqdm(ids):
+        garment_dir = os.path.join(folder, id)
+
+        if not os.path.isdir(garment_dir):
             continue
 
-        mask = np.load(os.path.join(folder, 'mesh_mask', f'{id}.npy')).astype(bool)
-        k_neighbors = np.argsort(dist[mask, :][:, mask], axis=-1)[:, :neighbourhood] #cloud.get_neighbors(k=neighbourhood)
-        out[id] = k_neighbors
+        # if os.path.exists(garment_dir + '/curvature_25_raw.npy'):
+        #     continue
 
-    return out
+        curvatures_garment = []
 
-def generate_curvatures(folder, neighbourhood, frames):
+        garments = [f.replace('.pc16','') for f in os.listdir(garment_dir) if f.find('_') == -1 and f != 'info.mat' and not f.endswith('.obj')]
+        # assert len (garments) == 1
+        if len (garments) != 1:
+            continue
+        garment = garments[0]
     
-    # ids = os.listdir(folder)[int(args.start):int(args.end)]
-    # frames = frames[int(args.start):int(args.end)]
-    os.makedirs(os.path.join(folder, f'mesh_curvature_raw_{neighbourhood}'), exist_ok=True)
+        bodies = readPC2(os.path.join(folder, id, 'Body_posed.pc16'), True)['V']
+        offsetss = readPC2(os.path.join(folder, id, garment + '_registered.pc16'), True)['V']
+        mask = np.squeeze(sio.loadmat(os.path.join(garment_dir, garment + '_mask.mat'))['mask'].astype(bool))
         
-    k_neighbors_cache = calculate_dist(folder, neighbourhood, frames)
+        _, faces = _maskFaces(bodies[0, :, :], F, mask)
+        v = bodies[0, mask, :] + offsetss[0, mask, :]
+        m = tm.Trimesh(v, faces, process=False, validate=False)
 
-    # for frame in tqdm.tqdm(frames):
+        outliers = np.array([len(v) for v in m.vertex_neighbors]) == 0
+        outliers = np.nonzero(outliers)[0]
+        outliers_n_neighbours = get_closest_n_points(v, outliers, 2)
+        outliers_faces = np.concatenate((outliers[:, np.newaxis], outliers_n_neighbours), axis=-1)
+        faces = np.concatenate((faces, outliers_faces), axis=0)
 
-    #     id = frame.split('_')[0]
-    #     frame_nr = frame.split('_')[1].split('.')[0]
+        step = 0
+        for body, offsets in zip(bodies, offsetss):
+            verts = body + offsets
+            verts = verts[mask, :]
 
-    #     # bodies = readPC2(os.path.join(folder, id, 'Body_posed.pc16'), True)['V']
-    #     # offsetss = readPC2(os.path.join(folder, id, garment + '_registered.pc16'), True)['V']
-    #     mask = np.load(os.path.join(folder, 'mesh_mask', f'{id}.npy')).astype(bool)
-    #     _, faces = _maskFaces(np.zeros((14475,3)), F, mask) #np.load(os.path.join(folder, 'faces', f'{id}.npy'))
-    #     v = np.load(os.path.join(folder, 'mesh_posed', f'{id}_{frame_nr}.npz'))['mesh_posed'][mask,:]
+            m = tm.Trimesh(verts, faces, process=False, validate=False)
+            export_to_ply(m, temp_file)
 
-    #     m = tm.Trimesh(v, faces, process=False, validate=False)
+            cloud = PyntCloud.from_file(temp_file)
+            # cloud.plot(mesh=True)
 
-    #     outliers = np.array([len(v) for v in m.vertex_neighbors]) == 0
-    #     outliers = np.nonzero(outliers)[0]
-    #     outliers_n_neighbours = get_closest_n_points(v, outliers, 2)
-    #     outliers_faces = np.concatenate((outliers[:, np.newaxis], outliers_n_neighbours), axis=-1)
-    #     faces = np.concatenate((faces, outliers_faces), axis=0)
+            k_neighbors = np.argsort(dist[mask, :][:, mask], axis=-1)[:, :neighbourhood] #cloud.get_neighbors(k=neighbourhood)
+            ev = cloud.add_scalar_field("eigen_values", k_neighbors=k_neighbors)
+            cloud.add_scalar_field("curvature", ev=ev)
+            curvature = np.array(cloud.points["curvature(" + str(neighbourhood+1) + ")"])
+            curvatures_garment.append(curvature)
 
-    #     verts = v
+            print(step)
+            step += 1
 
-    #     m = tm.Trimesh(verts, faces, process=False, validate=False)
-    #     export_to_ply(m, temp_file)
+        # curvatures_all.append(np.array(curvatures_garment))
+        np.save(garment_dir + '/curvature_25_raw.npy', np.array(curvatures_garment))
 
-    #     cloud = PyntCloud.from_file(temp_file)
-
-    #     k_neighbors = k_neighbors_cache[id] # np.argsort(dist[mask, :][:, mask], axis=-1)[:, :neighbourhood] #cloud.get_neighbors(k=neighbourhood)
-    #     ev = cloud.add_scalar_field("eigen_values", k_neighbors=k_neighbors)
-    #     cloud.add_scalar_field("curvature", ev=ev)
-    #     curvature = np.array(cloud.points["curvature(" + str(neighbourhood+1) + ")"])
-    #     out = np.zeros((14475), dtype=np.float32)
-    #     out[mask] = curvature
-        
-    #     np.savez_compressed(os.path.join(folder, f'mesh_curvature_raw_{neighbourhood}', f'{id}_{frame_nr}.npz'), mesh_curvature_raw=out)
-
-    return None
+    return curvatures_all
 
 
 def get_bins(values, nr_of_bins):
@@ -153,23 +152,41 @@ def get_bins(values, nr_of_bins):
     return bins
 
 
-def generate_curvature_labels(folder, bins, curvatures, frames, neighbourhood):
+def generate_curvature_labels(folder, bins, curvatures):
 
-    os.makedirs(os.path.join(folder, f'mesh_curvature_{neighbourhood}_2'), exist_ok=True)
+    ids = os.listdir(folder)#[:10]
     labels = np.linspace(0, bins.shape[0] - 2, bins.shape[0] - 1)
 
-    for i, frame in enumerate(tqdm.tqdm(frames)):
-        # id = frame.split('_')[0]
-        # mask = np.load(os.path.join(folder, 'mesh_mask', f'{id}.npy'))
-        # print(i) 
+    i = 0
+    for id in tqdm.tqdm(ids):
+        garment_dir = os.path.join(folder, id)
+
+        if not os.path.isdir(garment_dir):
+            continue
+
+        garments = [f.replace('.pc16','') for f in os.listdir(garment_dir) if f.find('_') == -1 and f != 'info.mat' and not f.endswith('.obj')]
+        # assert len (garments) == 1
+        if len (garments) != 1:
+            continue
+        garment = garments[0]
+        mask = np.squeeze(sio.loadmat(os.path.join(garment_dir, garment + '_mask.mat'))['mask'].astype(bool))
+
         curvature = curvatures[i]
+        i += 1
 
-        frame_labels = np.zeros((curvature.shape[0]), dtype=np.float32)
-        for j in range(bins.shape[0] - 2):
-            frame_labels[(curvature >= bins[j]) * (curvature < bins[j+1])] = labels[j]
-        frame_labels[curvature >= bins[-2]] = labels[-1]
+        curvature_label = np.zeros((curvature.shape[0], curvature.shape[1]))
+        frame = 0
+        for frame in range(curvature.shape[0]):
+            frame_labels = np.zeros((curvature.shape[1]), dtype=np.float32)
+            for j in range(bins.shape[0] - 2):
+                frame_labels[(curvature[frame, :] >= bins[j]) * (curvature[frame, :] < bins[j+1])] = labels[j]
+            frame_labels[curvature[frame, :] >= bins[-2]] = labels[-1]
+            curvature_label[frame, :] = frame_labels
+            frame += 1
 
-        np.savez_compressed(os.path.join(folder, f'mesh_curvature_{neighbourhood}_2', f'{frame}.npz'), mesh_curvature=frame_labels)
+        unmasked_label = np.zeros((curvature.shape[0], 14475), dtype=np.float32)
+        unmasked_label[:, mask] = curvature_label
+        np.save(os.path.join(garment_dir, "curvature_label_" + str(nr_of_labels) + "_" + str(neighbourhood) + ".npy"), unmasked_label)
         # writePC2(os.path.join(garment_dir, "curvature_label_" + str(nr_of_labels) + "_" + str(neighbourhood) + ".pc16"), unmasked_label, True)
 
 
@@ -240,10 +257,24 @@ def visualize_curvature_labels(folder):
         print()
 
 
-def read_raw_curvatures(folder, frames, neighbourhood):
+def read_raw_curvatures(folder):
+
+    ids = os.listdir(folder)[int(args.start):int(args.end)]
+
     curvatures_all = []
-    for frame in tqdm.tqdm(frames):
-        curv = np.load(os.path.join(folder, f'mesh_curvature_raw_{neighbourhood}', f'{frame}.npz'))['mesh_curvature_raw']
+
+    for id in tqdm.tqdm(ids):
+        garment_dir = os.path.join(folder, id)
+
+        if not os.path.isdir(garment_dir):
+            continue
+
+        garments = [f.replace('.pc16','') for f in os.listdir(garment_dir) if f.find('_') == -1 and f != 'info.mat' and not f.endswith('.obj')]
+        # assert len (garments) == 1
+        if len (garments) != 1:
+            continue
+
+        curv = np.load(garment_dir + '/curvature_25_raw.npy')
         curvatures_all.append(curv)
     
     return curvatures_all
@@ -251,46 +282,28 @@ def read_raw_curvatures(folder, frames, neighbourhood):
 
 if __name__ == '__main__':
     parser = argparse.ArgumentParser()
-    parser.add_argument("-f", "--folder", help = "process the given folder", default=r'/home/workspace/data/dataset/local-cache/train_skirt')
+    parser.add_argument("-f", "--folder", help = "process the given folder", default=r'/home/workspace/data/dataset/test')
     parser.add_argument("-s", "--start", help = "start of range", default=0)
-    parser.add_argument("-e", "--end", help = "end of range", default=30000)
+    parser.add_argument("-e", "--end", help = "end of range", default=1500)
     parser.add_argument("-n", "--name", help = "end of range", default="lhunor")
     args = parser.parse_args()
 
-    is_skirt = True
-    skirt_modifier = '_skirt' if is_skirt else ''
-    F = np.load("custom_utils/smpl_faces" + skirt_modifier + ".npy").astype(np.int32)
+    F = np.load("FeatureLines/superSMPL/smpl_faces.npy")
     # k_neighbours(k=25)
 
     folder = args.folder
-    frames_file = 'frames' + skirt_modifier + '_10p.txt'
-
     nr_of_labels = 6
-    neighbourhood = 100
-    temp_file = '/home/workspace/local-data/temp/' + ''.join(random.choice(string.ascii_lowercase) for i in range(10)) + '.ply'
-    if not is_skirt:
-        dist = np.load('custom_data/dijkstra.npy')
-    else:
-        dist = np.load('custom_data/dijkstra_skirt.npy')
+    neighbourhood = 25
+    temp_file = 'temp/' + ''.join(random.choice(string.ascii_lowercase) for i in range(10)) + '.ply'
+    dist = np.load('MeshUtils/dijsktra.npy')
+    # dist = np.load('MeshUtils/dijkstra_skirt.npy')
 
-    print('SKIRT' if is_skirt else 'NOT SKIRT')
-    print(f'params: -f {args.folder} -s {args.start} -e {args.end} -n {args.name} -skirt {is_skirt} -neigh {neighbourhood}')
-
-    frames = sorted(os.listdir(os.path.join(folder, 'mesh_posed')))[int(args.start):int(args.end)]
-    frames = [frame.split('.')[0] for frame in frames]
-
-    # frames = []
-    # with open(os.path.join(folder, frames_file), 'r') as f:
-    #     lines = f.readlines()
-    #     lines = [line.strip() for line in lines]
-    # frames = lines[int(args.start):int(args.end)]
-
-    generate_curvatures(folder, neighbourhood, frames)
-    # curvatures = read_raw_curvatures(folder, frames, neighbourhood)
+    generate_curvatures(folder, neighbourhood)
+    # curvatures = read_raw_curvatures(folder)
     # bins = get_bins(curvatures, nr_of_labels)
-    # np.save(f'custom_data/train_bins_skirt_{neighbourhood}.npy', bins)
-    # bins = np.load(f'custom_data/train_bins_skirt_{neighbourhood}.npy')
-    # generate_curvature_labels(folder, bins, curvatures, frames, neighbourhood)
+    # np.save('train_bins_skirt.npy', bins)
+    # bins = np.load('train_bins.npy')
+    # generate_curvature_labels(folder, bins, curvatures)
     # visualize_curvature_labels(folder)
 
     pass

custom_utils/custom_utils.py

@@ -2,6 +2,7 @@ import json
 import numpy as np
 import tensorflow as tf
 import scipy as sp
+import cmapy as cm
 import plotly.graph_objects as go
 from plotly.subplots import make_subplots
 
@@ -216,6 +217,35 @@ def plot_3d(mesh_gt, mesh_pred_unposed, faces, collision, collision_faces, colli
     return fig
 
 
+def plot_weights(weights, body, faces):
+    fig = go.Figure()
+    colors = np.array([cm.color('jet', 1 - w) for w in weights.numpy()])
+
+    # if flip_xy:
+    #     mesh_gt = flip_axis(mesh_gt)
+    #     mesh_pred_unposed = flip_axis(mesh_pred_unposed)
+    #     collision = flip_axis(collision, ind=14475)
+
+    fig.add_trace(go.Mesh3d(
+                x=body[:,0],
+                y=body[:,2],
+                z=body[:,1],
+                i = faces[:,0],
+                j = faces[:,1],
+                k = faces[:,2],
+                vertexcolor=colors
+            ))
+    
+
+    fig.update_layout(scene_aspectmode='manual', scene_aspectratio=dict(x=1, y=1, z=1),)
+    helper = dict(xaxis = dict(nticks=4, range=[-1,1],),
+                yaxis = dict(nticks=4, range=[-1,1],),
+                zaxis = dict(nticks=4, range=[-1,1],),)
+    fig.update_layout(scene = helper,)
+
+    return fig
+
+
 def plot_3d_collision(gt, collision_1, collision_2, collision_faces, collision_color, flip_xy=False):
     fig = make_subplots(rows=1, cols=3, start_cell="top-left", specs = [ [{ 'type': 'scene' } for _ in range(3)] ])
 

custom_utils/smpl.py

@@ -406,7 +406,8 @@ class SMPL:
         return T_out, J_out
 
 
-    def run_garment_with_weights(self, R, betas, v_cloth, weights, J=None):
+    def run_garment_with_weights(self, pose, betas, v_cloth, weights, J=None):
+        R = self.run_rodrigues(pose)
         
         if J is None:
             J = self.get_joints_template(betas)
@@ -430,13 +431,12 @@ class SMPL:
             J = tf.gather(J, tf.constant([0, 1, 2], tf.int32), axis=1)
             
             T = tf.tensordot(weights, results, axes=((1), (0)))
-            rest_shape_h = tf.concat((v_cloth, tf.ones((v_cloth.get_shape().as_list()[0], 1), dtype=tf.float32)), axis=1)
+            rest_shape_h = tf.concat((v_cloth, tf.ones((v_cloth.shape[0], 1), dtype=tf.float32)), axis=1)
             v = tf.matmul(T, tf.reshape(rest_shape_h, (-1, 4, 1)))
             v = tf.reshape(v, (-1, 4))[:, :3]
 
             return v, tf.squeeze(J)
 
-        # gender = tf.cast(tf.greater_equal(betas[:, 10] , 0), tf.int32)
         T_out, J_out = tf.map_fn(single_run, (R, J, v_cloth, weights), (tf.float32, tf.float32))
         
         J0 = tf.reshape(J_out[:,0,:], (-1, 1, 3))

cvae.py

@@ -38,14 +38,14 @@ else:
 from losses import collision_ratio, kl_loss, normal_loss #, concept_loss
 # from losses import collision_penalty as collision_penalty
 from losses import collision_loss as collision_penalty
-from custom_utils.custom_utils import batch_to_dict, load_model, plot_3d, UV2Mesh, get_summary_html, maskFacesBatch, _maskFaces, plot_3d_collision
+from custom_utils.custom_utils import batch_to_dict, load_model, plot_3d, UV2Mesh, UV2MeshLabel, get_summary_html, maskFacesBatch, _maskFaces, plot_3d_collision, plot_weights
 from dataset import DatasetFactory, StaticDataset
 from custom_utils.smpl import SMPL
 from models.cvae_model import CVAENew as CVAE
 
 
 def init_wandb():
-    run = wandb.init(project='ablation', name=config['name'], notes=config['notes'], dir='/wandb', tags=config['tags'])
+    run = wandb.init(project='ablation', name=config['name'], notes=config['notes'], dir='/wandb')
     artifact = wandb.Artifact('code', type='code')
     artifact.add_file('cvae.py')
     artifact.add_file('models/cvae_model.py')
@@ -58,12 +58,11 @@ def init_wandb():
     artifact.add_file('convnext/models/convnext_tf.py')
     config_file_names = [key for key in sys.modules.keys()  if key.startswith('configs.')]
     for config_file_name in config_file_names:
-        file_name = '/'.join(config_file_name.split('.')) + '.py'
-        if os.path.exists(file_name):
-            artifact.add_file(file_name)
+        artifact.add_file('/'.join(config_file_name.split('.')) + '.py')
     run.log_artifact(artifact)
 
 uv2mesh = UV2Mesh(res=256, is_skirt=config['is_skirt'], is_adaptive=False, is_smpl_orig=config['is_cape'])
+uv2mesh_label = UV2MeshLabel(res=256, is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape'])
 
 
 def kl_loss(mean, logvar):
@@ -73,9 +72,15 @@ def kl_loss(mean, logvar):
     return kl_loss
 
 
+def blend_weights_reg(pred_w, gender=None):
+    orig = smpl.weights
+    l1 = tf.reduce_mean(tf.abs(pred_w - orig[None, 0, :, :]))
+    return l1
+
+
 # 3d loss on posed !!!!!!!!!!!!
 
-# @tf.function
+@tf.function
 def train_step(batch):
 
     with tf.GradientTape() as tape:
@@ -84,9 +89,10 @@ def train_step(batch):
         else:
             mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed']
 
-        pred, mean, logvar = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=True)
+        pred, mean, logvar, weights = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=True)
 
         mesh_pred = uv2mesh(pred)
+        mesh_weigths = uv2mesh_label(weights)
 
         if config['use_skinning']:
             shape = batch['pose_shape'][:, 72:]
@@ -96,25 +102,31 @@ def train_step(batch):
             mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis]
             mesh_pred_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)
         else:
-            mesh_pred_posed = mesh_pred
+            shape = batch['pose_shape'][:, 72:]
+            gender = tf.cast(tf.greater_equal(shape[:, 10] , 0.5), tf.int32)
+            shape_offsets = tf.stack([tf.gather(tf.tensordot(shape[i,:10][tf.newaxis, :], smpl.shapedirs[gender[i]], axes=[[1], [2]])[0,:,:], smpl.to_keep, axis=0) for i in range(shape.shape[0])])
+
+            mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis]
+            mesh_pred_posed = smpl.run_garment_with_weights(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped, mesh_weigths)
 
         # is the output already masked?
 
         e_loss = tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask']))
         c_loss, c_ratio = collision_penalty(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask'])
         c_loss, c_ratio = tf.reduce_mean(c_loss), tf.reduce_mean(c_ratio)
-        l2_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(((uv_orig - pred) ** 2), axis=-1), axis=[1, 2]))
+        # l2_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(((uv_orig - pred) ** 2), axis=-1), axis=[1, 2]))
         l2_mesh_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (batch['mesh_posed'] - mesh_pred_posed) ** 2, axis=-1), axis=-1))
         n_loss = normal_loss(mesh_pred_posed, batch['mesh_posed'], batch['mesh_mask'], is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape'])
         # conc_loss = concept_loss(pred, batch['uv_unposed'])
         kl = kl_loss(mean, logvar)
+        weights_l = blend_weights_reg(mesh_weigths)
 
-        reconstr_loss = l2_loss
+        reconstr_loss = l2_mesh_loss + 1e-6 * weights_l
         if config['use_extra_losses']:
             if 'block_collision_loss' in config.keys() and config['block_collision_loss'] == True:
-                reconstr_loss = reconstr_loss + l2_mesh_loss + (e_loss) * config['reg_loss_coeff']
+                reconstr_loss = reconstr_loss + (e_loss) * config['reg_loss_coeff']
             else:
-                reconstr_loss = reconstr_loss + l2_mesh_loss + (e_loss + c_loss) * config['reg_loss_coeff']
+                reconstr_loss = reconstr_loss + (e_loss + c_loss) * config['reg_loss_coeff']
         if config['use_norm_loss'] and step > 2000:
             reconstr_loss = reconstr_loss + n_loss * config['reg_loss_coeff']
 
@@ -124,14 +136,14 @@ def train_step(batch):
         logvar = tf.reduce_mean(logvar)
 
     # ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(pred + 5, batch['uv_unposed'] + 5, max_val=10, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1)))
-    metric = tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig - mesh_pred) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask'])
+    metric = tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig - mesh_pred_posed) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask'])
     gradients = tape.gradient(loss, model.trainable_variables)
     optimizer.apply_gradients(zip(gradients, model.trainable_variables))
     return { 'train/loss': loss, 'train/edge_loss': e_loss, 'train/collision_loss': c_loss, 'train/euclid_error': metric,
              'train/reconstr_loss': reconstr_loss, 'train/collision_ratio': c_ratio,
              'train/mean': mean, 'train/logvar': logvar, 'train/kl_loss': kl, 'train/var': np.e ** logvar,
-             'train/l2_loss': l2_loss, 'train/l2_mesh_loss': l2_mesh_loss, 'train/normal_loss': n_loss,
-             # 'train/ms_ssim': ms_ssim, 
+             'train/l2_mesh_loss': l2_mesh_loss, 'train/normal_loss': n_loss, 'train/weights_loss': weights_l,
+             # 'train/ms_ssim': ms_ssim, 'train/l2_loss': l2_loss, 
             }
 
 
@@ -142,9 +154,10 @@ def valid_step(batch):
     else:
         mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed']
 
-    pred, mean, logvar = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=False)
+    pred, mean, logvar, weights = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=False)
 
     mesh_pred = uv2mesh(pred)
+    mesh_weigths = uv2mesh_label(weights)
 
     if config['use_skinning']:
         shape = batch['pose_shape'][:, 72:]
@@ -154,22 +167,28 @@ def valid_step(batch):
         mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis]
         mesh_pred_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)
     else:
-        mesh_pred_posed = mesh_pred
+        shape = batch['pose_shape'][:, 72:]
+        gender = tf.cast(tf.greater_equal(shape[:, 10] , 0.5), tf.int32)
+        shape_offsets = tf.stack([tf.gather(tf.tensordot(shape[i,:10][tf.newaxis, :], smpl.shapedirs[gender[i]], axes=[[1], [2]])[0,:,:], smpl.to_keep, axis=0) for i in range(shape.shape[0])])
+
+        mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis]
+        mesh_pred_posed = smpl.run_garment_with_weights(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped, mesh_weigths)
 
     # is the output already masked?
 
     e_loss = tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask']))
     c_loss, c_ratio = collision_penalty(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask'])
     c_loss, c_ratio = tf.reduce_mean(c_loss), tf.reduce_mean(c_ratio)
-    l2_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(((uv_orig - pred) ** 2), axis=-1), axis=[1, 2]))
+    # l2_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(((uv_orig - pred) ** 2), axis=-1), axis=[1, 2]))
     l2_mesh_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (batch['mesh_posed'] - mesh_pred_posed) ** 2, axis=-1), axis=-1))
     n_loss = normal_loss(mesh_pred_posed, batch['mesh_posed'], batch['mesh_mask'], is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape'])
     # conc_loss = concept_loss(pred, batch['uv_unposed'])
     kl = kl_loss(mean, logvar)
+    weights_l = blend_weights_reg(mesh_weigths)
 
-    reconstr_loss = l2_loss
+    reconstr_loss = l2_mesh_loss + 1e-6 * weights_l
     if config['use_extra_losses']:
-        reconstr_loss = reconstr_loss + l2_mesh_loss + (e_loss + c_loss) * config['reg_loss_coeff']
+        reconstr_loss = reconstr_loss + (e_loss + c_loss) * config['reg_loss_coeff']
     if config['use_norm_loss']:
         reconstr_loss = reconstr_loss + n_loss * config['reg_loss_coeff']
 
@@ -179,12 +198,12 @@ def valid_step(batch):
     logvar = tf.reduce_mean(logvar)
 
     # ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(pred + 5, batch['uv_unposed'] + 5, max_val=10, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1)))
-    metric = tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig - mesh_pred) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask'])
+    metric = tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig - mesh_pred_posed) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask'])
     # c_ratio = tf.reduce_mean(collision_ratio(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask']))
 
     return { 'valid/loss': loss, 'valid/edge_loss': e_loss, 'valid/collision_loss': c_loss, 'valid/euclid_error': metric, 
              'valid/reconstr_loss': reconstr_loss, 'valid/l2_mesh_loss': l2_mesh_loss, 'valid/collision_ratio': c_ratio,
-             'valid/mean': mean, 'valid/logvar': logvar, 'valid/kl_loss': kl, 'valid/var': np.e ** logvar,
+             'valid/mean': mean, 'valid/logvar': logvar, 'valid/kl_loss': kl, 'valid/var': np.e ** logvar, 'valid/weights_loss': weights_l,
               'valid/normal_loss': n_loss,# 'valid/ms_ssim': ms_ssim, 
               }
 
@@ -196,7 +215,7 @@ def test_step(batch):
     else:
         mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed']
     
-    pred, mean, logvar = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=False)
+    pred, mean, logvar, weights = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=False)
 
     mesh_pred = uv2mesh(pred)
 
@@ -210,7 +229,7 @@ def test_step(batch):
         mesh_orig_shaped = mesh_orig + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis]
         mesh_orig_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_orig_shaped)
     else:
-        mesh_pred_posed = mesh_pred
+        mesh_pred_posed = smpl.run_garment_with_weights(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred, weights)
         mesh_orig_posed = mesh_orig
     
     mesh_pred_posed_fixed = fix_collision(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask'])
@@ -252,9 +271,10 @@ def plot_everything(batch: dict, type: str):
     else:
         mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed']
 
-    pred, mean, logvar = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=False)
+    pred, mean, logvar, weights = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=False)
     
     mesh_pred = uv2mesh(pred).numpy()
+    mesh_weigths = uv2mesh_label(weights)
     
     orig_img = uv_orig
     uv_static_img = batch['uv_static']
@@ -279,7 +299,12 @@ def plot_everything(batch: dict, type: str):
             mesh_pred[i, mask[i], :] += shape_offsets.numpy()[i, mask[i], :]
         mesh_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred).numpy()
     else:
-        mesh_posed = mesh_pred
+        shape = batch['pose_shape'][:, 72:]
+        gender = tf.cast(tf.greater_equal(shape[:, 10] , 0.5), tf.int32)
+        shape_offsets = tf.stack([tf.gather(tf.tensordot(shape[i,:10][tf.newaxis, :], smpl.shapedirs[gender[i]], axes=[[1], [2]])[0,:,:], smpl.to_keep, axis=0) for i in range(shape.shape[0])])
+
+        mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis]
+        mesh_posed = smpl.run_garment_with_weights(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped, mesh_weigths).numpy()
         gt = [mesh_orig[i].numpy()[mask[i], :] for i in range(pred.shape[0])]
         garment_unposed, faces = maskFacesBatch(mesh_pred, F, mask)
 
@@ -298,13 +323,16 @@ def plot_everything(batch: dict, type: str):
     collision_fixed = [np.concatenate((body[i], garment_posed_fixed[i]), axis=0) for i in range(len(garment_posed))]
     collision_gt = [np.concatenate((body[i], gt_posed[i]), axis=0) for i in range(len(garment_posed))]
 
-    figs = { type + "/garment_" + str(i): plot_3d(gt[i], garment_unposed[i], faces[i], collision[i], collision_faces[i], collision_color[i], flip_xy=(not config['use_skinning'] and config['remove_global_orientation'])) for i in range(4) }
-    figs_coll = { type + "/garment_" + str(i) + '_collision': plot_3d_collision(collision_gt[i], collision[i], collision_fixed[i], collision_faces[i], collision_color[i], flip_xy=(not config['use_skinning'] and config['remove_global_orientation'])) for i in range(4) }
+    # figs = { type + "/garment_" + str(i): plot_3d(gt[i], garment_unposed[i], faces[i], garment_posed[i], faces[i], collision_color[i], flip_xy=(not config['use_skinning'] and config['remove_global_orientation'])) for i in range(4) }
+    figs = { type + "/garment_" + str(i): plot_3d(gt[i], garment_unposed[i], faces[i], collision[i], collision_faces[i], collision_color[i],) for i in range(4) }
+    figs_coll = { type + "/garment_" + str(i) + '_collision': plot_3d_collision(collision_gt[i], collision[i], collision_fixed[i], collision_faces[i], collision_color[i],) for i in range(4) }
+    figs_weights = { type + '/weights_' + str(i): plot_weights(mesh_weigths[0,:,i], body[0], F) for i in range(24) }
+    # figs_weights = { type + '/weights_' + str(i): plot_weights(smpl.weights[0,:,i], body[0], F) for i in range(24) }
 
     mean_hist = wandb.Histogram(sequence=mean.numpy().mean(axis=0))
     logvar_hist = wandb.Histogram(sequence=logvar.numpy().mean(axis=0))
 
-    return { **figs, **figs_coll, **{ type + '/images': imgs, type + '/mean_hist': mean_hist, type + '/logvar_hist': logvar_hist } }
+    return { **figs, **figs_coll, **figs_weights, **{ type + '/images': imgs, type + '/mean_hist': mean_hist, type + '/logvar_hist': logvar_hist } }
 
 
 def sample(folder): 
@@ -478,7 +506,7 @@ def test():
 
 
 if __name__ == '__main__':
-    # init_wandb()
+    init_wandb()
     parser = argparse.ArgumentParser(description='')
     parser.add_argument('--name', type=str)
     args = vars(parser.parse_args())

cvae_pyramid.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.config_abl_pyr_32_skirt import config
+from configs.post.config_abl_pyr_64_128_5 import config
 
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 import tensorflow as tf
@@ -41,7 +41,7 @@ from losses import collision_loss as collision_penalty
 from custom_utils.custom_utils import batch_to_dict, load_model
 from dataset import DatasetFactory, StaticDataset
 from custom_utils.smpl import SMPL
-from models.pyramid_model_optimized import Pyramid
+from models.pyramid_model_optimized import PyramidNew as Pyramid
 from postprocessing import fix_collision
 
 
@@ -59,11 +59,9 @@ def init_wandb():
     artifact.add_file('models/cond_encoder.py')
     artifact.add_file('dataset.py')
     artifact.add_file('convnext/models/convnext_tf.py')
-    config_file_names = [key for key in sys.modules.keys()  if key.startswith('configs')]
+    config_file_names = [key for key in sys.modules.keys()  if key.startswith('configs.post.')]
     for config_file_name in config_file_names:
-        file_name = '/'.join(config_file_name.split('.')) + '.py'
-        if os.path.exists(file_name):
-            artifact.add_file(file_name)
+        artifact.add_file('/'.join(config_file_name.split('.')) + '.py')
     run.log_artifact(artifact)
 
 uv2mesh = UV2Mesh(res=256, is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape'])
@@ -210,7 +208,7 @@ def plot_3d(mesh_gt, mesh_pred_unposed_levels, faces, mesh_posed, collision, col
     return fig
 
 
-# @tf.function
+@tf.function
 def train_step(batch):
     levels_input, conds = group_inputs_for_levels(batch, config)
 
@@ -263,8 +261,8 @@ def train_step(batch):
         else:
             reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss)
 
-        # if config['use_norm_loss'] and step > 2000:
-        #     reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff']
+        if config['use_norm_loss'] and step > 2000:
+            reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff']
         
         kl_total += kl
 
@@ -336,8 +334,8 @@ def valid_step(batch):
     else:
         reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss)
     
-    # if config['use_norm_loss'] and step > 2000:
-    #     reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff']
+    if config['use_norm_loss'] and step > 2000:
+        reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff']
         
     kl_total += kl
 
@@ -733,7 +731,7 @@ def speed_step(levels_input, conds):
 
 
 if __name__ == '__main__':
-    # init_wandb()
+    init_wandb()
     parser = argparse.ArgumentParser(description='')
     parser.add_argument('--name', type=str, default='lhunor')
     args = vars(parser.parse_args())
@@ -792,7 +790,7 @@ if __name__ == '__main__':
     # generate_results()
 
     ckpt = tf.train.Checkpoint(model=model)
-    manager = tf.train.CheckpointManager(ckpt, 'checkpoints/' + config['name'], max_to_keep=20)
+    manager = tf.train.CheckpointManager(ckpt, 'checkpoints/post/' + config['name'], max_to_keep=20)
 
     # load_model(model, 'checkpoints/pyr_abl_32_skirt', iteration='180000')
 
@@ -809,18 +807,18 @@ if __name__ == '__main__':
         model.static_enc.trainable = False
         model.body_enc.trainable = False
         model.curv_enc.trainable = False
-        model.cond_encoder.trainable = False
+
 
     # load_model(model.levels[0].upscale_enhancer, config['pyramid']['levels'][0]['upscale_enhancer'])
     # model.levels[0].upscale_enhancer.trainable = False
 
 
-    for i in range(len(model.levels)-1):
+    for i in range(len(model.levels)):
         load_model(model.levels[i].upscale_enhancer, config['pyramid']['levels'][i]['upscale_enhancer'])
         model.levels[i].upscale_enhancer.trainable = False
-    if config['pyramid']['resolutions'][-1] != 512:
-        load_model(model.upscale_enhancer, config['pyramid']['final_upscale_enhancer'])
-        model.upscale_enhancer.trainable = False
+    # if config['pyramid']['resolutions'][-1] != 512:
+    #     load_model(model.upscale_enhancer, config['pyramid']['final_upscale_enhancer'])
+    #     model.upscale_enhancer.trainable = False
 
     for i in range(len(model.levels)-1):
         model.levels[i].trainable = False

docker/Dockerfile

@@ -2,9 +2,41 @@ FROM tensorflow/tensorflow:2.9.0-gpu
 
 RUN apt-get update
 RUN apt-get upgrade -y
+
+# Add the current user to the image
+ARG USER_NAME=lhunor
+ARG USER_ID=11017
+ARG GROUP_NAME=guest
+ARG GROUP_ID=11000
+
+# Update the system and install required packages
+RUN apt-get update && apt-get upgrade -y && apt-get install -y sudo git
+
+# Create a new group with the same GID as the host
+RUN groupadd --gid $GROUP_ID $GROUP_NAME
+
+# Create a new user with the same UID and GID as the host
+RUN useradd --uid $USER_ID --gid $GROUP_ID --shell /bin/bash --create-home $USER_NAME
+
+# don't require password with sudo, for convenience
+# not the safest thing to do, but hopefully okay inside the container
+RUN echo '%sudo ALL=(ALL) NOPASSWD:ALL' >> /etc/sudoers
+
+# Add the new user to the sudo group
+RUN usermod -aG sudo $USER_NAME
+
+# Set the default user to the new user
+USER $USER_NAME
+
+WORKDIR //home-net
+
 RUN apt-get install git ffmpeg libsm6 libxext6 libopenexr-dev zip unzip htop nano -y
 RUN pip install numpy matplotlib opencv-python wandb OpenEXR tensorflow-graphics scipy plotly pandas tensorboardX opencv-python cmapy
 
+# defining the volumes that will be mounted
+VOLUME [ "/data-net" ]
+VOLUME [ "/data-local" ]
+VOLUME [ "/home-net" ]
 
-WORKDIR /home/workspace/data
-# RUN wandb login
+# Start the container with a bash shell
+CMD ["/bin/bash"]

evaluate_ae.py

@@ -39,7 +39,7 @@ else:
 from losses import collision_ratio, kl_loss #, concept_loss
 # from losses import collision_penalty as collision_penalty
 from losses import collision_loss as collision_penalty
-from custom_utils.custom_utils import batch_to_dict, load_model, plot_3d, UV2Mesh, get_summary_html, maskFacesBatch, _maskFaces, plot_3d_collision
+from custom_utils.custom_utils import batch_to_dict, load_model, plot_3d, UV2Mesh, UV2MeshLabel, get_summary_html, maskFacesBatch, _maskFaces, plot_3d_collision
 from dataset import DatasetFactory, StaticDataset
 from custom_utils.smpl import SMPL
 from models.cvae_model import CVAENew as CVAE
@@ -48,6 +48,7 @@ from custom_utils.supersmpl_io import writeOBJ
 
 
 uv2mesh = UV2Mesh(res=256, is_skirt=config['is_skirt'], is_adaptive=False, is_smpl_orig=config['is_cape'])
+uv2mesh_label = UV2MeshLabel(res=256, is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape'])
 
 @tf.function
 def step(batch):
@@ -56,9 +57,10 @@ def step(batch):
     else:
         uv_orig =  batch['uv_posed']
     
-    pred, _, _ = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=False)
+    pred, _, _, weights = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=False)
 
     mesh_pred = uv2mesh(pred)
+    mesh_weigths = uv2mesh_label(weights)
 
     if config['use_skinning']:
         shape = batch['pose_shape'][:, 72:]
@@ -68,7 +70,13 @@ def step(batch):
         mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis]
         mesh_pred_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)
     else:
-        mesh_pred_posed = mesh_pred
+        shape = batch['pose_shape'][:, 72:]
+        gender = tf.cast(tf.greater_equal(shape[:, 10] , 0.5), tf.int32)
+        shape_offsets = tf.stack([tf.gather(tf.tensordot(shape[i,:10][tf.newaxis, :], smpl.shapedirs[gender[i]], axes=[[1], [2]])[0,:,:], smpl.to_keep, axis=0) for i in range(shape.shape[0])])
+
+        mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis]
+        mesh_pred_posed = smpl.run_garment_with_weights(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped, mesh_weigths)
+
         
     # mesh_pred_posed_fixed = fix_collision(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask'])
 

fix_curv_uv_loc.py

@@ -1,23 +0,0 @@
-import os
-import shutil
-import tqdm
-
-if __name__ == '__main__':
-    folder = '/home/workspace/data/dataset/local-cache/train_skirt'
-    is_skirt = True 
-    skirt_modifier = '_skirt' if is_skirt else ''
-    frames_file = 'frames' + skirt_modifier + '_10p.txt'
-    neighbourhood = 10
-
-    frames = []
-    with open(os.path.join(folder, frames_file), 'r') as f:
-        lines = f.readlines()
-        lines = [line.strip() for line in lines]
-    frames = lines
-
-    os.makedirs(os.path.join(folder, f'uv_curvature_{neighbourhood}'), exist_ok=True)
-    for frame in tqdm.tqdm(frames):
-        id = frame.split('_')[0]
-        src = os.path.join(folder, f'{id}', 'curvature_uv_10', f'{frame}.npz')
-        dst = os.path.join(folder, f'uv_curvature_{neighbourhood}', f'{frame}.npz')
-        shutil.move(src, dst)

models/base.py

@@ -171,13 +171,13 @@ class AEEncoderNew(tf.keras.Model):
 
 class DecoderNew(tf.keras.Model):
     
-    def __init__(self, depths, dims, kernel_size=7, is_label=False):
+    def __init__(self, depths, dims, kernel_size=7, is_label=False, learn_weights=False):
         super(DecoderNew, self).__init__()
 
         self.is_label = is_label
 
         if not is_label:
-            self.decoder = ConvNeXtReverse(depths=depths, dims=dims, kernel_size=kernel_size)
+            self.decoder = ConvNeXtReverse(depths=depths, dims=dims, kernel_size=kernel_size, learn_weights=learn_weights)
         else:
             self.decoder = ConvNeXtReverseLabels(depths=depths, dims=dims, nr_of_classes=7)
             

models/cvae_model.py

@@ -43,7 +43,7 @@ class CVAE(tf.keras.Model):
         self.cond_encoder = tf.keras.Sequential([tf.keras.layers.Dense(512, activation='relu'),
                                                  tf.keras.layers.Dense(256, activation='relu'),
                                                  tf.keras.layers.Dense(128, activation='relu'),
-                                                #  tf.keras.layers.Lambda(lambda x: x / 1000),
+                                                 tf.keras.layers.Lambda(lambda x: x / 1000),
                                                  tf.keras.layers.Dense(config['latent_dim'], activation='tanh')])
 
         self.encoder = VariationalEncoder(config['cvae']['latent_dim'], config['cvae']['encoder_depths'], config['cvae']['encoder_dims'], kernel_size=config['cvae']['kernel_size'])
@@ -181,6 +181,7 @@ class CVAENew(tf.keras.Model):
 
         self.encoder = VariationalEncoderNew(config['cvae']['encoder_depths'], config['cvae']['encoder_dims'], kernel_size=config['cvae']['kernel_size'])
         self.decoder = DecoderNew(config['cvae']['decoder_depths'], config['cvae']['decoder_dims'], config['cvae']['kernel_size'])
+        self.decoder_weights = DecoderNew(config['cvae']['decoder_weights_depths'], config['cvae']['decoder_weights_dims'], config['cvae']['kernel_size'], learn_weights=True)
 
         self.reshape = tf.keras.layers.Reshape((8, 4, 64))
 
@@ -193,12 +194,12 @@ class CVAENew(tf.keras.Model):
         self.noise_amount = config['cvae']['noise_amount']
         self.use_curvature = config['use_curvature']
         self.only_curvatures = config['only_curvatures'] if 'only_curvatures' in config.keys() and config['only_curvatures'] == True else None
-        self.use_offsets_over_body = not config['use_skinning']
+        self.use_offsets_over_body = False
 
         if self.use_offsets_over_body:
             assert self.avg_garment is None, 'When we are not using skinning, we can\'t use avg_garment!'
-        if self.avg_garment is not None:
-            assert not self.use_offsets_over_body, 'When avg_garment is given, we must use skinning!'
+        # if self.avg_garment is not None:
+        #     assert not self.use_offsets_over_body, 'When avg_garment is given, we must use skinning!'
 
     # @tf.function
     def sample(self, uv_template, uv_body_posed, uv_curv, uv_mask, noise=None, add_noise=False):
@@ -214,6 +215,7 @@ class CVAENew(tf.keras.Model):
         z = tf.concat([eps, z_cond], axis=-1)
 
         x = self.decoder(z, training=False)
+        weights = self.decoder_weights(z, training=False)
         
         if self.avg_garment is not None:
             x = x + self.avg_garment[tf.newaxis,:,:,:]
@@ -223,7 +225,7 @@ class CVAENew(tf.keras.Model):
 
         x = x * uv_mask[:,:,:,tf.newaxis]
 
-        return x
+        return x, weights
 
 
     def reparameterize(self, mean, logvar, training, fix_noise=False):
@@ -272,6 +274,7 @@ class CVAENew(tf.keras.Model):
 
         z = tf.concat([z, z_cond], axis=-1)
         x = self.decoder(z, training=training)
+        weights = self.decoder_weights(z, training=training)
 
         if self.avg_garment is not None:
             x = x + self.avg_garment[tf.newaxis,:,:,:]
@@ -281,5 +284,5 @@ class CVAENew(tf.keras.Model):
 
         x = x * uv_mask[:,:,:,tf.newaxis]
 
-        return x, mean, logvar
+        return x, mean, logvar, weights
 

run_parallel.py

@@ -4,26 +4,24 @@ import os
 
 if __name__ == '__main__':
 
-    # folder = '/home/workspace/data/dataset/local-cache/train_skirt'
     folder = '/home/workspace/data/dataset/test_skirt_ready_2'
-    # folder = '/home/workspace/local-data/valid_skirt'
     # folder = '/home/workspace/local-data/cape_processed/train/male'
     # folder = '/home/workspace/local-data/valid_skirt'
     # folder = '/home/workspace/local-data/valid'
     # ids = os.listdir(folder)
-    # ids = os.listdir(folder + '/mesh_posed_no_orient')#[280000:]
+    ids = os.listdir(folder + '/mesh_posed_no_orient')#[280000:]
     skirt = 0
 
     count = 0
-    step = 20
+    step = 2000
 
     # !!!!!!! change skirt parameter in script
 
-    while count < 150:
+    while count < len(ids):
         # os.system('nohup python convert_to_uv_cape.py -f ' + folder + ' -s ' + str(count) + ' -e ' + str(count + step) + ' -n ' + 'to_uv_2_cape_train_male_' + str(count) + '_' + str(count+step) + ' > nohup/to_uv_2_cape_train_male_' + str(count) + '_' + str(count+step) + '.out' + ' 2>&1 &')
         # os.system('nohup python convert_to_uv.py -f ' + folder + ' -s ' + str(count) + ' -e ' + str(count + step) + ' -n ' + 'to_uv_train_unposed_onehot_' + str(count) + '_' + str(count+step) + ' > nohup/to_uv_train_unposed_onehot_' + str(count) + '_' + str(count+step) + '.out' + ' 2>&1 &')
         # os.system('nohup python convert_to_uv_local.py -f ' + folder + ' -s ' + str(count) + ' -e ' + str(count + step) + ' -n ' + 'to_uv_train_local_unposed_onehot_' + str(count) + '_' + str(count+step) + ' > nohup/to_uv_train_local_unposed_onehot_' + str(count) + '_' + str(count+step) + '.out' + ' 2>&1 &')
-        os.system('nohup python convert_to_uv_local_single.py -f ' + folder + ' -s ' + str(count) + ' -e ' + str(count + step) + ' -n ' + 'to_uv_curv_2_10_test_skirt_' + str(count) + '_' + str(count+step) + ' > nohup/to_uv_curv_2_10_test_skirt_' + str(count) + '_' + str(count+step) + '.out' + ' 2>&1 &')
+        os.system('nohup python convert_to_uv_local_single.py -f ' + folder + ' -s ' + str(count) + ' -e ' + str(count + step) + ' -n ' + 'to_uv_posed_no_orient_test_skirt_ready_' + str(count) + '_' + str(count+step) + ' > nohup/to_uv_posed_no_orient_test_skirt_ready_' + str(count) + '_' + str(count+step) + '.out' + ' 2>&1 &')
         # os.system('nohup python convert_to_uv_local_single.py -f ' + folder + ' -s ' + str(count) + ' -e ' + str(count + step) + ' -n ' + 'to_uv_train_skirt_local_unposed_onehot_3_' + str(count) + '_' + str(count+step) + ' > nohup/to_uv_train_skirt_local_unposed_onehot_3_' + str(count) + '_' + str(count+step) + '.out' + ' 2>&1 &')
         # os.system('nohup python convert_to_uv_local_single.py -f ' + folder + ' -s ' + str(count) + ' -e ' + str(count + step) + ' -n ' + 'to_uv_valid_skirt_local_unposed_onehot_3_' + str(count) + '_' + str(count+step) + ' > nohup/to_uv_valid_skirt_local_unposed_onehot_' + str(count) + '_' + str(count+step) + '.out' + ' 2>&1 &')
         # os.system('nohup python downscale.py -f ' + folder + ' -s ' + str(count) + ' -e ' + str(count + step) + ' -n ' + 'downscale_valid_posed_no_orient_' + str(count) + '_' + str(count+step) + ' > nohup/downscale_valid_posed_no_orient_' + str(count) + '_' + str(count+step) + '.out' + ' 2>&1 &')