fine tune

aaa_helpers.txt

@@ -1,3 +1,10 @@
+nohup python cvae_pyramid.py --name="lhunor_pyr_abl_32_64_e2e_r3" > nohup/review/pyr_abl_32_64_e2e_r3.out 2>&1 &
+nohup python cvae_pyramid.py --name="lhunor_pyr_abl_32_64_e2e_r3_pre" > nohup/review/pyr_abl_32_64_e2e_r3_pre.out 2>&1 &
+nohup python cvae_pyramid.py --name="lhunor_pyr_abl_32_64_e2e_r3_fine" > nohup/review/pyr_abl_32_64_e2e_r3_fine.out 2>&1 &
+nohup python evaluate_ae_pyramid.py --name evaluate_pyr_abl_32_64_e2e_r3 > nohup/evaluate/pyr_abl_32_64_e2e_r3.out 2>&1 &
+nohup python calculate_error.py --name error_pyr_abl_32_64_e2e_r3 > nohup/error/pyr_abl_32_64_e2e_r3.out 2>&1 &
+
+
 one final convolutional layer for smoothing, on the final coordinates
 
 skirts!!!!

auto_encoder_curv.py

@@ -95,7 +95,7 @@ def dice_dense(prediction, ground_truth, weight_map=None):
     return tf.reduce_mean(dice_score)
 
 
-# @tf.function
+@tf.function
 def train_step(batch):
     with tf.GradientTape() as tape:
         pred = model([batch['uv_curvature'], batch['uv_mask']], training=True)

calculate_error.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.config_abl_all_post import config
+from configs.config_abl_pyr_32 import config
 
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 # import tensorflow as tf
@@ -59,13 +59,13 @@ if __name__ == '__main__':
     folder = config['test_dir']
 
     checkpoint_name = config['name']
-    iteration = ''
+    iteration = '200000'
 
     F = np.load("custom_utils/smpl_faces" + skirt_modifier + ".npy").astype(np.int32)
     garment_type_table = np.load('custom_data/garment_type_table_test.npy', allow_pickle=True).item()
 
 
-    output_folder = '/home/workspace/data/results/post/' + checkpoint_name + '-' + iteration
+    output_folder = '/home/workspace/data/results/' + checkpoint_name + '-' + iteration
 
 
     faces_folder = '/home/workspace/data/results/support/faces' + ('_skirt' if config['is_skirt'] else '')

configs/config_abl_overfit_jumpsuit_2.py

@@ -19,7 +19,7 @@ config['only_curvatures'] =           True
 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'] = '3'
+config['gpu'] = '5'
 config['name'] = 'abl_overfit_jumpsuit_2'
 config['notes'] = 'remove other conditions from input as well'
 

configs/config_abl_pyr_32.py

@@ -1,8 +1,9 @@
 config = dict()
 
 config['gpu'] = '0'
-config['name'] = 'pyr_abl_32_r1'
+config['name'] = 'pyr_abl_32_64_e2e_r3_fine_2'
 config['notes'] = ''
+config['tags'] = ['review_3']
 
 # DON'T FORGET TO RESET SSIM LOSS USAGE
 # DON'T FORGET TO CHECK MODEL LOADING
@@ -21,9 +22,12 @@ config['use_offsets'] =               False
 
 
 config['pyramid'] = dict()
-config['pyramid']['resolutions'] = [32]
+config['pyramid']['resolutions'] = [32, 64]
 config['pyramid']['pretrained_pyramid'] = ''
-config['pyramid']['final_upscale_enhancer'] = 'checkpoints/32_512_4'
+config['pyramid']['final_upscale_enhancer'] = 'checkpoints/64_512_2'
+
+config['pretrained_model'] = 'checkpoints/pyr_abl_32_64_e2e_r3_fine'
+config['pretrained_model_iteration'] = ''
 
 config['train_dir'] = '/home/workspace/local-data/train'
 config['valid_dir'] = '/home/workspace/local-data/valid'
@@ -40,7 +44,7 @@ config['smpl_res'] = 14475
 if config['is_cape']:
   config['smpl_res'] = 3638
 
-config['lr'] = 0.0001
+config['lr'] = 0.00001
 config['starting_balancing_coeff'] = 0.0001
 config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
 config['avg_garment_path'] = ''
@@ -64,7 +68,7 @@ config['pyramid']['latent_dim'] = config['latent_dim']
 config['pyramid']['add_noise'] = True
 config['pyramid']['noise_amount'] = 0.025
 
-config['pyramid']['loss_weights'] = [1,1,1,1,1]
+config['pyramid']['loss_weights'] = [2,1,1,1,1]
 
 for res in config['pyramid']['resolutions']:
   if res != 512:
@@ -149,7 +153,7 @@ for res in config['pyramid']['resolutions']:
     level['decoder_depths'] = [9, 9]
     level['decoder_dims'] = [256, 256]
     level['avg_garment_path'] = ''
-    level['upscale_enhancer'] = ''#'checkpoints/up_3_d32_64_2'
+    level['upscale_enhancer'] = 'checkpoints/32_512_4'#'checkpoints/up_3_d32_64_2'
     level['upscale_enhancer_freeze'] = True
     config['pyramid']['levels'].append(level)
   else:

curvature_analysis.py

@@ -1,348 +0,0 @@
-import os
-import sys
-os.environ["CUDA_VISIBLE_DEVICES"] = '4'
-
-
-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 postprocessing import fix_collision
-
-from custom_utils.supersmpl_io import readPC2, readPC2Frame, writePC2, readOBJ
-from custom_utils.custom_utils import _maskFaces
-from auto_encoder_curv import dice_dense
-
-def postprocess(mesh, faces, mask=None, body=None, do_smoothing=True):
-    if body is not None:
-        mesh_fixed = fix_collision(mesh, body[np.newaxis,:,:], mask[np.newaxis,:])[0].numpy()[mask, :]
-    else:
-        mesh_fixed = mesh
-
-    if do_smoothing:
-        m = tm.Trimesh(mesh_fixed, 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(mesh_fixed, outliers, 2)
-        outliers_faces = np.concatenate((outliers[:, np.newaxis], outliers_n_neighbours), axis=-1)
-        faces_fixed = np.concatenate((faces, outliers_faces), axis=0)
-        m = tm.Trimesh(mesh_fixed, faces_fixed, process=False, validate=False)
-        tm.smoothing.filter_humphrey(m, iterations=1, alpha=0.6, beta=0.4)
-
-        mesh = m.vertices
-    else:
-        mesh = mesh_fixed
-
-    return mesh
-
-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(v, faces, mask, neighbourhood=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)
-
-    k_neighbors = np.argsort(dist[mask, :][:, mask], axis=-1)[:, :neighbourhood]
-    # k_neighbors = cloud.get_neighbors(k=neighbourhood)
-    # tree = sp.spatial.cKDTree(verts)
-    # k_neighbors = tree.query(verts, 25)[1]
-    #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 = np.load(f'custom_data/train_bins.npy')
-    # bins = get_bins(curvature, nr_of_labels)
-    labels = np.linspace(0, bins.shape[0] - 2, bins.shape[0] - 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]
-       
-    return frame_labels, curvature
-
-import tensorflow as tf
-from configs.config_abl_overfit_jumpsuit_2 import config
-from custom_utils.custom_utils import batch_to_dict, load_model, plot_3d, UV2Mesh, get_summary_html, maskFacesBatch, _maskFaces, plot_3d_collision, UV2MeshLabel
-
-from custom_utils.smpl import SMPL
-from models.cvae_model import CVAE
-
-uv2mesh = UV2Mesh(res=256, is_skirt=False, is_adaptive=False, is_smpl_orig=False)
-uv2meshlabel = UV2MeshLabel(res=256, is_skirt=False)
-
-def get_prediction(folder, frame, curv):
-    smpl = SMPL(use_one_hot=False, orig_smpl=False)
-    model = CVAE(config)
-    load_model(model, 'checkpoints/' + config['name'])
-
-    id = frame.split('_')[0]
-    frame_nr = frame.split('_')[1].split('.')[0]
-
-    mesh_mask = np.load(os.path.join(folder, 'mesh_mask', f'{id}.npy')).astype(bool)
-    uv_mask = np.load(os.path.join(folder, 'uv_mask', f'{id}.npz'))['uv_mask'].astype(np.float32)  
-    pose_shape = np.load(os.path.join(folder, 'pose_shape', f'{id}_{frame_nr}.npy')).astype(np.float32)  
-    pose_shape[:3] = 0
-    uv_unposed = np.load(os.path.join(folder, 'uv_unposed_no_shape', f'{id}_{frame_nr}.npz'))['uv_unposed_no_shape']
-    uv_static = np.load(os.path.join(folder, 'uv_static', f'{id}.npz'))['uv_static']
-    uv_body_posed = np.load(os.path.join(folder, 'uv_posed_body_no_orient_2', f'{id}_{frame_nr}.npz'))['uv_posed_body_no_orient']
-
-    pred, _, _ = model([uv_unposed[None,:,:,:], uv_static[None,:,:,:], uv_body_posed[None,:,:,:], curv[None,:,:,:], uv_mask[None,:,:]], training=False)
-    mesh_pred = uv2mesh(pred)
-
-    shape = pose_shape[None, 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 * mesh_mask[tf.newaxis,:,tf.newaxis]
-    mesh_pred_posed = smpl.run_garment(pose_shape[None, :72], pose_shape[None, 72:], mesh_pred_shaped)
-    
-    return mesh_pred_posed.numpy()[0,mesh_mask,:]
-
-
-def visualize_curvature_labels(folder, results_folder, frame):
-    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,:]
-    pred = np.load(os.path.join(results_folder, frame + '.npy'))
-    pred = postprocess(pred, faces)
-
-    uv_curvature = np.load(os.path.join(folder, 'uv_curvature', f'{id}_{frame_nr}.npz'))['curvature_uv']
-    mesh_curvature = np.load(os.path.join(folder, 'mesh_curvature', f'{id}_{frame_nr}.npz'))['mesh_curvature'][mask]
-    mesh_curvature_raw = np.load(os.path.join(folder, 'mesh_curvature_raw', f'{id}_{frame_nr}.npz'))['mesh_curvature_raw'][mask]
-    uv_curvature = tf.one_hot(uv_curvature, 7)
-    pred_new = get_prediction(folder, frame, uv_curvature)
-    pred_new = postprocess(pred_new, faces)
-
-    curvature_labels_gt, curv_gt = generate_curvatures(verts, faces, mask, 25)
-    curvature_labels_pred, _ = generate_curvatures(pred, faces, mask, 25)
-    curvatures_new = (uv2meshlabel(uv_curvature[None,:,:,:])[0].numpy() * mask[:,None])[mask, :]
-    curvatures_pred_new, curv_gt_new = generate_curvatures(pred_new, faces, mask, 25)
-    dice = dice_dense(tf.one_hot(curvature_labels_pred, 7)[None,:], tf.one_hot(curvature_labels_gt, 7)[None,:])
-    dice_new = dice_dense(tf.one_hot(curvatures_pred_new, 7)[None,:], curvatures_new[None,:])
-    curvatures_new = curvatures_new.argmax(axis=-1) - 1
-
-    colors_binned_all = []
-
-    for curvature_labels in [curvature_labels_gt, curvature_labels_pred, curvatures_new, curvatures_pred_new]:
-        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=4, start_cell="top-left", specs = [ [{ 'type': 'scene' } for _ in range(4)] ])
-
-    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_all[0]
-            ),
-            row=1, col=1)
-
-    fig.add_trace(go.Mesh3d(
-                # 8 vertices of a cube
-                x=-pred[:,0],
-                y=pred[:,2],
-                z=pred[:,1],
-                # i, j and k give the vertices of triangles
-                i = faces[:,0],
-                j = faces[:,1],
-                k = faces[:,2],
-                vertexcolor=colors_binned_all[1],
-                text=f'dice: {dice}'
-            ),
-            row=1, col=2)
-    
-    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_all[2]
-            ),
-            row=1, col=3)
-
-    fig.add_trace(go.Mesh3d(
-                # 8 vertices of a cube
-                x=-pred_new[:,0],
-                y=pred_new[:,2],
-                z=pred_new[:,1],
-                # i, j and k give the vertices of triangles
-                i = faces[:,0],
-                j = faces[:,1],
-                k = faces[:,2],
-                vertexcolor=colors_binned_all[3],
-                text=f'dice: {dice_new}'
-            ),
-            row=1, col=4)
-
-    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],),)
-    #                     )
-
-    return fig, dice
-
-import wandb
-
-def init_wandb():
-    run = wandb.init(project='plots', name='review_5', dir='/home/workspace/local-data/temp/')
-    artifact = wandb.Artifact('code', type='code')
-    artifact.add_file('curvature_analysis.py')
-    run.log_artifact(artifact)
-
-if __name__ == '__main__':
-    # init_wandb()
-
-    is_skirt = False
-    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/train'
-    results_folder = '/home/workspace/data/results/post/abl_overfit_jumpsuit_2-'
-
-    frames_file = 'frames_jumpsuit_30k.txt'
-    frames = []
-    with open(os.path.join(folder, frames_file), 'r') as f:
-        lines = f.readlines()
-        lines = [line.strip() for line in lines]
-    frames = lines
-
-    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')
-
-    i = 0
-    while True:
-        # frame = np.random.choice(frames)
-        frame = '02806_129'
-        fig, dice = visualize_curvature_labels(folder, results_folder, frame)
-        wandb.log({f'{frame}-dice:{dice}': fig}, step=i)
-        i += 1
-        print(frame)

custom_utils/custom_utils.py

@@ -45,7 +45,7 @@ class UV2Mesh(tf.keras.Model):
         if uv.shape[1] == 3:
             uv = tf.transpose(uv, [0,2,3,1])
         if uv.shape[1] != 512:
-            uv = tf.image.resize(uv, (512, 256), tf.image.ResizeMethod.LANCZOS5)
+            uv = tf.image.resize(uv, (512, 256), tf.image.ResizeMethod.BILINEAR)
             
         batch_size = uv.shape[0]
 

cvae.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.config_abl_overfit_jumpsuit_2 import config
+from configs.config_abl_all_post 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, 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 models.cvae_model import CVAENew as CVAE
 
 
 def init_wandb():

cvae_pyramid.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.config_abl_pyr_32_skirt import config
+from configs.config_abl_pyr_32 import config
 
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 import tensorflow as tf
@@ -210,73 +210,77 @@ 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)
 
     with tf.GradientTape() as tape:
         out_levels = model([levels_input, conds], training=True)
 
-        if config['use_skinning']:
-            mesh_orig, uv_orig = batch['mesh_unposed'], batch['uv_unposed']
-        else:
-            mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed']
+        mesh_orig, uv_orig = batch['mesh_unposed'], batch['uv_unposed']
 
         output = dict()
         reconstr_loss_total = 0
         kl_total = 0
 
-        #for i, res in enumerate(config['pyramid']['resolutions']):
-        i = -1
-        res = config['pyramid']['resolutions'][-1]
-        res_modifier = '_' + str(res) if res != 512 else ''
-        pred, mean, logvar = out_levels[i]
+        for i, res in enumerate(config['pyramid']['resolutions']):
+            # i = -1
+            # res = config['pyramid']['resolutions'][-1]
+            if res != 512:
+                if i == len(config['pyramid']['resolutions']) - 1:
+                    res_modifier = ''
+                else:
+                    res_modifier = '_' + str(res)
+            else:
+                res_modifier = ''
 
-        mesh_pred = uv2mesh(pred)
+            pred, mean, logvar = out_levels[i]
 
-        if config['use_skinning']:
-            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 = uv2mesh(pred)
 
-            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
+            if config['use_skinning']:
+                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])])
 
-        # is the output already masked?
+                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
 
-        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]))
-        # 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)))
-        # ms_ssim = tf.reduce_mean(tf.image.ssim(pred + 1, batch['uv_unposed'] + 1, max_val=3))
-        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'])
-        kl = kl_loss(mean, logvar)
+            # is the output already masked?
 
-        if config['use_extra_losses']:
-            reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss + l2_mesh_loss)
-            if not config['is_cape']:
-                reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (e_loss + c_loss) * config['reg_loss_coeff'] 
-        else:
-            reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss)
+            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(((batch['uv_unposed' + res_modifier] - pred) ** 2), axis=-1), axis=[1, 2]))
+            # 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)))
+            # ms_ssim = tf.reduce_mean(tf.image.ssim(pred + 1, batch['uv_unposed'] + 1, max_val=3))
+            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'])
+            kl = kl_loss(mean, logvar)
 
-        # if config['use_norm_loss'] and step > 2000:
-        #     reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff']
-        
-        kl_total += kl
+            if config['use_extra_losses']:
+                reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss + l2_mesh_loss)
+                if not config['is_cape']:
+                    reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (e_loss + c_loss) * config['reg_loss_coeff'] 
+            else:
+                reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss)
 
-        mean = tf.reduce_mean(mean)
-        logvar = tf.reduce_mean(logvar)
+            # if config['use_norm_loss'] and step > 2000:
+            #     reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff']
+            
+            kl_total += kl
 
-        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'])
+            mean = tf.reduce_mean(mean)
+            logvar = tf.reduce_mean(logvar)
 
-        output = { **output, **{ 'train/edge_loss' + res_modifier: e_loss, 'train/collision_loss' + res_modifier: c_loss,'train/euclid_error' + res_modifier: metric, 
-                                 'train/mean' + res_modifier: mean, 'train/logvar' + res_modifier: logvar, 'train/kl_loss' + res_modifier: kl,
-                                 'train/var' + res_modifier: np.e ** logvar, 'train/l2_loss' + res_modifier: l2_loss, 'train/normal_loss': n_loss,
-                                 'train/euclid_error': metric, 'train/l2_mesh_loss': l2_mesh_loss } } # 'train/ms_ssim' + res_modifier: ms_ssim,
+            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'])
+
+            output = { **output, **{ 'train/edge_loss' + res_modifier: e_loss, 'train/collision_loss' + res_modifier: c_loss,'train/euclid_error' + res_modifier: metric, 
+                                    'train/mean' + res_modifier: mean, 'train/logvar' + res_modifier: logvar, 'train/kl_loss' + res_modifier: kl,
+                                    'train/var' + res_modifier: np.e ** logvar, 'train/l2_loss' + res_modifier: l2_loss, 'train/normal_loss': n_loss,
+                                    'train/euclid_error': metric, 'train/l2_mesh_loss': l2_mesh_loss } } # 'train/ms_ssim' + res_modifier: ms_ssim,
 
         loss = reconstr_loss_total + balancing_coeff * kl_total
 
@@ -290,66 +294,69 @@ def valid_step(batch):
     levels_input, conds = group_inputs_for_levels(batch, config)
     out_levels = model([levels_input, conds], training=False)
 
-
-    if config['use_skinning']:
-        mesh_orig, uv_orig = batch['mesh_unposed'], batch['uv_unposed']
-    else:
-        mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed']
+    mesh_orig, uv_orig = batch['mesh_unposed'], batch['uv_unposed']
 
     output = dict()
     reconstr_loss_total = 0
     kl_total = 0
 
-    #for i, res in enumerate(config['pyramid']['resolutions']):
-    i = -1
-    res = config['pyramid']['resolutions'][-1]
-    res_modifier = '_' + str(res) if res != 512 else ''
-    pred, mean, logvar = out_levels[i]
+    for i, res in enumerate(config['pyramid']['resolutions']):
+        # i = -1
+        # res = config['pyramid']['resolutions'][-1]
+        if res != 512:
+            if i == len(config['pyramid']['resolutions']) - 1:
+                res_modifier = ''
+            else:
+                res_modifier = '_' + str(res)
+        else:
+            res_modifier = ''
 
-    mesh_pred = uv2mesh(pred)
+        pred, mean, logvar = out_levels[i]
 
-    if config['use_skinning']:
-        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 = uv2mesh(pred)
 
-        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
-    # is the output already masked?
+        if config['use_skinning']:
+            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])])
 
-    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]))
-    # 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)))
-    # ms_ssim = tf.reduce_mean(tf.image.ssim(pred + 1, batch['uv_unposed'] + 1, max_val=3))
-    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'])
-    kl = kl_loss(mean, logvar)
+            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
+        # is the output already masked?
 
-    if config['use_extra_losses']:
-        reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss + l2_mesh_loss)
-        if not config['is_cape']:
-            reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (e_loss + c_loss) * config['reg_loss_coeff'] 
-    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']
+        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(((batch['uv_unposed' + res_modifier] - pred) ** 2), axis=-1), axis=[1, 2]))
+        # 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)))
+        # ms_ssim = tf.reduce_mean(tf.image.ssim(pred + 1, batch['uv_unposed'] + 1, max_val=3))
+        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'])
+        kl = kl_loss(mean, logvar)
+
+        if config['use_extra_losses']:
+            reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss + l2_mesh_loss)
+            if not config['is_cape']:
+                reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (e_loss + c_loss) * config['reg_loss_coeff'] 
+        else:
+            reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss)
         
-    kl_total += kl
+        # if config['use_norm_loss'] and step > 2000:
+        #     reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff']
+            
+        kl_total += kl
 
-    mean = tf.reduce_mean(mean)
-    logvar = tf.reduce_mean(logvar)
+        mean = tf.reduce_mean(mean)
+        logvar = tf.reduce_mean(logvar)
 
-    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) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask'])
 
-    output = { **output, **{ 'valid/edge_loss' + res_modifier: e_loss, 'valid/collision_loss' + res_modifier: c_loss,'valid/euclid_error' + res_modifier: metric, 
-                                 'valid/mean' + res_modifier: mean, 'valid/logvar' + res_modifier: logvar, 'valid/kl_loss' + res_modifier: kl,
-                                'valid/var' + res_modifier: np.e ** logvar, 'valid/l2_loss' + res_modifier: l2_loss, 'valid/normal_loss': n_loss,
-                                'valid/euclid_error': metric, 'valid/l2_mesh_loss': l2_mesh_loss } } # 'valid/ms_ssim' + res_modifier: ms_ssim,
+        output = { **output, **{ 'valid/edge_loss' + res_modifier: e_loss, 'valid/collision_loss' + res_modifier: c_loss,'valid/euclid_error' + res_modifier: metric, 
+                                    'valid/mean' + res_modifier: mean, 'valid/logvar' + res_modifier: logvar, 'valid/kl_loss' + res_modifier: kl,
+                                    'valid/var' + res_modifier: np.e ** logvar, 'valid/l2_loss' + res_modifier: l2_loss, 'valid/normal_loss': n_loss,
+                                    'valid/euclid_error': metric, 'valid/l2_mesh_loss': l2_mesh_loss } } # 'valid/ms_ssim' + res_modifier: ms_ssim,
 
     loss = reconstr_loss_total + balancing_coeff * kl_total
 
@@ -733,7 +740,7 @@ 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())
@@ -800,16 +807,19 @@ if __name__ == '__main__':
         # assert len(config['pyramid']['resolutions']) == 1
         load_model(model, config['pretrained_model'], iteration=config['pretrained_model_iteration'])
 
-    if len(config['pyramid']['resolutions']) == 1:
-        model.static_enc.trainable = False
-        model.body_enc.trainable = False
-        model.curv_enc.trainable = False
-    else:
-        load_model(model, config['pyramid']['pretrained_pyramid'], iteration=(config['pyramid']['pretrained_pyramid_iteration'] if 'pretrained_pyramid_iteration' in config.keys() else ''))
-        model.static_enc.trainable = False
-        model.body_enc.trainable = False
-        model.curv_enc.trainable = False
-        model.cond_encoder.trainable = False
+    model.static_enc.trainable = False
+    model.body_enc.trainable = False
+    model.curv_enc.trainable = False
+
+    # model.trainable = False
+    # model.cond_encoder_2.trainable = True
+    # if len(config['pyramid']['resolutions']) == 1:
+    # else:
+    #     load_model(model, config['pyramid']['pretrained_pyramid'], iteration=(config['pyramid']['pretrained_pyramid_iteration'] if 'pretrained_pyramid_iteration' in config.keys() else ''))
+    #     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
@@ -822,8 +832,8 @@ if __name__ == '__main__':
         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
+    # for i in range(len(model.levels)-1):
+    #     model.levels[i].trainable = False
 
     # load_model(model.cond_encoder, config['pyramid']['pretrained_pyramid'])
     # load_model(model.levels[0], config['pyramid']['pretrained_pyramid'])

evaluate_ae.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.config_abl_overfit_jumpsuit_2 import config
+from configs.config_abl_all_post import config
 
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 import tensorflow as tf
@@ -42,7 +42,7 @@ 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 models.cvae_model import CVAENew as CVAE
 from custom_utils.supersmpl_io import writeOBJ
 # from unif_metric import chamfer_and_score
 
@@ -104,7 +104,7 @@ if __name__ == '__main__':
 
     iteration = ''
 
-    load_model(model, 'checkpoints/' + checkpoint_name, iteration=iteration)
+    load_model(model, 'checkpoints/post/' + checkpoint_name, iteration=iteration)
     # load_model(model, 'checkpoints/' + 'abl_all_120k')
 
     output_folder = '/home/workspace/data/results/post/' + checkpoint_name + '-' + iteration

evaluate_ae_pyramid.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.config_abl_2_pyr_32_64_128_256_512 import config
+from configs.config_abl_pyr_32 import config
 
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 import tensorflow as tf
@@ -97,7 +97,7 @@ if __name__ == '__main__':
     ids = [id.split('_')[0] for id in ids]
     ids = set(ids)
 
-    iteration = '50000'
+    iteration = '200000'
 
     load_model(model, 'checkpoints/' + checkpoint_name, iteration=iteration)
     # load_model(model, 'checkpoints/' + 'abl_all_120k')

models/pyramid_level.py

@@ -92,7 +92,7 @@ class PyramidLevel(tf.keras.Model):
         
         # x = x * uv_mask_high[:,:,:,tf.newaxis]
 
-        return x, mean, logvar
+        return x, z, mean, logvar
 
 
 

models/pyramid_model_optimized.py

@@ -78,6 +78,11 @@ class Pyramid(tf.keras.Model):
             load_model(self.upscale_enhancer, config['pyramid']['final_upscale_enhancer'])
             self.upscale_enhancer.trainable = False
 
+        self.cond_encoder_2 = 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.Dense(config['pyramid']['latent_dim'], activation='tanh'),])
+
     def enhance(self, low, mask, training):
         x = self.upscale_enhancer([low, mask], training=training)
         return x
@@ -90,44 +95,54 @@ class Pyramid(tf.keras.Model):
         z_cond = tf.concat([z_static, z_body, z_curv], axis=-1)
         z_cond = self.cond_encoder(z_cond, training=training)
 
+        return z_cond, z_static, z_body, z_curv
+
+    def encode_conds_2(self, z, z_static, z_body, z_curv, training):
+        z_cond = tf.concat([z, z_static, z_body, z_curv], axis=-1)
+        z_cond = self.cond_encoder_2(z_cond, training=training)
+
         return z_cond
 
     def call(self, inputs, training):
         levels_input, conds = inputs
         uv_static, uv_body, uv_curv = conds[0], conds[1], conds[2]
 
-        z_cond = self.encode_conds(uv_static, uv_body, uv_curv, training)
+        z_cond, z_static, z_body, z_curv = self.encode_conds(uv_static, uv_body, uv_curv, training)
 
         if self.add_noise == True and training == True:
             z_cond = z_cond + (tf.random.uniform(z_cond.shape, maxval=self.noise_amount * 2) - self.noise_amount)
 
         out_levels = []
-        pred, mean, logvar = self.levels[0](levels_input[0], z_cond, training=training)
+        pred, z, mean, logvar = self.levels[0](levels_input[0], z_cond, training=training)
         if self.use_offsets:
             pred = pred + levels_input[0][2] # uv_body_posed_32
         if 1 != len(self.levels):
             pred = self.levels[0].enhance(pred, levels_input[0][-2], training=training)  # levels_input[i][-2]=uv_mask_res
-            pred = tf.image.resize(pred, (self.levels[1].size, self.levels[1].size//2), tf.image.ResizeMethod.LANCZOS5)
             out_levels.append([pred, mean, logvar])
+            pred = tf.image.resize(pred, (self.levels[1].size, self.levels[1].size//2), tf.image.ResizeMethod.BILINEAR)
             pred = pred * levels_input[1][-2][:,:,:,tf.newaxis]
         else:
             pred = self.enhance(pred, levels_input[0][-2], training=training)
-            pred = tf.image.resize(pred, (512, 256), tf.image.ResizeMethod.LANCZOS5)
+            pred = tf.image.resize(pred, (512, 256), tf.image.ResizeMethod.BILINEAR)
             pred = pred * levels_input[-1][-1][:,:,:,tf.newaxis] # full res uv mask
             out_levels.append([pred, mean, logvar])
 
         for i in range(1, len(self.levels)):
-            pred_level, mean, logvar = self.levels[i](levels_input[i], z_cond, training=training)
+            input = levels_input[i]
+            input[0] = pred # use previous level output as input for next level
+            z_cond_2 = self.encode_conds_2(z, z_static, z_body, z_curv, training=training)
+
+            pred_level, z, mean, logvar = self.levels[i](input, z_cond_2, training=training)
             pred = pred + pred_level
             if i != len(self.levels) - 1:
                 pred = self.levels[i].enhance(pred, levels_input[i][-2], training=training)
                 out_levels.append([pred, mean, logvar])
-                pred = tf.image.resize(pred, (self.levels[i+1].size, self.levels[i+1].size//2), tf.image.ResizeMethod.LANCZOS5)
+                pred = tf.image.resize(pred, (self.levels[i+1].size, self.levels[i+1].size//2), tf.image.ResizeMethod.BILINEAR)
                 pred = pred * levels_input[i+1][-2][:,:,:,tf.newaxis]
             else:
                 if self.upscale_enhancer is not None:
                     pred = self.enhance(pred, levels_input[-1][-2], training=training)
-                    pred = tf.image.resize(pred, (512, 256), tf.image.ResizeMethod.LANCZOS5)
+                    pred = tf.image.resize(pred, (512, 256), tf.image.ResizeMethod.BILINEAR)
                 pred = pred * levels_input[-1][-1][:,:,:,tf.newaxis] # full res uv mask
                 out_levels.append([pred, mean, logvar])