added skinning and gnn discriminator

auto_encoder.py

@@ -1,17 +1,18 @@
 import os
 import time
 import argparse
+from cv2 import polarToCart
 import wandb
-from cv2 import drawFrameAxes
+import random
 import numpy as np
 import tensorflow as tf
 from custom_utils.custom_utils import UV2Mesh, maskFacesBatch
 from tensorboardX import SummaryWriter
+import plotly.graph_objects as go
 
 from utils import str_to_bool
 from tf_utils import check_tf_version, allow_memory_growth, split_gpu_for_testing
 from load_models import load_generator, load_discriminator
-from dataset import DatasetSimple
 from losses import d_logistic, d_logistic_r1_reg, g_logistic_non_saturating, g_logistic_ns_pathreg, edge_loss, uv_mask_loss
 # from losses import collision_penalty as collision_penalty
 from losses import collision_loss as collision_penalty
@@ -19,8 +20,8 @@ from convnext.models.convnext_tf import ConvNeXt
 from stylegan2_ae.generator import Generator
 
 
-os.environ["CUDA_VISIBLE_DEVICES"] = "3"
-run = wandb.init(config=tf.compat.v1.flags.FLAGS, sync_tensorboard=True, project='stylegan', name='ae_1_2', notes='convnext + stylegan generator')
+os.environ["CUDA_VISIBLE_DEVICES"] = "2"
+run = wandb.init(config=tf.compat.v1.flags.FLAGS, sync_tensorboard=True, project='stylegan', name='ae_unposed_1', notes='convnext + stylegan generator')
 artifact = wandb.Artifact('code', type='code')
 artifact.add_file('auto_encoder.py')
 artifact.add_file('stylegan2_ae/layers/mapping_block.py')
@@ -29,6 +30,35 @@ run.log_artifact(artifact)
 uv2mesh = UV2Mesh(res=256)
 
 
+class DatasetSimple(tf.data.Dataset):
+
+    def _generator(folder):
+        # Opening the file
+        folder = folder.decode("utf-8")
+        uv_folder = os.path.join(folder, 'uv_posed') 
+        frames = os.listdir(uv_folder)
+        random.shuffle(frames)
+
+        for frame in frames:
+            id, frame_nr = frame.split('.')[0].split('_')
+            mesh_mask = np.load(os.path.join(folder, 'mesh_mask', id + '.npy')); mesh_mask = mesh_mask.astype(np.float32)
+            uv_mask = np.load(os.path.join(folder, 'uv_mask', id + '.npz')); uv_mask=uv_mask['uv_mask']; uv_mask = uv_mask.astype(np.float32)
+            mesh_unposed = np.load(os.path.join(folder, 'mesh_unposed', id + '_' + frame_nr + '.npz')); mesh_unposed = mesh_unposed['mesh_unposed']
+            uv_unposed = np.load(os.path.join(folder, 'uv_unposed', id + '_' + frame_nr + '.npz')); uv_unposed = uv_unposed['uv_unposed']; uv_unposed = np.transpose(uv_unposed, [2, 0, 1])
+
+            yield uv_unposed, mesh_unposed, uv_mask, mesh_mask
+
+    def __new__(cls, folder, res=256):
+        return tf.data.Dataset.from_generator(
+            cls._generator,
+            output_signature = (tf.TensorSpec(shape = (3, res * 2, res,), dtype = tf.float32), 
+                                tf.TensorSpec(shape = (14475, 3,), dtype = tf.float32), 
+                                tf.TensorSpec(shape = (res * 2, res,), dtype = tf.float32), 
+                                tf.TensorSpec(shape = (14475,), dtype = tf.float32), ),
+            args=(folder, )
+        )
+
+
 
 def filter_resolutions_featuremaps(resolutions, featuremaps, res):
     index = resolutions.index(res)
@@ -37,6 +67,43 @@ def filter_resolutions_featuremaps(resolutions, featuremaps, res):
     return filtered_resolutions, filtered_featuremaps
 
 
+def plot_3d(mesh_gt, mesh_pred, faces):
+    mesh_pred[:,1] += 2
+    fig = go.Figure(data=[
+        go.Mesh3d(
+            # 8 vertices of a cube
+            x=mesh_gt[:,0],
+            y=mesh_gt[:,1],
+            z=mesh_gt[:,2],
+            # i, j and k give the vertices of triangles
+            i = faces[:,0],
+            j = faces[:,1],
+            k = faces[:,2]
+        ),
+        go.Mesh3d(
+            # 8 vertices of a cube
+            x=mesh_pred[:,0],
+            y=mesh_pred[:,1],
+            z=mesh_pred[:,2],
+            # i, j and k give the vertices of triangles
+            i = faces[:,0],
+            j = faces[:,1],
+            k = faces[:,2],
+        )
+    ])
+
+    fig.update_layout(scene_aspectmode='manual',
+                    scene_aspectratio=dict(x=1, y=2, z=1))
+    fig.update_layout(
+        scene = dict(
+            xaxis = dict(nticks=4, range=[-1,1],),
+                        yaxis = dict(nticks=4, range=[-1,3],),
+                        zaxis = dict(nticks=4, range=[-1,1],),)
+                        )
+
+    return fig
+
+
 class AutoEncoder(tf.keras.Model):
     
     def __init__(self):
@@ -78,19 +145,18 @@ class AutoEncoder(tf.keras.Model):
 
 @tf.function
 def train_step(batch):
-    posed_uv, conditions,_, mesh_body_posed, mesh_mask = batch
-    uv_mask = conditions[3]
+    uv_unposed, mesh_unposed, uv_mask, mesh_mask = batch
 
     with tf.GradientTape() as tape:
 
-        pred = model([posed_uv, uv_mask])
+        pred = model([uv_unposed, uv_mask])
 
         mesh_pred = uv2mesh(pred)
-        mesh_orig = uv2mesh(posed_uv)
+        mesh_orig = mesh_unposed
 
         e_loss = 0.0#edge_loss(mesh_pred, mesh_orig, mesh_mask)
         c_loss = 0.0#collision_penalty(mesh_pred, mesh_body_posed, mesh_mask)
-        l1_loss = tf.reduce_mean(tf.reduce_sum((tf.math.abs(posed_uv - pred)), axis=1) * uv_mask)
+        l1_loss = tf.reduce_mean(tf.reduce_sum((tf.math.abs(uv_unposed - pred)), axis=1) * uv_mask)
         loss = l1_loss + e_loss + c_loss
 
     metric = tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(mesh_mask[:,:,tf.newaxis] * (mesh_orig - mesh_pred) ** 2, axis=-1))) / tf.reduce_sum(mesh_mask)
@@ -102,16 +168,15 @@ def train_step(batch):
 
 @tf.function
 def valid_step(batch):
-    posed_uv, conditions,_, mesh_body_posed, mesh_mask = batch
-    uv_mask = conditions[3]
+    uv_unposed, mesh_unposed, uv_mask, mesh_mask = batch
 
-    pred = model([posed_uv, uv_mask])
+    pred = model([uv_unposed, uv_mask])
     mesh_pred = uv2mesh(pred)
-    mesh_orig = uv2mesh(posed_uv)
+    mesh_orig = mesh_unposed
 
     e_loss = 0.0#edge_loss(mesh_pred, mesh_orig, mesh_mask)
     c_loss = 0.0#collision_penalty(mesh_pred, mesh_body_posed, mesh_mask)
-    l1_loss = tf.reduce_mean(tf.reduce_sum((tf.math.abs(posed_uv - pred)), axis=1) * uv_mask)
+    l1_loss = tf.reduce_mean(tf.reduce_sum((tf.math.abs(uv_unposed - pred)), axis=1) * uv_mask)
     loss = l1_loss + e_loss + c_loss
 
     metric = tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(mesh_mask[:,:,tf.newaxis] * (mesh_orig - mesh_pred) ** 2, axis=-1))) / tf.reduce_sum(mesh_mask)
@@ -122,7 +187,7 @@ if __name__ == '__main__':
     allow_memory_growth()
     
     
-    name = 'test-9'
+    name = 'ae_unposed_1'
     dataset_train = DatasetSimple('/home/workspace/data/dataset/stylegan_new/train').cache().batch(8).repeat()
     dataset_valid = DatasetSimple('/home/workspace/data/dataset/stylegan_new/valid').cache().batch(8).repeat()
 
@@ -131,8 +196,7 @@ if __name__ == '__main__':
     optimizer = tf.optimizers.Adam()
     folder = 'models/ae_logs/'
     train_summary_writer = tf.summary.create_file_writer(folder + name + '/train')
-    valid_summary_writer = tf.summary.create_file_writer(folder + name + '/valid')
-    mesh_writer = SummaryWriter(folder + name + '/mesh')
+    # valid_summary_writer = tf.summary.create_file_writer(folder + name + '/valid')
 
     step = 0
     for batch in dataset_train:
@@ -142,18 +206,19 @@ if __name__ == '__main__':
             with train_summary_writer.as_default():
                 tf.summary.scalar(key, train_loss[key], step=step)
 
-        data_valid = iter(dataset_valid).get_next()
-        valid_loss = valid_step(data_valid)
+        data_valid = batch
+        # data_valid = iter(dataset_valid).get_next()
+        # valid_loss = valid_step(data_valid)
 
-        for key in valid_loss.keys():
-            with valid_summary_writer.as_default():
-                tf.summary.scalar(key, valid_loss[key], step=step)
+        # for key in valid_loss.keys():
+        #     with valid_summary_writer.as_default():
+        #         tf.summary.scalar(key, valid_loss[key], step=step)
 
         if step % 250 == 0:
-            pred = model([data_valid[0], data_valid[1][3]])
+            pred = model([data_valid[0], data_valid[2]])
             
             mesh_pred = uv2mesh(pred)
-            mesh_orig = uv2mesh(data_valid[0])
+            mesh_orig = data_valid[1]
             
             orig_img = tf.transpose(data_valid[0], [0,2,3,1])
             pred_img = tf.transpose(pred, [0,2,3,1])
@@ -162,12 +227,13 @@ if __name__ == '__main__':
                 tf.summary.image('images', img, step=step)
 
             F = np.load("custom_utils/smpl_faces.npy")
-            garment, faces = maskFacesBatch(mesh_pred.numpy(), F, data_valid[4].numpy().astype(bool))
-            gt, _ = maskFacesBatch(mesh_orig.numpy(), F, data_valid[4].numpy().astype(bool))
+            garment, faces = maskFacesBatch(mesh_pred.numpy(), F, data_valid[3].numpy().astype(bool))
+            gt = [mesh_orig[i].numpy()[data_valid[3][i].numpy().astype(bool), :] for i in range(pred.shape[0])]
             
-            for i in range(len(garment)):
-                mesh_writer.add_mesh('garment_pred_' + str(i), vertices=garment[i][np.newaxis,:,:], faces=faces[i][np.newaxis,:,:], global_step=step)
-                mesh_writer.add_mesh('garment_gt_' + str(i), vertices=gt[i][np.newaxis,:,:], faces=faces[i][np.newaxis,:,:], global_step=step)
+            for i in range(pred.shape[0]):
+                fig = plot_3d(gt[i], garment[i], faces[i])
+                wandb.log({"garment_" + str(i): fig})
+                
 
         print(step)