create end2end laplacian pyramid

aaa_helpers.txt

@@ -1,3 +1,6 @@
+nohup python cvae_pyramid.py --name="lhunor_pyr_abl_32_64_e2e_r3" > nohup/review/pyr_abl_32_64_e2e_r3.out 2>&1 &
+
+
 one final convolutional layer for smoothing, on the final coordinates
 
 skirts!!!!

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'
 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'] = ''
+config['pretrained_model_iteration'] = ''
 
 config['train_dir'] = '/home/workspace/local-data/train'
 config['valid_dir'] = '/home/workspace/local-data/valid'
@@ -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:

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_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
@@ -210,26 +210,107 @@ 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']
-            mesh_orig, uv_orig = batch['mesh_unposed'], batch['uv_unposed']
-        else:
-            mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed']
 
         output = dict()
         reconstr_loss_total = 0
         kl_total = 0
 
-        #for i, res in enumerate(config['pyramid']['resolutions']):
+        for i, res in enumerate(config['pyramid']['resolutions']):
-        i = -1
+            # i = -1
-        res = config['pyramid']['resolutions'][-1]
+            # res = config['pyramid']['resolutions'][-1]
-        res_modifier = '_' + str(res) if res != 512 else ''
+            if res != 512:
+                if i == len(config['pyramid']['resolutions']) - 1:
+                    res_modifier = ''
+                else:
+                    res_modifier = '_' + str(res)
+            else:
+                res_modifier = ''
+
+            pred, mean, logvar = out_levels[i]
+
+            mesh_pred = uv2mesh(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])])
+
+                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?
+
+            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)
+
+            # 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)
+
+            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
+
+    gradients = tape.gradient(loss, model.trainable_variables)
+    optimizer.apply_gradients(zip(gradients, model.trainable_variables))
+    return { **{ 'train/loss': loss, 'train/reconstr_loss_total': reconstr_loss_total, 'train/kl_total': kl_total }, **output }
+
+
+@tf.function
+def valid_step(batch):
+    levels_input, conds = group_inputs_for_levels(batch, config)
+    out_levels = model([levels_input, conds], training=False)
+
+    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]
+        if res != 512:
+            if i == len(config['pyramid']['resolutions']) - 1:
+                res_modifier = ''
+            else:
+                res_modifier = '_' + str(res)
+        else:
+            res_modifier = ''
+
         pred, mean, logvar = out_levels[i]
 
         mesh_pred = uv2mesh(pred)
@@ -243,13 +324,12 @@ def train_step(batch):
             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?
 
         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(((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))
@@ -273,83 +353,10 @@ def train_step(batch):
 
         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, 
+        output = { **output, **{ 'valid/edge_loss' + res_modifier: e_loss, 'valid/collision_loss' + res_modifier: c_loss,'valid/euclid_error' + res_modifier: metric, 
-                                 'train/mean' + res_modifier: mean, 'train/logvar' + res_modifier: logvar, 'train/kl_loss' + res_modifier: kl,
+                                    'valid/mean' + res_modifier: mean, 'valid/logvar' + res_modifier: logvar, 'valid/kl_loss' + res_modifier: kl,
-                                 'train/var' + res_modifier: np.e ** logvar, 'train/l2_loss' + res_modifier: l2_loss, 'train/normal_loss': n_loss,
+                                    'valid/var' + res_modifier: np.e ** logvar, 'valid/l2_loss' + res_modifier: l2_loss, 'valid/normal_loss': n_loss,
-                                 'train/euclid_error': metric, 'train/l2_mesh_loss': l2_mesh_loss } } # 'train/ms_ssim' + res_modifier: ms_ssim,
+                                    '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
-
-    gradients = tape.gradient(loss, model.trainable_variables)
-    optimizer.apply_gradients(zip(gradients, model.trainable_variables))
-    return { **{ 'train/loss': loss, 'train/reconstr_loss_total': reconstr_loss_total, 'train/kl_total': kl_total }, **output }
-
-
-@tf.function
-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']
-
-    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]
-
-    mesh_pred = uv2mesh(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])])
-
-        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?
-
-    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)
-
-    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']
-        
-    kl_total += kl
-
-    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'])
-
-    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 +807,16 @@ 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.static_enc.trainable = False
+    model.body_enc.trainable = False
-        model.body_enc.trainable = False
+    model.curv_enc.trainable = False
-        model.curv_enc.trainable = False
+    # if len(config['pyramid']['resolutions']) == 1:
-    else:
+    # else:
-        load_model(model, config['pyramid']['pretrained_pyramid'], iteration=(config['pyramid']['pretrained_pyramid_iteration'] if 'pretrained_pyramid_iteration' in config.keys() 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.static_enc.trainable = False
-        model.body_enc.trainable = False
+    #     model.body_enc.trainable = False
-        model.curv_enc.trainable = False
+    #     model.curv_enc.trainable = False
-        model.cond_encoder.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 +829,8 @@ 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):
+    # for i in range(len(model.levels)-1):
-        model.levels[i].trainable = False
+    #     model.levels[i].trainable = False
 
     # load_model(model.cond_encoder, config['pyramid']['pretrained_pyramid'])
     # load_model(model.levels[0], config['pyramid']['pretrained_pyramid'])

models/pyramid_model_optimized.py

@@ -107,27 +107,30 @@ class Pyramid(tf.keras.Model):
             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
+
+            pred_level, mean, logvar = self.levels[i](input, z_cond, 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])