add auto encoder

auto_encoder.py

@@ -0,0 +1,174 @@
+import os
+import time
+import argparse
+import wandb
+from cv2 import drawFrameAxes
+import numpy as np
+import tensorflow as tf
+from custom_utils.custom_utils import UV2Mesh, maskFacesBatch
+from tensorboardX import SummaryWriter
+
+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
+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')
+artifact = wandb.Artifact('code', type='code')
+artifact.add_file('auto_encoder.py')
+artifact.add_file('stylegan2_ae/layers/mapping_block.py')
+run.log_artifact(artifact)
+
+uv2mesh = UV2Mesh(res=256)
+
+
+
+def filter_resolutions_featuremaps(resolutions, featuremaps, res):
+    index = resolutions.index(res)
+    filtered_resolutions = resolutions[:index + 1]
+    filtered_featuremaps = featuremaps[:index + 1]
+    return filtered_resolutions, filtered_featuremaps
+
+
+class AutoEncoder(tf.keras.Model):
+    
+    def __init__(self):
+        super(AutoEncoder, self).__init__()
+
+        resolutions = [4, 8, 16, 32, 64, 128, 256, 512, 1024]
+        g_featuremaps = [256, 256, 256, 256, 256, 128, 64, 32, 16]
+        train_resolutions, train_g_featuremaps = filter_resolutions_featuremaps(resolutions, g_featuremaps, 512)
+        g_params = {
+            'z_dim': 256,
+            'w_dim': 256,
+            'labels_dim': -1,
+            'n_mapping': 8,
+            'resolutions': train_resolutions,
+            'featuremaps': train_g_featuremaps,
+        }
+
+        # test_latent = tf.ones((1, g_params['z_dim']), dtype=tf.float32)
+        self.decoder = Generator(g_params)
+        # _ = generator(test_latent)
+
+
+        self.encoder = ConvNeXt(depths=[3, 3, 27, 3], dims=[96, 192, 256, g_params['z_dim']], include_top=False)
+        self.pooling = tf.keras.layers.GlobalAveragePooling2D()
+
+
+    def call(self, inputs, training=None):
+        x, uv_mask = inputs
+
+        x = tf.transpose(x, [0,2,3,1])
+        x = self.encoder(x, training=training)
+        x = self.pooling(x)
+
+        x = self.decoder(x, training=training)
+        x = x * uv_mask[:,tf.newaxis,:,:]
+
+        return x
+
+
+@tf.function
+def train_step(batch):
+    posed_uv, conditions,_, mesh_body_posed, mesh_mask = batch
+    uv_mask = conditions[3]
+
+    with tf.GradientTape() as tape:
+
+        pred = model([posed_uv, uv_mask])
+
+        mesh_pred = uv2mesh(pred)
+        mesh_orig = uv2mesh(posed_uv)
+
+        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)
+        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)
+    gradients = tape.gradient(loss, model.trainable_variables)
+    optimizer.apply_gradients(zip(gradients, model.trainable_variables))
+    return { 'loss': loss, 'edge_loss': e_loss, 'collision_loss': c_loss, 'l1_loss': l1_loss, 'euclid_error': metric }
+        
+
+
+@tf.function
+def valid_step(batch):
+    posed_uv, conditions,_, mesh_body_posed, mesh_mask = batch
+    uv_mask = conditions[3]
+
+    pred = model([posed_uv, uv_mask])
+    mesh_pred = uv2mesh(pred)
+    mesh_orig = uv2mesh(posed_uv)
+
+    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)
+    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)
+    return { 'loss': loss, 'edge_loss': e_loss, 'collision_loss': c_loss, 'l1_loss': l1_loss, 'euclid_error': metric }
+
+
+if __name__ == '__main__':
+    allow_memory_growth()
+    
+    
+    name = 'test-9'
+    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()
+
+    model = AutoEncoder()
+    # optimizer = tf.optimizers.Adam(learning_rate=0.002, beta_1=0.0, beta_2=0.99, epsilon=1e-8)
+    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')
+
+    step = 0
+    for batch in dataset_train:
+        train_loss = train_step(batch)
+
+        for key in train_loss.keys():
+            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)
+
+        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]])
+            
+            mesh_pred = uv2mesh(pred)
+            mesh_orig = uv2mesh(data_valid[0])
+            
+            orig_img = tf.transpose(data_valid[0], [0,2,3,1])
+            pred_img = tf.transpose(pred, [0,2,3,1])
+            img = tf.concat((orig_img, pred_img), axis=2)
+            with train_summary_writer.as_default():
+                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))
+            
+            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)
+
+        print(step)
+
+        step += 1