Merge branch 'review_7' into iccv_resnet
This commit is contained in:
+31
-13
@@ -1,5 +1,7 @@
|
||||
import tensorflow as tf
|
||||
from convnext.models.convnext_tf import ConvNeXt, ConvNeXtReverse, Block, ConvNeXtReverseLabels
|
||||
from models.resnet import resnet_18, make_basic_block_layer
|
||||
|
||||
|
||||
class Bottleneck(tf.keras.Model):
|
||||
|
||||
@@ -111,20 +113,34 @@ class Decoder(tf.keras.Model):
|
||||
|
||||
class VariationalEncoderNew(tf.keras.Model):
|
||||
|
||||
def __init__(self, depths, dims, kernel_size=7):
|
||||
def __init__(self, features):
|
||||
super(VariationalEncoderNew, self).__init__()
|
||||
|
||||
self.encoder = ConvNeXt(depths=depths, dims=dims, include_top=False, kernel_size=kernel_size)
|
||||
self.encoder = resnet_18(features)
|
||||
|
||||
self.mean_branch = tf.keras.Sequential(
|
||||
[Block(dim=64, drop_path=0, kernel_size=kernel_size,
|
||||
layer_scale_init_value=1e-6, prefix=f'bottleneck{j}') for j in range(5)]
|
||||
)
|
||||
self.mean_branch = tf.keras.Sequential([
|
||||
tf.keras.layers.Conv2D(filters=features,
|
||||
kernel_size=(3, 3),
|
||||
strides=1,
|
||||
padding="same"),
|
||||
tf.keras.layers.BatchNormalization(),
|
||||
tf.keras.layers.Conv2D(filters=features,
|
||||
kernel_size=(3, 3),
|
||||
strides=1,
|
||||
padding="same")
|
||||
])
|
||||
|
||||
self.var_branch = tf.keras.Sequential(
|
||||
[Block(dim=64, drop_path=0, kernel_size=kernel_size,
|
||||
layer_scale_init_value=1e-6, prefix=f'bottleneck{j}') for j in range(5)]
|
||||
)
|
||||
self.var_branch = tf.keras.Sequential([
|
||||
tf.keras.layers.Conv2D(filters=features,
|
||||
kernel_size=(3, 3),
|
||||
strides=1,
|
||||
padding="same"),
|
||||
tf.keras.layers.BatchNormalization(),
|
||||
tf.keras.layers.Conv2D(filters=features,
|
||||
kernel_size=(3, 3),
|
||||
strides=1,
|
||||
padding="same")
|
||||
])
|
||||
|
||||
self.flatten_mean = tf.keras.layers.Flatten()
|
||||
self.flatten_var = tf.keras.layers.Flatten()
|
||||
@@ -147,10 +163,10 @@ class VariationalEncoderNew(tf.keras.Model):
|
||||
|
||||
class AEEncoderNew(tf.keras.Model):
|
||||
|
||||
def __init__(self, depths, dims, kernel_size=7, activation='tanh'):
|
||||
def __init__(self, features, activation='tanh'):
|
||||
super(AEEncoderNew, self).__init__()
|
||||
|
||||
self.encoder = ConvNeXt(depths=depths, dims=dims, include_top=False, kernel_size=kernel_size)
|
||||
self.encoder = resnet_18(features)
|
||||
self.act = tf.keras.layers.Activation(activation)
|
||||
|
||||
|
||||
@@ -171,15 +187,17 @@ class AEEncoderNew(tf.keras.Model):
|
||||
|
||||
class DecoderNew(tf.keras.Model):
|
||||
|
||||
def __init__(self, features, is_label=False, is_cvae=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 = resnet_18(features, reversed=True, is_cvae=is_cvae)
|
||||
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)
|
||||
self.decoder = resnet_18(features, reversed=True, labels=6, is_cvae=is_cvae)
|
||||
|
||||
|
||||
def call(self, inputs, training):
|
||||
|
||||
@@ -25,8 +25,8 @@ class AutoEncoderNew(tf.keras.Model):
|
||||
def __init__(self, config):
|
||||
super(AutoEncoderNew, self).__init__()
|
||||
|
||||
self.encoder : AEEncoderNew = AEEncoderNew(config['encoder_depths'], config['encoder_dims'], config['kernel_size'], config['activation'])
|
||||
self.decoder : DecoderNew = DecoderNew(config['decoder_depths'], config['decoder_dims'], kernel_size=config['kernel_size'], is_label=config['is_label'])
|
||||
self.encoder : AEEncoderNew = AEEncoderNew(config['bottleneck_size'], config['activation'])
|
||||
self.decoder : DecoderNew = DecoderNew(config['bottleneck_size'], is_label=config['is_label'])
|
||||
|
||||
|
||||
def call(self, inputs, training):
|
||||
|
||||
@@ -159,16 +159,16 @@ class CVAENew(tf.keras.Model):
|
||||
self.size = config['resolution']
|
||||
|
||||
if not('only_curvatures' in config.keys() and config['only_curvatures'] == True):
|
||||
self.static_enc : AEEncoderNew = AEEncoderNew(config['cond_ae_static']['encoder_depths'], config['cond_ae_static']['encoder_dims'], config['cond_ae_static']['kernel_size'], config['cond_ae_static']['activation'])
|
||||
self.static_enc : AEEncoderNew = AEEncoderNew(config['cond_ae_static']['bottleneck_size'], config['cond_ae_static']['activation'])
|
||||
if config['static_model'] != '':
|
||||
load_model(self.static_enc, config['static_model'] + '_enc')
|
||||
|
||||
self.body_enc : AEEncoderNew = AEEncoderNew(config['cond_ae_body']['encoder_depths'], config['cond_ae_body']['encoder_dims'], config['cond_ae_body']['kernel_size'])
|
||||
self.body_enc : AEEncoderNew = AEEncoderNew(config['cond_ae_body']['bottleneck_size'])
|
||||
if config['body_model'] != '':
|
||||
load_model(self.body_enc, config['body_model'] + '_enc')
|
||||
|
||||
if config['use_curvature']:
|
||||
self.curv_enc : AEEncoderNew = AEEncoderNew(config['cond_ae_curv']['encoder_depths'], config['cond_ae_curv']['encoder_dims'], config['cond_ae_curv']['kernel_size'], config['cond_ae_curv']['activation'])
|
||||
self.curv_enc : AEEncoderNew = AEEncoderNew(config['cond_ae_curv']['bottleneck_size'], config['cond_ae_curv']['activation'])
|
||||
if config['curvature_model'] != '':
|
||||
load_model(self.curv_enc, config['curvature_model'] + '_enc')
|
||||
|
||||
@@ -182,8 +182,10 @@ 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.encoder = VariationalEncoderNew(config['cvae']['encoder_dims'][-1])
|
||||
self.decoder = DecoderNew(config['cvae']['decoder_dims'][-1], is_cvae=True)
|
||||
|
||||
self.reshape = tf.keras.layers.Reshape((8, 4, 64))
|
||||
self.reshape = tf.keras.layers.Reshape((8, 4, config['cvae']['decoder_dims'][-1]))
|
||||
|
||||
if config['avg_garment_path'] != '':
|
||||
self.avg_garment = np.load(config['avg_garment_path'])
|
||||
|
||||
@@ -0,0 +1,254 @@
|
||||
# taken from https://github.com/calmisential/TensorFlow2.0_ResNet/blob/master/models/resnet.py
|
||||
|
||||
import tensorflow as tf
|
||||
|
||||
|
||||
class BasicBlock(tf.keras.layers.Layer):
|
||||
|
||||
def __init__(self, filter_num, stride=1, upsample=False):
|
||||
super(BasicBlock, self).__init__()
|
||||
if not upsample:
|
||||
self.conv1 = tf.keras.layers.Conv2D(filters=filter_num,
|
||||
kernel_size=(3, 3),
|
||||
strides=stride,
|
||||
padding="same")
|
||||
else:
|
||||
self.conv1 = tf.keras.layers.Conv2DTranspose(filters=filter_num,
|
||||
kernel_size=(3, 3),
|
||||
strides=stride,
|
||||
padding="same")
|
||||
self.bn1 = tf.keras.layers.BatchNormalization()
|
||||
self.conv2 = tf.keras.layers.Conv2D(filters=filter_num,
|
||||
kernel_size=(3, 3),
|
||||
strides=1,
|
||||
padding="same")
|
||||
self.bn2 = tf.keras.layers.BatchNormalization()
|
||||
if stride != 1:
|
||||
if not upsample:
|
||||
self.updownsample = tf.keras.Sequential()
|
||||
self.updownsample.add(tf.keras.layers.Conv2D(filters=filter_num,
|
||||
kernel_size=(1, 1),
|
||||
strides=stride))
|
||||
self.updownsample.add(tf.keras.layers.BatchNormalization())
|
||||
else:
|
||||
self.updownsample = tf.keras.Sequential()
|
||||
self.updownsample.add(tf.keras.layers.Conv2DTranspose(filters=filter_num,
|
||||
kernel_size=(1, 1),
|
||||
strides=stride))
|
||||
self.updownsample.add(tf.keras.layers.BatchNormalization())
|
||||
else:
|
||||
self.updownsample = lambda x: x
|
||||
|
||||
def call(self, inputs, training=None, **kwargs):
|
||||
residual = self.updownsample(inputs)
|
||||
|
||||
x = self.conv1(inputs)
|
||||
x = self.bn1(x, training=training)
|
||||
x = tf.nn.relu(x)
|
||||
x = self.conv2(x)
|
||||
x = self.bn2(x, training=training)
|
||||
|
||||
output = tf.nn.relu(tf.keras.layers.add([residual, x]))
|
||||
|
||||
return output
|
||||
|
||||
|
||||
class BottleNeck(tf.keras.layers.Layer):
|
||||
def __init__(self, filter_num, stride=1):
|
||||
super(BottleNeck, self).__init__()
|
||||
self.conv1 = tf.keras.layers.Conv2D(filters=filter_num,
|
||||
kernel_size=(1, 1),
|
||||
strides=1,
|
||||
padding='same')
|
||||
self.bn1 = tf.keras.layers.BatchNormalization()
|
||||
self.conv2 = tf.keras.layers.Conv2D(filters=filter_num,
|
||||
kernel_size=(3, 3),
|
||||
strides=stride,
|
||||
padding='same')
|
||||
self.bn2 = tf.keras.layers.BatchNormalization()
|
||||
self.conv3 = tf.keras.layers.Conv2D(filters=filter_num * 4,
|
||||
kernel_size=(1, 1),
|
||||
strides=1,
|
||||
padding='same')
|
||||
self.bn3 = tf.keras.layers.BatchNormalization()
|
||||
|
||||
self.downsample = tf.keras.Sequential()
|
||||
self.downsample.add(tf.keras.layers.Conv2D(filters=filter_num * 4,
|
||||
kernel_size=(1, 1),
|
||||
strides=stride))
|
||||
self.downsample.add(tf.keras.layers.BatchNormalization())
|
||||
|
||||
def call(self, inputs, training=None, **kwargs):
|
||||
residual = self.downsample(inputs)
|
||||
|
||||
x = self.conv1(inputs)
|
||||
x = self.bn1(x, training=training)
|
||||
x = tf.nn.relu(x)
|
||||
x = self.conv2(x)
|
||||
x = self.bn2(x, training=training)
|
||||
x = tf.nn.relu(x)
|
||||
x = self.conv3(x)
|
||||
x = self.bn3(x, training=training)
|
||||
|
||||
output = tf.nn.relu(tf.keras.layers.add([residual, x]))
|
||||
|
||||
return output
|
||||
|
||||
|
||||
def make_basic_block_layer(filter_num, blocks, stride=1, upsample=False):
|
||||
res_block = tf.keras.Sequential()
|
||||
res_block.add(BasicBlock(filter_num, stride=stride, upsample=upsample))
|
||||
|
||||
for _ in range(1, blocks):
|
||||
res_block.add(BasicBlock(filter_num, stride=1))
|
||||
|
||||
return res_block
|
||||
|
||||
|
||||
def make_bottleneck_layer(filter_num, blocks, stride=1):
|
||||
res_block = tf.keras.Sequential()
|
||||
res_block.add(BottleNeck(filter_num, stride=stride))
|
||||
|
||||
for _ in range(1, blocks):
|
||||
res_block.add(BottleNeck(filter_num, stride=1))
|
||||
|
||||
return res_block
|
||||
|
||||
|
||||
class ResNetTypeI(tf.keras.Model):
|
||||
def __init__(self, layer_params, features, reversed=False, labels=None, is_cvae=False):
|
||||
super(ResNetTypeI, self).__init__()
|
||||
self.reversed = reversed
|
||||
self.labels = labels
|
||||
|
||||
if not reversed:
|
||||
self.conv1 = tf.keras.layers.Conv2D(filters=64,
|
||||
kernel_size=(7, 7),
|
||||
strides=2,
|
||||
padding="same")
|
||||
self.bn1 = tf.keras.layers.BatchNormalization()
|
||||
self.pool1 = tf.keras.layers.MaxPool2D(pool_size=(3, 3),
|
||||
strides=2,
|
||||
padding="same")
|
||||
else:
|
||||
self.conv1 = tf.keras.layers.Conv2DTranspose(filters=3 if labels is None else labels,
|
||||
kernel_size=(7, 7),
|
||||
strides=2,
|
||||
padding="same")
|
||||
self.bn1 = tf.keras.layers.BatchNormalization()
|
||||
# self.pool1 = tf.keras.layers.MaxPool2D(pool_size=(3, 3),
|
||||
# strides=2,
|
||||
# padding="same")
|
||||
self.pool1 = tf.keras.layers.UpSampling2D()
|
||||
|
||||
self.layer1 = make_basic_block_layer(filter_num=64,
|
||||
blocks=layer_params[0],
|
||||
stride=1 if not reversed else 2,
|
||||
upsample=reversed)
|
||||
self.layer2 = make_basic_block_layer(filter_num=64,
|
||||
blocks=layer_params[1],
|
||||
stride=2,
|
||||
upsample=reversed)
|
||||
self.layer3 = make_basic_block_layer(filter_num=64,
|
||||
blocks=layer_params[2],
|
||||
stride=2,
|
||||
upsample=reversed)
|
||||
self.layer4 = make_basic_block_layer(filter_num=128,
|
||||
blocks=layer_params[3],
|
||||
stride=2,
|
||||
upsample=reversed)
|
||||
self.layer5 = make_basic_block_layer(filter_num=features if not is_cvae else features*2,
|
||||
blocks=layer_params[4],
|
||||
stride=2 if not reversed else 1,
|
||||
upsample=reversed)
|
||||
|
||||
def call(self, inputs, training=None, mask=None):
|
||||
if not self.reversed:
|
||||
x = self.conv1(inputs)
|
||||
x = self.bn1(x, training=training)
|
||||
x = tf.nn.relu(x)
|
||||
x = self.pool1(x)
|
||||
x = self.layer1(x, training=training)
|
||||
x = self.layer2(x, training=training)
|
||||
x = self.layer3(x, training=training)
|
||||
x = self.layer4(x, training=training)
|
||||
x = self.layer5(x, training=training)
|
||||
else:
|
||||
x = self.layer5(inputs, training=training)
|
||||
x = self.layer4(x, training=training)
|
||||
x = self.layer3(x, training=training)
|
||||
x = self.layer2(x, training=training)
|
||||
x = self.layer1(x, training=training)
|
||||
|
||||
x = self.pool1(x)
|
||||
x = self.bn1(x, training=training)
|
||||
# x = tf.nn.relu(x)
|
||||
x = self.conv1(x)
|
||||
if self.labels is None:
|
||||
x = tf.nn.tanh(x)
|
||||
# else:
|
||||
# x = tf.nn.softmax(x)
|
||||
|
||||
return x
|
||||
|
||||
|
||||
class ResNetTypeII(tf.keras.Model):
|
||||
def __init__(self, layer_params):
|
||||
super(ResNetTypeII, self).__init__()
|
||||
self.conv1 = tf.keras.layers.Conv2D(filters=64,
|
||||
kernel_size=(7, 7),
|
||||
strides=2,
|
||||
padding="same")
|
||||
self.bn1 = tf.keras.layers.BatchNormalization()
|
||||
self.pool1 = tf.keras.layers.MaxPool2D(pool_size=(3, 3),
|
||||
strides=2,
|
||||
padding="same")
|
||||
|
||||
self.layer1 = make_bottleneck_layer(filter_num=64,
|
||||
blocks=layer_params[0])
|
||||
self.layer2 = make_bottleneck_layer(filter_num=128,
|
||||
blocks=layer_params[1],
|
||||
stride=2)
|
||||
self.layer3 = make_bottleneck_layer(filter_num=256,
|
||||
blocks=layer_params[2],
|
||||
stride=2)
|
||||
self.layer4 = make_bottleneck_layer(filter_num=512,
|
||||
blocks=layer_params[3],
|
||||
stride=2)
|
||||
|
||||
self.avgpool = tf.keras.layers.GlobalAveragePooling2D()
|
||||
self.fc = tf.keras.layers.Dense(units=NUM_CLASSES, activation=tf.keras.activations.softmax)
|
||||
|
||||
def call(self, inputs, training=None, mask=None):
|
||||
x = self.conv1(inputs)
|
||||
x = self.bn1(x, training=training)
|
||||
x = tf.nn.relu(x)
|
||||
x = self.pool1(x)
|
||||
x = self.layer1(x, training=training)
|
||||
x = self.layer2(x, training=training)
|
||||
x = self.layer3(x, training=training)
|
||||
x = self.layer4(x, training=training)
|
||||
x = self.avgpool(x)
|
||||
output = self.fc(x)
|
||||
|
||||
return output
|
||||
|
||||
|
||||
def resnet_18(features, reversed=False, labels=None, is_cvae=False):
|
||||
return ResNetTypeI(layer_params=[2, 2, 2, 2, 2], features=features, reversed=reversed, labels=labels, is_cvae=is_cvae)
|
||||
|
||||
|
||||
def resnet_34():
|
||||
return ResNetTypeI(layer_params=[3, 4, 6, 3])
|
||||
|
||||
|
||||
def resnet_50():
|
||||
return ResNetTypeII(layer_params=[3, 4, 6, 3])
|
||||
|
||||
|
||||
def resnet_101():
|
||||
return ResNetTypeII(layer_params=[3, 4, 23, 3])
|
||||
|
||||
|
||||
def resnet_152():
|
||||
return ResNetTypeII(layer_params=[3, 8, 36, 3])
|
||||
Reference in New Issue
Block a user