def deform_center_cnn(class_num, trainable=False, GPU=1):
conv_args = {
'trainable': trainable,
'kernel_initializer': Orthogonal(gain=1.0, seed=None),
'kernel_regularizer': OrthLocalReg2D,
'padding': 'same'
}
sep_conv_args = {
'trainable': trainable,
'kernel_initializer': Orthogonal(gain=1.0, seed=None),
'kernel_regularizer': OrthLocalRegSep2D,
'padding': 'same'
}
inputs = l = Input((None, None, 3), name='input')
input_target = Input((1, ), name='input_target')
# norm_input = RGB2Gray()(inputs)
norm_input = ImageNorm()(inputs)
# norm_input = inputs
stem_stride = (2, 2)
# conv11
l = Conv2D(32, (3, 3), strides=stem_stride, name='conv11',
**conv_args)(norm_input)
l = Activation('relu', name='conv11_relu')(l)
l = BatchNormalization(name='conv11_bn')(l)
l2 = InvConv2D(32, (3, 3),
strides=stem_stride,
name='inv_conv11',
**conv_args)(norm_input)
l2 = Activation('relu', name='inv_conv11_relu')(l2)
l2 = BatchNormalization(name='inv_conv11_bn')(l2)
l = concatenate([l, l2])
l5 = SeparableConv2D(64, (5, 5),
strides=(2, 2),
name='conv5_11_12',
**sep_conv_args)(l)
l5 = Activation('relu', name='conv5_11_12_relu')(l5)
l5 = BatchNormalization(name='conv5_11_12_bn')(l5)
l3 = SeparableConv2D(64, (3, 3),
strides=(2, 2),
name='conv3_11_12',
**sep_conv_args)(l)
l3 = Activation('relu', name='conv3_11_12_relu')(l3)
l3 = BatchNormalization(name='conv3_11_12_bn')(l3)
l = concatenate([l3, l5])
l = SeparableConv2D(128, (3, 3), name='conv12_1', **sep_conv_args)(l)
l = Activation('relu', name='conv12_1_relu')(l)
l = BatchNormalization(name='conv12_1_bn')(l)
l = SeparableConv2D(128, (1, 1), name='conv12_2', **sep_conv_args)(l)
l = Activation('relu', name='conv12_2_relu')(l)
l = BatchNormalization(name='conv12_2_bn')(l)
l = SeparableConv2D(128, (3, 3), name='conv13', **sep_conv_args)(l)
l = Activation('relu', name='conv13_relu')(l)
l = BatchNormalization(name='conv13_bn')(l)
l = SeparableConv2D(256, (3, 3),
strides=(2, 2),
name='conv14',
**sep_conv_args)(l)
l = Activation('relu', name='conv14_relu')(l)
l = l14 = BatchNormalization(name='conv14_bn')(l)
l = SeparableConv2D(256, (3, 3), name='conv21', **sep_conv_args)(l)
l = Activation('relu', name='conv21_relu')(l)
l = BatchNormalization(name='conv21_bn')(l)
l = SeparableConv2D(256, (3, 3), name='conv22', **sep_conv_args)(l)
l = Activation('relu', name='conv22_relu')(l)
l = BatchNormalization(name='conv22_bn')(l)
l = Add(name='residual_14_22')([l14, l])
# conv22
# l_offset = ConvOffset2D(192, name='conv32_offset')(l)
# l = Conv2D(256, (3, 3), strides=(2, 2), name='conv23', **conv_args)(l)
# l = Activation('relu', name='conv23_relu')(l)
# l = l23 = BatchNormalization(name='conv23_bn')(l)
#
# l = Conv2D(256, (3, 3), name='conv31', **conv_args)(l)
# l = Activation('relu', name='conv31_relu')(l)
# l = BatchNormalization(name='conv31_bn')(l)
# l = Conv2D(256, (1, 1), name='conv32', **conv_args)(l31)
# l = Activation('relu', name='conv32_relu')(l)
# l = BatchNormalization(name='conv32_bn')(l)
# l = Conv2D(256, (3, 3), name='conv33', **conv_args)(l)
# l = Activation('relu', name='conv33_relu')(l)
# l = BatchNormalization(name='conv33_bn')(l)
# l = Add(name='residual_23_33')([l23, l])
l_offset = ConvOffset2D(256, name='conv33_offset')(l)
l = SeparableConv2D(512, (3, 3),
strides=(2, 2),
name='conv41',
**sep_conv_args)(l_offset)
l = Activation('relu', name='conv41_relu')(l)
l = BatchNormalization(name='conv41_bn')(l)
l = SeparableConv2D(512, (3, 3), name='conv42', **sep_conv_args)(l)
l = Activation('relu', name='conv42_relu')(l)
l = BatchNormalization(name='conv42_bn')(l)
# l_offset = ConvOffset2D(512, name='conv35_offset')(l)
l = SeparableConv2D(512, (3, 3), name='conv43', **sep_conv_args)(l)
l = Activation('relu', name='conv43_relu')(l)
l = BatchNormalization(name='conv43_bn')(l)
# l = LocallyConnected2D(512, (3, 3), name='conv44', padding='valid')(l)
# l = Activation('relu', name='conv44_relu')(l)
# l = BatchNormalization(name='conv44_bn')(l)
l = SeparableConv2D(1024, (3, 3),
strides=(2, 2),
name='conv51',
**sep_conv_args)(l)
l = Activation('relu', name='conv51_relu')(l)
l = BatchNormalization(name='conv51_bn')(l)
# l_offset = ConvOffset2D(1024, name='conv35_offset')(l)
l = SeparableConv2D(1024, (3, 3), name='conv52', **sep_conv_args)(l)
l = Activation('relu', name='conv52_relu')(l)
l = BatchNormalization(name='conv52_bn')(l)
l = SeparableConv2D(1024, (3, 3), name='conv53', **sep_conv_args)(l)
l = Activation('relu', name='conv53_relu')(l)
l = BatchNormalization(name='conv53_bn')(l)
# out
l = GlobalAvgPool2D(name='avg_pool')(l)
# l = MaxPooling2D(name='max_pool_final')(l)
# l = Flatten(name='flatten_maxpool')(l)
l = Dense(512, name='fc1', trainable=trainable)(l)
l = Activation('relu', name='fc1_relu')(l)
l = Dense(256, name='fc2', trainable=trainable)(l)
l = feature = Activation('relu', name='fc2_relu')(l)
l = Dense(class_num, name='fc3', trainable=trainable)(l)
outputs = l = Activation('softmax', name='out')(l)
if GPU == 1:
centers = Embedding(class_num, 256)(input_target)
l2_loss = Lambda(
lambda x: K.sum(K.square(x[0] - x[1][:, 0]), 1, keepdims=True),
name='l2_loss')([feature, centers])
Model(inputs=[inputs, input_target], outputs=[outputs, l2_loss])
elif GPU == 0:
return inputs, outputs
else:
BODY = Model(inputs=[inputs, input_target], outputs=[outputs, feature])
BODY = make_parallel(BODY, GPU)
softmax_output = Lambda(lambda x: x, name='output')(BODY.outputs[0])
centers = Embedding(class_num, 256)(input_target)
l2_loss = Lambda(
lambda x: K.sum(K.square(x[0] - x[1][:, 0]), 1, keepdims=True),
name='l2_loss')([BODY.outputs[1], centers])
model_withcneter = Model(inputs=BODY.inputs,
outputs=[softmax_output, l2_loss])
return model_withcneter
def get_large_deform_cnn2(class_num, trainable=False, GPU=1):
# init = Orthogonal(gain=1.0, seed=None)
init = 'random_normal'
inputs = l = Input((200, 200, 3), name='input')
input_target = Input((1, ), name='input_target')
#norm_input = ImageNorm()(inputs)
norm_input = inputs
# conv11
l = Conv2D(32, (3, 3),
padding='same',
name='conv11',
trainable=trainable,
kernel_initializer=init,
kernel_regularizer=OrthLocalReg2D)(norm_input)
l = Activation('relu', name='conv11_relu')(l)
l = BatchNormalization(name='conv11_bn')(l)
l2 = InvConv2D(32, (3, 3),
padding='same',
name='inv_conv11',
trainable=trainable,
kernel_initializer=init,
kernel_regularizer=OrthLocalReg2D)(norm_input)
l2 = Activation('relu', name='inv_conv11_relu')(l2)
l2 = BatchNormalization(name='inv_conv11_bn')(l2)
l3 = Conv2D(32, (3, 1),
padding='same',
name='conv11_2',
trainable=trainable,
kernel_initializer=init,
kernel_regularizer=OrthLocalReg2D)(norm_input)
l3 = Activation('relu', name='conv11_2_relu')(l3)
l3 = BatchNormalization(name='conv11_2_bn')(l3)
l5 = Conv2D(32, (1, 3),
padding='same',
name='conv11_3',
trainable=trainable,
kernel_initializer=init,
kernel_regularizer=OrthLocalReg2D)(norm_input)
l5 = Activation('relu', name='conv11_3_relu')(l5)
l5 = BatchNormalization(name='conv11_3_bn')(l5)
l4 = InvConv2D(32, (3, 1),
padding='same',
name='conv11_2i',
trainable=trainable,
kernel_initializer=init,
kernel_regularizer=OrthLocalReg2D)(norm_input)
l4 = Activation('relu', name='conv11_2i_relu')(l4)
l4 = BatchNormalization(name='conv11_2i_bn')(l4)
l6 = InvConv2D(32, (1, 3),
padding='same',
name='conv11_3i',
trainable=trainable,
kernel_initializer=init,
kernel_regularizer=OrthLocalReg2D)(norm_input)
l6 = Activation('relu', name='conv11_3i_relu')(l6)
l6 = BatchNormalization(name='conv11_3i_bn')(l6)
l = concatenate([l, l2, l3, l5, l4, l6])
# conv12
# l_offset = ConvOffset2D(32, name='conv12_offset')(l)
l5 = Conv2D(128, (5, 5),
padding='same',
strides=(2, 2),
name='pool5_11_12',
trainable=trainable,
kernel_initializer=init,
kernel_regularizer=OrthLocalReg2D)(l)
l5 = Activation('relu', name='pool5_11_12_relu')(l5)
l5 = BatchNormalization(name='pool5_11_12_bn')(l5)
l3 = Conv2D(128, (3, 3),
padding='same',
strides=(2, 2),
name='pool3_11_12',
trainable=trainable,
kernel_initializer=init,
kernel_regularizer=OrthLocalReg2D)(l)
l3 = Activation('relu', name='pool3_11_12_relu')(l3)
l3 = BatchNormalization(name='pool3_11_12_bn')(l3)
l = concatenate([l3, l5])
l3 = Conv2D(32, (5, 3),
padding='same',
name='conv12_2',
trainable=trainable,
kernel_initializer=init,
kernel_regularizer=OrthLocalReg2D)(l)
l3 = Activation('relu', name='conv12_2_relu')(l3)
l3 = BatchNormalization(name='conv12_2_bn')(l3)
l5 = Conv2D(32, (3, 5),
padding='same',
name='conv12_3',
trainable=trainable,
kernel_initializer=init,
kernel_regularizer=OrthLocalReg2D)(l)
l5 = Activation('relu', name='conv12_3_relu')(l5)
l5 = BatchNormalization(name='conv12_3_bn')(l5)
l = Conv2D(128, (3, 3),
padding='same',
name='conv12',
trainable=trainable,
kernel_initializer=init,
kernel_regularizer=OrthLocalReg2D)(l)
l = Activation('relu', name='conv12_relu')(l)
l = BatchNormalization(name='conv12_bn')(l)
l = concatenate([l, l3, l5])
l = Conv2D(128, (3, 3),
padding='same',
name='conv13',
trainable=trainable,
kernel_initializer=init,
kernel_regularizer=OrthLocalReg2D)(l)
l = Activation('relu', name='conv13_relu')(l)
l = jump = BatchNormalization(name='conv13_bn')(l)
l = Conv2D(192, (3, 3),
padding='same',
strides=(2, 2),
name='conv14',
trainable=trainable,
kernel_initializer=init,
kernel_regularizer=OrthLocalReg2D)(l)
l = Activation('relu', name='conv14_relu')(l)
# l = BatchNormalization(name='conv14_bn')(l)
l = Conv2D(192, (3, 3),
padding='same',
name='conv21',
trainable=trainable,
kernel_initializer=init,
kernel_regularizer=OrthLocalReg2D)(l)
l = Activation('relu', name='conv21_relu')(l)
l = BatchNormalization(name='conv21_bn')(l)
l = Conv2D(192, (3, 3),
padding='same',
name='conv22',
trainable=trainable,
kernel_initializer=init,
kernel_regularizer=OrthLocalReg2D)(l)
l = Activation('relu', name='conv22_relu')(l)
l = BatchNormalization(name='conv22_bn')(l)
# conv22
# l_offset = ConvOffset2D(192, name='conv32_offset')(l)
l = Conv2D(256, (3, 3),
padding='same',
strides=(2, 2),
name='conv23',
trainable=trainable,
kernel_initializer=init,
kernel_regularizer=OrthLocalReg2D)(l)
l = Activation('relu', name='conv23_relu')(l)
l = BatchNormalization(name='conv23_bn')(l)
l = Conv2D(256, (3, 3),
padding='same',
name='conv31',
trainable=trainable,
kernel_initializer=init,
kernel_regularizer=OrthLocalReg2D)(l)
l = Activation('relu', name='conv31_relu')(l)
l31 = BatchNormalization(name='conv31_bn')(l)
# l = Conv2D(256, (1, 1), padding='same', name='conv32', trainable=trainable, kernel_initializer=init, kernel_regularizer=OrthLocalReg2D)(l31)
# l = Activation('relu', name='conv32_relu')(l)
# l = BatchNormalization(name='conv32_bn')(l)
l = Conv2D(256, (3, 3),
padding='same',
name='conv33',
trainable=trainable,
kernel_initializer=init,
kernel_regularizer=OrthLocalReg2D)(l)
l = Activation('relu', name='conv33_relu')(l)
l = BatchNormalization(name='conv33_bn')(l)
l = Add(name='residual_31_32')([l31, l])
lj = Conv2D(256, (3, 3),
padding='same',
strides=(2, 2),
name='jump_pool',
trainable=trainable,
kernel_initializer=init,
kernel_regularizer=OrthLocalReg2D)(jump)
lj = Activation('relu', name='jump_pool_relu')(lj)
lj = BatchNormalization(name='jump_pool_bn')(lj)
lj = Conv2D(256, (3, 3),
padding='same',
strides=(2, 2),
name='jump_pool2',
trainable=trainable,
kernel_initializer=init,
kernel_regularizer=OrthLocalReg2D)(lj)
lj = Activation('relu', name='jump_pool2_relu')(lj)
lj = BatchNormalization(name='jump_pool2_bn')(lj)
l = concatenate([l, lj])
l_offset = ConvOffset2D(512, name='conv33_offset')(l)
l = Conv2D(512, (3, 3),
padding='same',
strides=(2, 2),
name='conv41',
trainable=trainable,
kernel_initializer=init,
kernel_regularizer=OrthLocalReg2D)(l_offset)
l = Activation('relu', name='conv41_relu')(l)
l = BatchNormalization(name='conv41_bn')(l)
l = Conv2D(512, (3, 3),
padding='same',
name='conv42',
trainable=trainable,
kernel_initializer=init,
kernel_regularizer=OrthLocalReg2D)(l)
l = Activation('relu', name='conv42_relu')(l)
l = BatchNormalization(name='conv42_bn')(l)
# l_offset = ConvOffset2D(512, name='conv35_offset')(l)
l = Conv2D(512, (3, 3),
padding='same',
name='conv43',
trainable=trainable,
kernel_initializer=init,
kernel_regularizer=OrthLocalReg2D)(l)
l = Activation('relu', name='conv43_relu')(l)
l = BatchNormalization(name='conv43_bn')(l)
# out
# l = GlobalAvgPool2D(name='avg_pool')(l)
l = MaxPooling2D(name='max_pool_final')(l)
l = Flatten(name='flatten_maxpool')(l)
l = Dense(768,
name='fc1',
trainable=trainable,
kernel_initializer=init,
kernel_regularizer=OrthLocalReg1D)(l)
l = Activation('relu', name='fc1_relu')(l)
l = feature = Dense(256,
name='fc2',
trainable=trainable,
kernel_initializer=init)(l)
l = Activation('relu', name='fc2_relu')(l)
l = Dense(class_num, name='fc3', trainable=trainable)(l)
outputs = l = Activation('softmax', name='out')(l)
if GPU == 1:
centers = Embedding(class_num, 256)(input_target)
l2_loss = Lambda(
lambda x: K.sum(K.square(x[0] - x[1][:, 0]), 1, keepdims=True),
name='l2_loss')([feature, centers])
Model(inputs=[inputs, input_target], outputs=[outputs, l2_loss])
elif GPU == 0:
return inputs, outputs
else:
BODY = Model(inputs=[inputs, input_target], outputs=[outputs, feature])
BODY = make_parallel(BODY, GPU)
softmax_output = Lambda(lambda x: x, name='output')(BODY.outputs[0])
centers = Embedding(class_num, 256)(input_target)
l2_loss = Lambda(
lambda x: K.sum(K.square(x[0] - x[1][:, 0]), 1, keepdims=True),
name='l2_loss')([BODY.outputs[1], centers])
model_withcneter = Model(inputs=BODY.inputs,
outputs=[softmax_output, l2_loss])
return model_withcneter
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
with tf.Session(config=config) as sess:
with tf.device(GPU):
K.set_session(sess)
# ---
# Deformable CNN
inputs, outputs = get_large_res_deform_cnn2(class_num, trainable=True)
model = Model(inputs=inputs, outputs=outputs)
model.summary()
if GPU_NUM > 1:
model = make_parallel(model, GPU_NUM)
if args.weight is not None:
print(colored("[weight] %s" % args.weight, color='green'))
model.load_weights(args.weight)
optim = Adam(1e-4)
# optim = SGD(1e-4, momentum=0.99, nesterov=True)
loss = categorical_crossentropy
# model._weights('../models/deform_cnn.h5')
model.compile(optim, [loss, loss], metrics=['accuracy'])
checkpoint = ModelCheckpoint("deform_cnn_inv_best.h5",
monitor='concatenate_3_acc',
save_best_only=True)
checkpoint_tl = ModelCheckpoint("deform_cnn_inv_trainbest.h5",
parser = argparse.ArgumentParser()
parser.add_argument("-w", "--weight", help=".h5 model weight file.")
parser.add_argument("-g", "--gpu_num", help="gpu number used when training this model.")
parser.add_argument("-c", "--class_num", help="number of class of classifier's output")
args = parser.parse_args()
class_num = int(args.class_num) if args.class_num is not None else 6
K.set_learning_phase(0)
inputs, outputs = get_test_cnn(class_num, trainable=False)
# inputs, outputs = get_large_deform_cnn(class_num, trainable=True)
# inputs, outputs = get_large_deform_cnn(class_num, trainable=True)
model = Model(inputs=inputs, outputs=outputs)
if args.gpu_num:
model = make_parallel(model, int(args.gpu_num))
model.load_weights(args.weight)
model.summary()
if args.gpu_num:
print(colored('[Deparallelize model]', color='green'))
single_gpu_model = model.layers[-2] # TODO: subscript of layers may change?
model = single_gpu_model
model.summary()
model_name = args.weight[:-3] + '_1gpu.h5'
model.save_weights(model_name)
print(colored('Restart this script with new .h5 weight:', color='red'))
print(model_name)
sys.exit(0)
