nonlinearjunkie

position_block_15 = base_model.get_layer('block_15_add')

for layer in base_model.layers:
    layer.trainable = True
    

all_layers = base_model.layers
for i in range(base_model.layers.index(position_block_15)):
    all_layers[i].trainable = False
    

nonlinearjunkie

base_model = tf.keras.applications.MobileNetV2(input_shape=(224,224,3),
                                               alpha=1.0,
                                               include_top=False,
                                               weights="imagenet")
for layer in base_model.layers:
    layer.trainable = False
    
model_transfered_1=Sequential()

model_transfered_1.add(base_model)

nonlinearjunkie

base_model = tf.keras.applications.MobileNetV2(input_shape=(224,224,3),
                                               alpha=1.0,
                                               include_top=False,
                                               weights="imagenet")
for layer in base_model.layers:
    layer.trainable = False
    
model_transfered_1=Sequential()

model_transfered_1.add(base_model)

nonlinearjunkie

model=Sequential()

# Conv-layer-1
model.add(Conv2D(32,(3,3),input_shape=(128,128,1)))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(Dropout(0.3))

# Conv-layer-2

nonlinearjunkie

model=Sequential()

# Conv-layer-1
model.add(Conv2D(32,(3,3),input_shape=(128,128,1)))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2,2)))

# Conv-layer-2
model.add(Conv2D(128,(5,5)))