def extract_DenseNet(path):
import densenet
from keras.preprocessing import image
import numpy as np
img = image.load_img(path, target_size=(224, 224))
x = image.img_to_array(img)
img_tensor = densenet.preprocess_input(np.expand_dims(x, axis=0))
image_dim = (224, 224, 3)
DenseNet_model = densenet.DenseNetImageNet161(input_shape=image_dim,
include_top=False)
DenseNet_output = DenseNet_model.predict(img_tensor)
return DenseNet_output
def cnn_model():
input_tensor = Input(shape=(params.target_img_size[0],params.target_img_size[1],params.num_channels))
baseModel = densenet.DenseNetImageNet161(input_shape=(params.target_img_size[0], params.target_img_size[1], params.num_channels), include_top=False, input_tensor=input_tensor)
modelStruct = baseModel.layers[-1].output
modelStruct = Dense(params.cnn_last_layer_length, activation='relu', name='fc1')(modelStruct)
modelStruct = Dropout(0.5)(modelStruct)
modelStruct = Dense(params.cnn_last_layer_length, activation='relu', name='fc2')(modelStruct)
modelStruct = Dropout(0.5)(modelStruct)
predictions = Dense(params.num_labels, activation='softmax')(modelStruct)
model = Model(inputs=[baseModel.input], outputs=predictions)
for i,layer in enumerate(model.layers[-5:]):
layer.trainable = True
for i,layer in enumerate(model.layers[:-5]):
layer.trainable = False
return model
https://github.com/titu1994/DenseNet
The imported |densenet| library is from this repo.
This script was RUN IN THAT REPO, and the files moved over.
"""
import densenet
import keras
from keras.models import Model
import json
image_dim = (224, 224, 3) # Tensorflow backend
print("Image dimensions set to %s." % str(image_dim))
print("Loading denseNet model...")
densenet_model = densenet.DenseNetImageNet161(input_shape=image_dim,
include_top=False)
print("Extracting a subset of denseNet to use as an encoder.")
n_final_layer = 393
print("Final layer is %d." % n_final_layer)
inp = densenet_model.input
res56 = densenet_model.layers[49]
print("res56 layer is %s" % str(res56))
out_res56 = res56.output
res28 = densenet_model.layers[137]
print("res28 layer is %s" % str(res28))
out_res28 = res28.output
def get_cnn_model(params):
"""
Load base CNN model and add metadata fusion layers if 'use_metadata' is set in params.py
:param params: global parameters, used to find location of the dataset and json file
:return model: CNN model with or without depending on params
"""
input_tensor = Input(shape=(params.target_img_size[0],
params.target_img_size[1],
params.num_channels))
baseModel = densenet.DenseNetImageNet161(
input_shape=(params.target_img_size[0], params.target_img_size[1],
params.num_channels),
include_top=False,
input_tensor=input_tensor)
modelStruct = baseModel.layers[-1].output
if params.use_nlm:
modelStruct = baseModel.layers[-2].output
modelStruct = non_local_block(modelStruct,
computation_compression=1,
mode='embedded')
modelStruct = Conv2D(params.cnn_lstm_layer_length, [3, 3],
name='conv_nlm')(modelStruct)
modelStruct = Flatten()(modelStruct)
modelStruct = Dense(params.cnn_lstm_layer_length,
activation='relu',
name='fc_nlm')(modelStruct)
modelStruct = Dropout(0.5)(modelStruct)
if params.use_spp:
modelStruct = baseModel.layers[-2].output
modelStruct = SpatialPyramidPooling([1, 2, 4], name='spp')(modelStruct)
modelStruct = Dense(params.cnn_lstm_layer_length,
activation='relu',
name='fc_spp')(modelStruct)
modelStruct = Dropout(0.5)(modelStruct)
if params.use_deform:
modelStruct = baseModel.layers[-2].output
modelStruct = ConvOffset2D(params.cnn_lstm_layer_length,
name='deform')(modelStruct)
modelStruct = Conv2D(params.cnn_lstm_layer_length, [3, 3],
name='conv_deform')(modelStruct)
modelStruct = Flatten()(modelStruct)
modelStruct = Dense(params.cnn_lstm_layer_length,
activation='relu',
name='fc_deform')(modelStruct)
modelStruct = Dropout(0.5)(modelStruct)
if params.use_metadata:
auxiliary_input = Input(shape=(params.metadata_length, ),
name='aux_input')
modelStruct = merge([modelStruct, auxiliary_input], 'concat')
modelStruct = Dense(params.cnn_last_layer_length,
activation='relu',
name='fc1')(modelStruct)
modelStruct = Dropout(0.5)(modelStruct)
modelStruct = Dense(params.cnn_last_layer_length,
activation='relu',
name='fc2')(modelStruct)
modelStruct = Dropout(0.5)(modelStruct)
predictions = Dense(params.num_labels, activation='softmax')(modelStruct)
if not params.use_metadata:
model = Model(input=[baseModel.input], output=predictions)
else:
model = Model(input=[baseModel.input, auxiliary_input],
output=predictions)
for i, layer in enumerate(model.layers):
layer.trainable = True
return model
bn_weights[-1][1] = v_w[1]
continue
v = f[name]
v_w = v[v.attrs['weight_names'][0]][:]
conv_weights.append(v_w)
count_layers = 1 # for dense matrix
count_layers += len(conv_weights)
count_layers += len(bn_weights)
print('Copying %d weights. (%d layers)' % (count_layers, count_layers // 2))
import densenet
model = densenet.DenseNetImageNet161((224, 224, 3), weights=None)
conv_layer_ids = []
bn_layer_ids = []
for i, layer in enumerate(model.layers):
if layer.__class__.__name__ == 'Input':
continue
if layer.__class__.__name__ == 'Activation':
continue
if layer.__class__.__name__ == 'MaxPooling2D':
continue
if layer.__class__.__name__ == 'AveragePooling2D':