Add keras.applications, refactor 2 convnet scripts
This commit is contained in:
parent
d0659327bd
commit
f23f2ff2c9
@ -3,32 +3,21 @@
|
||||
This script can run on CPU in a few minutes (with the TensorFlow backend).
|
||||
|
||||
Results example: http://i.imgur.com/4nj4KjN.jpg
|
||||
|
||||
Before running this script, download the weights for the VGG16 model at:
|
||||
https://drive.google.com/file/d/0Bz7KyqmuGsilT0J5dmRCM0ROVHc/view?usp=sharing
|
||||
(source: https://gist.github.com/baraldilorenzo/07d7802847aaad0a35d3)
|
||||
and make sure the variable `weights_path` in this script matches the location of the file.
|
||||
'''
|
||||
from __future__ import print_function
|
||||
from scipy.misc import imsave
|
||||
import numpy as np
|
||||
import time
|
||||
import os
|
||||
import h5py
|
||||
|
||||
from keras.models import Sequential
|
||||
from keras.layers import Convolution2D, ZeroPadding2D, MaxPooling2D
|
||||
from keras.applications import vgg16
|
||||
from keras import backend as K
|
||||
|
||||
# dimensions of the generated pictures for each filter.
|
||||
img_width = 128
|
||||
img_height = 128
|
||||
|
||||
# path to the model weights file.
|
||||
weights_path = 'vgg16_weights.h5'
|
||||
|
||||
# the name of the layer we want to visualize (see model definition below)
|
||||
layer_name = 'conv5_1'
|
||||
# the name of the layer we want to visualize
|
||||
# (see model definition at keras/applications/vgg16.py)
|
||||
layer_name = 'block5_conv1'
|
||||
|
||||
# util function to convert a tensor into a valid image
|
||||
def deprocess_image(x):
|
||||
@ -43,70 +32,22 @@ def deprocess_image(x):
|
||||
|
||||
# convert to RGB array
|
||||
x *= 255
|
||||
x = x.transpose((1, 2, 0))
|
||||
if K.image_dim_ordering() == 'th':
|
||||
x = x.transpose((1, 2, 0))
|
||||
x = np.clip(x, 0, 255).astype('uint8')
|
||||
return x
|
||||
|
||||
# build the VGG16 network
|
||||
model = Sequential()
|
||||
model.add(ZeroPadding2D((1, 1), batch_input_shape=(1, 3, img_width, img_height)))
|
||||
first_layer = model.layers[-1]
|
||||
# this is a placeholder tensor that will contain our generated images
|
||||
input_img = first_layer.input
|
||||
|
||||
model.add(Convolution2D(64, 3, 3, activation='relu', name='conv1_1'))
|
||||
model.add(ZeroPadding2D((1, 1)))
|
||||
model.add(Convolution2D(64, 3, 3, activation='relu', name='conv1_2'))
|
||||
model.add(MaxPooling2D((2, 2), strides=(2, 2)))
|
||||
|
||||
model.add(ZeroPadding2D((1, 1)))
|
||||
model.add(Convolution2D(128, 3, 3, activation='relu', name='conv2_1'))
|
||||
model.add(ZeroPadding2D((1, 1)))
|
||||
model.add(Convolution2D(128, 3, 3, activation='relu', name='conv2_2'))
|
||||
model.add(MaxPooling2D((2, 2), strides=(2, 2)))
|
||||
|
||||
model.add(ZeroPadding2D((1, 1)))
|
||||
model.add(Convolution2D(256, 3, 3, activation='relu', name='conv3_1'))
|
||||
model.add(ZeroPadding2D((1, 1)))
|
||||
model.add(Convolution2D(256, 3, 3, activation='relu', name='conv3_2'))
|
||||
model.add(ZeroPadding2D((1, 1)))
|
||||
model.add(Convolution2D(256, 3, 3, activation='relu', name='conv3_3'))
|
||||
model.add(MaxPooling2D((2, 2), strides=(2, 2)))
|
||||
|
||||
model.add(ZeroPadding2D((1, 1)))
|
||||
model.add(Convolution2D(512, 3, 3, activation='relu', name='conv4_1'))
|
||||
model.add(ZeroPadding2D((1, 1)))
|
||||
model.add(Convolution2D(512, 3, 3, activation='relu', name='conv4_2'))
|
||||
model.add(ZeroPadding2D((1, 1)))
|
||||
model.add(Convolution2D(512, 3, 3, activation='relu', name='conv4_3'))
|
||||
model.add(MaxPooling2D((2, 2), strides=(2, 2)))
|
||||
|
||||
model.add(ZeroPadding2D((1, 1)))
|
||||
model.add(Convolution2D(512, 3, 3, activation='relu', name='conv5_1'))
|
||||
model.add(ZeroPadding2D((1, 1)))
|
||||
model.add(Convolution2D(512, 3, 3, activation='relu', name='conv5_2'))
|
||||
model.add(ZeroPadding2D((1, 1)))
|
||||
model.add(Convolution2D(512, 3, 3, activation='relu', name='conv5_3'))
|
||||
model.add(MaxPooling2D((2, 2), strides=(2, 2)))
|
||||
|
||||
# load the weights of the VGG16 networks
|
||||
# (trained on ImageNet, won the ILSVRC competition in 2014)
|
||||
# note: when there is a complete match between your model definition
|
||||
# and your weight savefile, you can simply call model.load_weights(filename)
|
||||
assert os.path.exists(weights_path), 'Model weights not found (see "weights_path" variable in script).'
|
||||
f = h5py.File(weights_path)
|
||||
for k in range(f.attrs['nb_layers']):
|
||||
if k >= len(model.layers):
|
||||
# we don't look at the last (fully-connected) layers in the savefile
|
||||
break
|
||||
g = f['layer_{}'.format(k)]
|
||||
weights = [g['param_{}'.format(p)] for p in range(g.attrs['nb_params'])]
|
||||
model.layers[k].set_weights(weights)
|
||||
f.close()
|
||||
# build the VGG16 network with ImageNet weights
|
||||
model = vgg16.VGG16(weights='imagenet', include_top=False)
|
||||
print('Model loaded.')
|
||||
|
||||
model.summary()
|
||||
|
||||
# this is the placeholder for the input images
|
||||
input_img = model.input
|
||||
|
||||
# get the symbolic outputs of each "key" layer (we gave them unique names).
|
||||
layer_dict = dict([(layer.name, layer) for layer in model.layers])
|
||||
layer_dict = dict([(layer.name, layer) for layer in model.layers[1:]])
|
||||
|
||||
|
||||
def normalize(x):
|
||||
@ -124,7 +65,10 @@ for filter_index in range(0, 200):
|
||||
# we build a loss function that maximizes the activation
|
||||
# of the nth filter of the layer considered
|
||||
layer_output = layer_dict[layer_name].output
|
||||
loss = K.mean(layer_output[:, filter_index, :, :])
|
||||
if K.image_dim_ordering() == 'th':
|
||||
loss = K.mean(layer_output[:, filter_index, :, :])
|
||||
else:
|
||||
loss = K.mean(layer_output[:, :, :, filter_index])
|
||||
|
||||
# we compute the gradient of the input picture wrt this loss
|
||||
grads = K.gradients(loss, input_img)[0]
|
||||
@ -139,7 +83,11 @@ for filter_index in range(0, 200):
|
||||
step = 1.
|
||||
|
||||
# we start from a gray image with some random noise
|
||||
input_img_data = np.random.random((1, 3, img_width, img_height)) * 20 + 128.
|
||||
if K.image_dim_ordering() == 'th':
|
||||
input_img_data = np.random.random((1, 3, img_width, img_height))
|
||||
else:
|
||||
input_img_data = np.random.random((1, img_width, img_height, 3))
|
||||
input_img_data = (input_img_data - 0.5) * 20 + 128
|
||||
|
||||
# we run gradient ascent for 20 steps
|
||||
for i in range(20):
|
||||
|
@ -1,10 +1,5 @@
|
||||
'''Neural style transfer with Keras.
|
||||
|
||||
Before running this script, download the weights for the VGG16 model at:
|
||||
https://drive.google.com/file/d/0Bz7KyqmuGsilT0J5dmRCM0ROVHc/view?usp=sharing
|
||||
(source: https://gist.github.com/baraldilorenzo/07d7802847aaad0a35d3)
|
||||
and make sure the variable `weights_path` in this script matches the location of the file.
|
||||
|
||||
Run the script with:
|
||||
```
|
||||
python neural_style_transfer.py path_to_your_base_image.jpg path_to_your_reference.jpg prefix_for_results
|
||||
@ -15,7 +10,6 @@ python neural_style_transfer.py img/tuebingen.jpg img/starry_night.jpg results/m
|
||||
```
|
||||
|
||||
It is preferable to run this script on GPU, for speed.
|
||||
If running on CPU, prefer the TensorFlow backend (much faster).
|
||||
|
||||
Example result: https://twitter.com/fchollet/status/686631033085677568
|
||||
|
||||
@ -49,16 +43,14 @@ keeping the generated image close enough to the original one.
|
||||
'''
|
||||
|
||||
from __future__ import print_function
|
||||
from scipy.misc import imread, imresize, imsave
|
||||
from keras.preprocessing.image import load_img, img_to_array
|
||||
from scipy.misc import imsave
|
||||
import numpy as np
|
||||
from scipy.optimize import fmin_l_bfgs_b
|
||||
import time
|
||||
import os
|
||||
import argparse
|
||||
import h5py
|
||||
|
||||
from keras.models import Sequential
|
||||
from keras.layers import Convolution2D, ZeroPadding2D, MaxPooling2D
|
||||
from keras.applications import vgg16
|
||||
from keras import backend as K
|
||||
|
||||
parser = argparse.ArgumentParser(description='Neural style transfer with Keras.')
|
||||
@ -73,14 +65,12 @@ args = parser.parse_args()
|
||||
base_image_path = args.base_image_path
|
||||
style_reference_image_path = args.style_reference_image_path
|
||||
result_prefix = args.result_prefix
|
||||
weights_path = 'vgg16_weights.h5'
|
||||
|
||||
# these are the weights of the different loss components
|
||||
total_variation_weight = 1.
|
||||
style_weight = 1.
|
||||
content_weight = 0.025
|
||||
|
||||
|
||||
# dimensions of the generated picture.
|
||||
img_width = 400
|
||||
img_height = 400
|
||||
@ -88,22 +78,23 @@ assert img_height == img_width, 'Due to the use of the Gram matrix, width and he
|
||||
|
||||
# util function to open, resize and format pictures into appropriate tensors
|
||||
def preprocess_image(image_path):
|
||||
img = imresize(imread(image_path), (img_width, img_height))
|
||||
img = img[:, :, ::-1].astype('float64')
|
||||
img[:, :, 0] -= 103.939
|
||||
img[:, :, 1] -= 116.779
|
||||
img[:, :, 2] -= 123.68
|
||||
img = img.transpose((2, 0, 1))
|
||||
img = load_img(image_path, target_size=(img_width, img_height))
|
||||
img = img_to_array(img)
|
||||
img = np.expand_dims(img, axis=0)
|
||||
img = vgg16.preprocess_input(img)
|
||||
return img
|
||||
|
||||
# util function to convert a tensor into a valid image
|
||||
def deprocess_image(x):
|
||||
x = x.transpose((1, 2, 0))
|
||||
if K.image_dim_ordering() == 'th':
|
||||
x = x.reshape((3, img_width, img_height))
|
||||
x = x.transpose((1, 2, 0))
|
||||
else:
|
||||
x = x.reshape((img_width, img_height, 3))
|
||||
x = x[:, :, ::-1]
|
||||
x[:, :, 0] += 103.939
|
||||
x[:, :, 1] += 116.779
|
||||
x[:, :, 2] += 123.68
|
||||
x = x[:, :, ::-1]
|
||||
x = np.clip(x, 0, 255).astype('uint8')
|
||||
return x
|
||||
|
||||
@ -112,7 +103,10 @@ base_image = K.variable(preprocess_image(base_image_path))
|
||||
style_reference_image = K.variable(preprocess_image(style_reference_image_path))
|
||||
|
||||
# this will contain our generated image
|
||||
combination_image = K.placeholder((1, 3, img_width, img_height))
|
||||
if K.image_dim_ordering() == 'th':
|
||||
combination_image = K.placeholder((1, 3, img_width, img_height))
|
||||
else:
|
||||
combination_image = K.placeholder((1, img_width, img_height, 3))
|
||||
|
||||
# combine the 3 images into a single Keras tensor
|
||||
input_tensor = K.concatenate([base_image,
|
||||
@ -120,60 +114,9 @@ input_tensor = K.concatenate([base_image,
|
||||
combination_image], axis=0)
|
||||
|
||||
# build the VGG16 network with our 3 images as input
|
||||
first_layer = ZeroPadding2D((1, 1))
|
||||
first_layer.set_input(input_tensor, shape=(3, 3, img_width, img_height))
|
||||
|
||||
model = Sequential()
|
||||
model.add(first_layer)
|
||||
model.add(Convolution2D(64, 3, 3, activation='relu', name='conv1_1'))
|
||||
model.add(ZeroPadding2D((1, 1)))
|
||||
model.add(Convolution2D(64, 3, 3, activation='relu'))
|
||||
model.add(MaxPooling2D((2, 2), strides=(2, 2)))
|
||||
|
||||
model.add(ZeroPadding2D((1, 1)))
|
||||
model.add(Convolution2D(128, 3, 3, activation='relu', name='conv2_1'))
|
||||
model.add(ZeroPadding2D((1, 1)))
|
||||
model.add(Convolution2D(128, 3, 3, activation='relu'))
|
||||
model.add(MaxPooling2D((2, 2), strides=(2, 2)))
|
||||
|
||||
model.add(ZeroPadding2D((1, 1)))
|
||||
model.add(Convolution2D(256, 3, 3, activation='relu', name='conv3_1'))
|
||||
model.add(ZeroPadding2D((1, 1)))
|
||||
model.add(Convolution2D(256, 3, 3, activation='relu'))
|
||||
model.add(ZeroPadding2D((1, 1)))
|
||||
model.add(Convolution2D(256, 3, 3, activation='relu'))
|
||||
model.add(MaxPooling2D((2, 2), strides=(2, 2)))
|
||||
|
||||
model.add(ZeroPadding2D((1, 1)))
|
||||
model.add(Convolution2D(512, 3, 3, activation='relu', name='conv4_1'))
|
||||
model.add(ZeroPadding2D((1, 1)))
|
||||
model.add(Convolution2D(512, 3, 3, activation='relu', name='conv4_2'))
|
||||
model.add(ZeroPadding2D((1, 1)))
|
||||
model.add(Convolution2D(512, 3, 3, activation='relu'))
|
||||
model.add(MaxPooling2D((2, 2), strides=(2, 2)))
|
||||
|
||||
model.add(ZeroPadding2D((1, 1)))
|
||||
model.add(Convolution2D(512, 3, 3, activation='relu', name='conv5_1'))
|
||||
model.add(ZeroPadding2D((1, 1)))
|
||||
model.add(Convolution2D(512, 3, 3, activation='relu'))
|
||||
model.add(ZeroPadding2D((1, 1)))
|
||||
model.add(Convolution2D(512, 3, 3, activation='relu'))
|
||||
model.add(MaxPooling2D((2, 2), strides=(2, 2)))
|
||||
|
||||
# load the weights of the VGG16 networks
|
||||
# (trained on ImageNet, won the ILSVRC competition in 2014)
|
||||
# note: when there is a complete match between your model definition
|
||||
# and your weight savefile, you can simply call model.load_weights(filename)
|
||||
assert os.path.exists(weights_path), 'Model weights not found (see "weights_path" variable in script).'
|
||||
f = h5py.File(weights_path)
|
||||
for k in range(f.attrs['nb_layers']):
|
||||
if k >= len(model.layers):
|
||||
# we don't look at the last (fully-connected) layers in the savefile
|
||||
break
|
||||
g = f['layer_{}'.format(k)]
|
||||
weights = [g['param_{}'.format(p)] for p in range(g.attrs['nb_params'])]
|
||||
model.layers[k].set_weights(weights)
|
||||
f.close()
|
||||
# the model will be loaded with pre-trained ImageNet weights
|
||||
model = vgg16.VGG16(input_tensor=input_tensor,
|
||||
weights='imagenet', include_top=False)
|
||||
print('Model loaded.')
|
||||
|
||||
# get the symbolic outputs of each "key" layer (we gave them unique names).
|
||||
@ -213,19 +156,25 @@ def content_loss(base, combination):
|
||||
# designed to keep the generated image locally coherent
|
||||
def total_variation_loss(x):
|
||||
assert K.ndim(x) == 4
|
||||
a = K.square(x[:, :, :img_width-1, :img_height-1] - x[:, :, 1:, :img_height-1])
|
||||
b = K.square(x[:, :, :img_width-1, :img_height-1] - x[:, :, :img_width-1, 1:])
|
||||
if K.image_dim_ordering() == 'th':
|
||||
a = K.square(x[:, :, :img_width-1, :img_height-1] - x[:, :, 1:, :img_height-1])
|
||||
b = K.square(x[:, :, :img_width-1, :img_height-1] - x[:, :, :img_width-1, 1:])
|
||||
else:
|
||||
a = K.square(x[:, :img_width-1, :img_height-1, :] - x[:, 1:, :img_height-1, :])
|
||||
b = K.square(x[:, :img_width-1, :img_height-1, :] - x[:, :img_width-1, 1:, :])
|
||||
return K.sum(K.pow(a + b, 1.25))
|
||||
|
||||
# combine these loss functions into a single scalar
|
||||
loss = K.variable(0.)
|
||||
layer_features = outputs_dict['conv4_2']
|
||||
layer_features = outputs_dict['block4_conv2']
|
||||
base_image_features = layer_features[0, :, :, :]
|
||||
combination_features = layer_features[2, :, :, :]
|
||||
loss += content_weight * content_loss(base_image_features,
|
||||
combination_features)
|
||||
|
||||
feature_layers = ['conv1_1', 'conv2_1', 'conv3_1', 'conv4_1', 'conv5_1']
|
||||
feature_layers = ['block1_conv1', 'block2_conv1',
|
||||
'block3_conv1', 'block4_conv1',
|
||||
'block5_conv1']
|
||||
for layer_name in feature_layers:
|
||||
layer_features = outputs_dict[layer_name]
|
||||
style_reference_features = layer_features[1, :, :, :]
|
||||
@ -244,8 +193,12 @@ else:
|
||||
outputs.append(grads)
|
||||
|
||||
f_outputs = K.function([combination_image], outputs)
|
||||
|
||||
def eval_loss_and_grads(x):
|
||||
x = x.reshape((1, 3, img_width, img_height))
|
||||
if K.image_dim_ordering() == 'th':
|
||||
x = x.reshape((1, 3, img_width, img_height))
|
||||
else:
|
||||
x = x.reshape((1, img_width, img_height, 3))
|
||||
outs = f_outputs([x])
|
||||
loss_value = outs[0]
|
||||
if len(outs[1:]) == 1:
|
||||
@ -283,10 +236,11 @@ evaluator = Evaluator()
|
||||
|
||||
# run scipy-based optimization (L-BFGS) over the pixels of the generated image
|
||||
# so as to minimize the neural style loss
|
||||
x = np.random.uniform(0, 255, (1, 3, img_width, img_height))
|
||||
x[0, 0, :, :] -= 103.939
|
||||
x[0, 1, :, :] -= 116.779
|
||||
x[0, 2, :, :] -= 123.68
|
||||
if K.image_dim_ordering() == 'th':
|
||||
x = np.random.uniform(0, 255, (1, 3, img_width, img_height)) - 128.
|
||||
else:
|
||||
x = np.random.uniform(0, 255, (1, img_width, img_height, 3)) - 128.
|
||||
|
||||
for i in range(10):
|
||||
print('Start of iteration', i)
|
||||
start_time = time.time()
|
||||
@ -294,7 +248,7 @@ for i in range(10):
|
||||
fprime=evaluator.grads, maxfun=20)
|
||||
print('Current loss value:', min_val)
|
||||
# save current generated image
|
||||
img = deprocess_image(x.copy().reshape((3, img_width, img_height)))
|
||||
img = deprocess_image(x.copy())
|
||||
fname = result_prefix + '_at_iteration_%d.png' % i
|
||||
imsave(fname, img)
|
||||
end_time = time.time()
|
||||
|
0
keras/applications/__init__.py
Normal file
0
keras/applications/__init__.py
Normal file
43
keras/applications/imagenet_utils.py
Normal file
43
keras/applications/imagenet_utils.py
Normal file
@ -0,0 +1,43 @@
|
||||
import numpy as np
|
||||
import json
|
||||
|
||||
from ..utils.data_utils import get_file
|
||||
from .. import backend as K
|
||||
|
||||
CLASS_INDEX = None
|
||||
CLASS_INDEX_PATH = 'https://s3.amazonaws.com/deep-learning-models/image-models/imagenet_class_index.json'
|
||||
|
||||
|
||||
def preprocess_input(x, dim_ordering='default'):
|
||||
if dim_ordering == 'default':
|
||||
dim_ordering = K.image_dim_ordering()
|
||||
assert dim_ordering in {'tf', 'th'}
|
||||
|
||||
if dim_ordering == 'th':
|
||||
x[:, 0, :, :] -= 103.939
|
||||
x[:, 1, :, :] -= 116.779
|
||||
x[:, 2, :, :] -= 123.68
|
||||
# 'RGB'->'BGR'
|
||||
x = x[:, ::-1, :, :]
|
||||
else:
|
||||
x[:, :, :, 0] -= 103.939
|
||||
x[:, :, :, 1] -= 116.779
|
||||
x[:, :, :, 2] -= 123.68
|
||||
# 'RGB'->'BGR'
|
||||
x = x[:, :, :, ::-1]
|
||||
return x
|
||||
|
||||
|
||||
def decode_predictions(preds):
|
||||
global CLASS_INDEX
|
||||
assert len(preds.shape) == 2 and preds.shape[1] == 1000
|
||||
if CLASS_INDEX is None:
|
||||
fpath = get_file('imagenet_class_index.json',
|
||||
CLASS_INDEX_PATH,
|
||||
cache_subdir='models')
|
||||
CLASS_INDEX = json.load(open(fpath))
|
||||
indices = np.argmax(preds, axis=-1)
|
||||
results = []
|
||||
for i in indices:
|
||||
results.append(CLASS_INDEX[str(i)])
|
||||
return results
|
312
keras/applications/inception_v3.py
Normal file
312
keras/applications/inception_v3.py
Normal file
@ -0,0 +1,312 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
'''Inception V3 model for Keras.
|
||||
|
||||
Note that the ImageNet weights provided are from a model that had not fully converged.
|
||||
Inception v3 should be able to reach 6.9% top-5 error, but our model
|
||||
only gets to 7.8% (same as a fully-converged ResNet 50).
|
||||
For comparison, VGG16 only gets to 9.9%, quite a bit worse.
|
||||
|
||||
Also, do note that the input image format for this model is different than for
|
||||
other models (299x299 instead of 224x224), and that the input preprocessing function
|
||||
is also different.
|
||||
|
||||
# Reference:
|
||||
|
||||
- [Rethinking the Inception Architecture for Computer Vision](http://arxiv.org/abs/1512.00567)
|
||||
|
||||
'''
|
||||
from __future__ import print_function
|
||||
from __future__ import absolute_import
|
||||
|
||||
import warnings
|
||||
|
||||
from ..models import Model
|
||||
from ..layers import Flatten, Dense, Input, BatchNormalization, merge
|
||||
from ..layers import Convolution2D, MaxPooling2D, AveragePooling2D
|
||||
from ..utils.layer_utils import convert_all_kernels_in_model
|
||||
from ..utils.data_utils import get_file
|
||||
from .. import backend as K
|
||||
from .imagenet_utils import decode_predictions
|
||||
|
||||
|
||||
TH_WEIGHTS_PATH = 'https://github.com/fchollet/deep-learning-models/releases/download/v0.2/inception_v3_weights_th_dim_ordering_th_kernels.h5'
|
||||
TF_WEIGHTS_PATH = 'https://github.com/fchollet/deep-learning-models/releases/download/v0.2/inception_v3_weights_tf_dim_ordering_tf_kernels.h5'
|
||||
TH_WEIGHTS_PATH_NO_TOP = 'https://github.com/fchollet/deep-learning-models/releases/download/v0.2/inception_v3_weights_th_dim_ordering_th_kernels_notop.h5'
|
||||
TF_WEIGHTS_PATH_NO_TOP = 'https://github.com/fchollet/deep-learning-models/releases/download/v0.2/inception_v3_weights_tf_dim_ordering_tf_kernels_notop.h5'
|
||||
|
||||
|
||||
def conv2d_bn(x, nb_filter, nb_row, nb_col,
|
||||
border_mode='same', subsample=(1, 1),
|
||||
name=None):
|
||||
'''Utility function to apply conv + BN.
|
||||
'''
|
||||
if name is not None:
|
||||
bn_name = name + '_bn'
|
||||
conv_name = name + '_conv'
|
||||
else:
|
||||
bn_name = None
|
||||
conv_name = None
|
||||
if K.image_dim_ordering() == 'th':
|
||||
bn_axis = 1
|
||||
else:
|
||||
bn_axis = 3
|
||||
x = Convolution2D(nb_filter, nb_row, nb_col,
|
||||
subsample=subsample,
|
||||
activation='relu',
|
||||
border_mode=border_mode,
|
||||
name=conv_name)(x)
|
||||
x = BatchNormalization(axis=bn_axis, name=bn_name)(x)
|
||||
return x
|
||||
|
||||
|
||||
def InceptionV3(include_top=True, weights='imagenet',
|
||||
input_tensor=None):
|
||||
'''Instantiate the Inception v3 architecture,
|
||||
optionally loading weights pre-trained
|
||||
on ImageNet. Note that when using TensorFlow,
|
||||
for best performance you should set
|
||||
`image_dim_ordering="tf"` in your Keras config
|
||||
at ~/.keras/keras.json.
|
||||
|
||||
The model and the weights are compatible with both
|
||||
TensorFlow and Theano. The dimension ordering
|
||||
convention used by the model is the one
|
||||
specified in your Keras config file.
|
||||
|
||||
Note that the default input image size for this model is 299x299.
|
||||
|
||||
# Arguments
|
||||
include_top: whether to include the 3 fully-connected
|
||||
layers at the top of the network.
|
||||
weights: one of `None` (random initialization)
|
||||
or "imagenet" (pre-training on ImageNet).
|
||||
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
|
||||
to use as image input for the model.
|
||||
|
||||
# Returns
|
||||
A Keras model instance.
|
||||
'''
|
||||
if weights not in {'imagenet', None}:
|
||||
raise ValueError('The `weights` argument should be either '
|
||||
'`None` (random initialization) or `imagenet` '
|
||||
'(pre-training on ImageNet).')
|
||||
# Determine proper input shape
|
||||
if K.image_dim_ordering() == 'th':
|
||||
if include_top:
|
||||
input_shape = (3, 299, 299)
|
||||
else:
|
||||
input_shape = (3, None, None)
|
||||
else:
|
||||
if include_top:
|
||||
input_shape = (299, 299, 3)
|
||||
else:
|
||||
input_shape = (None, None, 3)
|
||||
|
||||
if input_tensor is None:
|
||||
img_input = Input(shape=input_shape)
|
||||
else:
|
||||
if not K.is_keras_tensor(input_tensor):
|
||||
img_input = Input(tensor=input_tensor)
|
||||
else:
|
||||
img_input = input_tensor
|
||||
|
||||
if K.image_dim_ordering() == 'th':
|
||||
channel_axis = 1
|
||||
else:
|
||||
channel_axis = 3
|
||||
|
||||
x = conv2d_bn(img_input, 32, 3, 3, subsample=(2, 2), border_mode='valid')
|
||||
x = conv2d_bn(x, 32, 3, 3, border_mode='valid')
|
||||
x = conv2d_bn(x, 64, 3, 3)
|
||||
x = MaxPooling2D((3, 3), strides=(2, 2))(x)
|
||||
|
||||
x = conv2d_bn(x, 80, 1, 1, border_mode='valid')
|
||||
x = conv2d_bn(x, 192, 3, 3, border_mode='valid')
|
||||
x = MaxPooling2D((3, 3), strides=(2, 2))(x)
|
||||
|
||||
# mixed 0, 1, 2: 35 x 35 x 256
|
||||
for i in range(3):
|
||||
branch1x1 = conv2d_bn(x, 64, 1, 1)
|
||||
|
||||
branch5x5 = conv2d_bn(x, 48, 1, 1)
|
||||
branch5x5 = conv2d_bn(branch5x5, 64, 5, 5)
|
||||
|
||||
branch3x3dbl = conv2d_bn(x, 64, 1, 1)
|
||||
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
|
||||
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
|
||||
|
||||
branch_pool = AveragePooling2D(
|
||||
(3, 3), strides=(1, 1), border_mode='same')(x)
|
||||
branch_pool = conv2d_bn(branch_pool, 32, 1, 1)
|
||||
x = merge([branch1x1, branch5x5, branch3x3dbl, branch_pool],
|
||||
mode='concat', concat_axis=channel_axis,
|
||||
name='mixed' + str(i))
|
||||
|
||||
# mixed 3: 17 x 17 x 768
|
||||
branch3x3 = conv2d_bn(x, 384, 3, 3, subsample=(2, 2), border_mode='valid')
|
||||
|
||||
branch3x3dbl = conv2d_bn(x, 64, 1, 1)
|
||||
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
|
||||
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3,
|
||||
subsample=(2, 2), border_mode='valid')
|
||||
|
||||
branch_pool = MaxPooling2D((3, 3), strides=(2, 2))(x)
|
||||
x = merge([branch3x3, branch3x3dbl, branch_pool],
|
||||
mode='concat', concat_axis=channel_axis,
|
||||
name='mixed3')
|
||||
|
||||
# mixed 4: 17 x 17 x 768
|
||||
branch1x1 = conv2d_bn(x, 192, 1, 1)
|
||||
|
||||
branch7x7 = conv2d_bn(x, 128, 1, 1)
|
||||
branch7x7 = conv2d_bn(branch7x7, 128, 1, 7)
|
||||
branch7x7 = conv2d_bn(branch7x7, 192, 7, 1)
|
||||
|
||||
branch7x7dbl = conv2d_bn(x, 128, 1, 1)
|
||||
branch7x7dbl = conv2d_bn(branch7x7dbl, 128, 7, 1)
|
||||
branch7x7dbl = conv2d_bn(branch7x7dbl, 128, 1, 7)
|
||||
branch7x7dbl = conv2d_bn(branch7x7dbl, 128, 7, 1)
|
||||
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)
|
||||
|
||||
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), border_mode='same')(x)
|
||||
branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
|
||||
x = merge([branch1x1, branch7x7, branch7x7dbl, branch_pool],
|
||||
mode='concat', concat_axis=channel_axis,
|
||||
name='mixed4')
|
||||
|
||||
# mixed 5, 6: 17 x 17 x 768
|
||||
for i in range(2):
|
||||
branch1x1 = conv2d_bn(x, 192, 1, 1)
|
||||
|
||||
branch7x7 = conv2d_bn(x, 160, 1, 1)
|
||||
branch7x7 = conv2d_bn(branch7x7, 160, 1, 7)
|
||||
branch7x7 = conv2d_bn(branch7x7, 192, 7, 1)
|
||||
|
||||
branch7x7dbl = conv2d_bn(x, 160, 1, 1)
|
||||
branch7x7dbl = conv2d_bn(branch7x7dbl, 160, 7, 1)
|
||||
branch7x7dbl = conv2d_bn(branch7x7dbl, 160, 1, 7)
|
||||
branch7x7dbl = conv2d_bn(branch7x7dbl, 160, 7, 1)
|
||||
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)
|
||||
|
||||
branch_pool = AveragePooling2D(
|
||||
(3, 3), strides=(1, 1), border_mode='same')(x)
|
||||
branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
|
||||
x = merge([branch1x1, branch7x7, branch7x7dbl, branch_pool],
|
||||
mode='concat', concat_axis=channel_axis,
|
||||
name='mixed' + str(5 + i))
|
||||
|
||||
# mixed 7: 17 x 17 x 768
|
||||
branch1x1 = conv2d_bn(x, 192, 1, 1)
|
||||
|
||||
branch7x7 = conv2d_bn(x, 192, 1, 1)
|
||||
branch7x7 = conv2d_bn(branch7x7, 192, 1, 7)
|
||||
branch7x7 = conv2d_bn(branch7x7, 192, 7, 1)
|
||||
|
||||
branch7x7dbl = conv2d_bn(x, 160, 1, 1)
|
||||
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 7, 1)
|
||||
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)
|
||||
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 7, 1)
|
||||
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)
|
||||
|
||||
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), border_mode='same')(x)
|
||||
branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
|
||||
x = merge([branch1x1, branch7x7, branch7x7dbl, branch_pool],
|
||||
mode='concat', concat_axis=channel_axis,
|
||||
name='mixed7')
|
||||
|
||||
# mixed 8: 8 x 8 x 1280
|
||||
branch3x3 = conv2d_bn(x, 192, 1, 1)
|
||||
branch3x3 = conv2d_bn(branch3x3, 320, 3, 3,
|
||||
subsample=(2, 2), border_mode='valid')
|
||||
|
||||
branch7x7x3 = conv2d_bn(x, 192, 1, 1)
|
||||
branch7x7x3 = conv2d_bn(branch7x7x3, 192, 1, 7)
|
||||
branch7x7x3 = conv2d_bn(branch7x7x3, 192, 7, 1)
|
||||
branch7x7x3 = conv2d_bn(branch7x7x3, 192, 3, 3,
|
||||
subsample=(2, 2), border_mode='valid')
|
||||
|
||||
branch_pool = AveragePooling2D((3, 3), strides=(2, 2))(x)
|
||||
x = merge([branch3x3, branch7x7x3, branch_pool],
|
||||
mode='concat', concat_axis=channel_axis,
|
||||
name='mixed8')
|
||||
|
||||
# mixed 9: 8 x 8 x 2048
|
||||
for i in range(2):
|
||||
branch1x1 = conv2d_bn(x, 320, 1, 1)
|
||||
|
||||
branch3x3 = conv2d_bn(x, 384, 1, 1)
|
||||
branch3x3_1 = conv2d_bn(branch3x3, 384, 1, 3)
|
||||
branch3x3_2 = conv2d_bn(branch3x3, 384, 3, 1)
|
||||
branch3x3 = merge([branch3x3_1, branch3x3_2],
|
||||
mode='concat', concat_axis=channel_axis,
|
||||
name='mixed9_' + str(i))
|
||||
|
||||
branch3x3dbl = conv2d_bn(x, 448, 1, 1)
|
||||
branch3x3dbl = conv2d_bn(branch3x3dbl, 384, 3, 3)
|
||||
branch3x3dbl_1 = conv2d_bn(branch3x3dbl, 384, 1, 3)
|
||||
branch3x3dbl_2 = conv2d_bn(branch3x3dbl, 384, 3, 1)
|
||||
branch3x3dbl = merge([branch3x3dbl_1, branch3x3dbl_2],
|
||||
mode='concat', concat_axis=channel_axis)
|
||||
|
||||
branch_pool = AveragePooling2D(
|
||||
(3, 3), strides=(1, 1), border_mode='same')(x)
|
||||
branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
|
||||
x = merge([branch1x1, branch3x3, branch3x3dbl, branch_pool],
|
||||
mode='concat', concat_axis=channel_axis,
|
||||
name='mixed' + str(9 + i))
|
||||
|
||||
if include_top:
|
||||
# Classification block
|
||||
x = AveragePooling2D((8, 8), strides=(8, 8), name='avg_pool')(x)
|
||||
x = Flatten(name='flatten')(x)
|
||||
x = Dense(1000, activation='softmax', name='predictions')(x)
|
||||
|
||||
# Create model
|
||||
model = Model(img_input, x)
|
||||
|
||||
# load weights
|
||||
if weights == 'imagenet':
|
||||
if K.image_dim_ordering() == 'th':
|
||||
if include_top:
|
||||
weights_path = get_file('inception_v3_weights_th_dim_ordering_th_kernels.h5',
|
||||
TH_WEIGHTS_PATH,
|
||||
cache_subdir='models',
|
||||
md5_hash='b3baf3070cc4bf476d43a2ea61b0ca5f')
|
||||
else:
|
||||
weights_path = get_file('inception_v3_weights_th_dim_ordering_th_kernels_notop.h5',
|
||||
TH_WEIGHTS_PATH_NO_TOP,
|
||||
cache_subdir='models',
|
||||
md5_hash='79aaa90ab4372b4593ba3df64e142f05')
|
||||
model.load_weights(weights_path)
|
||||
if K.backend() == 'tensorflow':
|
||||
warnings.warn('You are using the TensorFlow backend, yet you '
|
||||
'are using the Theano '
|
||||
'image dimension ordering convention '
|
||||
'(`image_dim_ordering="th"`). '
|
||||
'For best performance, set '
|
||||
'`image_dim_ordering="tf"` in '
|
||||
'your Keras config '
|
||||
'at ~/.keras/keras.json.')
|
||||
convert_all_kernels_in_model(model)
|
||||
else:
|
||||
if include_top:
|
||||
weights_path = get_file('inception_v3_weights_tf_dim_ordering_tf_kernels.h5',
|
||||
TF_WEIGHTS_PATH,
|
||||
cache_subdir='models',
|
||||
md5_hash='fe114b3ff2ea4bf891e9353d1bbfb32f')
|
||||
else:
|
||||
weights_path = get_file('inception_v3_weights_tf_dim_ordering_tf_kernels_notop.h5',
|
||||
TF_WEIGHTS_PATH_NO_TOP,
|
||||
cache_subdir='models',
|
||||
md5_hash='2f3609166de1d967d1a481094754f691')
|
||||
model.load_weights(weights_path)
|
||||
if K.backend() == 'theano':
|
||||
convert_all_kernels_in_model(model)
|
||||
return model
|
||||
|
||||
|
||||
def preprocess_input(x):
|
||||
x /= 255.
|
||||
x -= 0.5
|
||||
x *= 2.
|
||||
return x
|
235
keras/applications/resnet50.py
Normal file
235
keras/applications/resnet50.py
Normal file
@ -0,0 +1,235 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
'''ResNet50 model for Keras.
|
||||
|
||||
# Reference:
|
||||
|
||||
- [Deep Residual Learning for Image Recognition](https://arxiv.org/abs/1512.03385)
|
||||
|
||||
Adapted from code contributed by BigMoyan.
|
||||
'''
|
||||
from __future__ import print_function
|
||||
from __future__ import absolute_import
|
||||
|
||||
import warnings
|
||||
|
||||
from ..layers import merge, Input
|
||||
from ..layers import Dense, Activation, Flatten
|
||||
from ..layers import Convolution2D, MaxPooling2D, ZeroPadding2D, AveragePooling2D
|
||||
from ..layers import BatchNormalization
|
||||
from ..models import Model
|
||||
from .. import backend as K
|
||||
from ..utils.layer_utils import convert_all_kernels_in_model
|
||||
from ..utils.data_utils import get_file
|
||||
from .imagenet_utils import decode_predictions, preprocess_input
|
||||
|
||||
|
||||
TH_WEIGHTS_PATH = 'https://github.com/fchollet/deep-learning-models/releases/download/v0.2/resnet50_weights_th_dim_ordering_th_kernels.h5'
|
||||
TF_WEIGHTS_PATH = 'https://github.com/fchollet/deep-learning-models/releases/download/v0.2/resnet50_weights_tf_dim_ordering_tf_kernels.h5'
|
||||
TH_WEIGHTS_PATH_NO_TOP = 'https://github.com/fchollet/deep-learning-models/releases/download/v0.2/resnet50_weights_th_dim_ordering_th_kernels_notop.h5'
|
||||
TF_WEIGHTS_PATH_NO_TOP = 'https://github.com/fchollet/deep-learning-models/releases/download/v0.2/resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5'
|
||||
|
||||
|
||||
def identity_block(input_tensor, kernel_size, filters, stage, block):
|
||||
'''The identity_block is the block that has no conv layer at shortcut
|
||||
|
||||
# Arguments
|
||||
input_tensor: input tensor
|
||||
kernel_size: defualt 3, the kernel size of middle conv layer at main path
|
||||
filters: list of integers, the nb_filters of 3 conv layer at main path
|
||||
stage: integer, current stage label, used for generating layer names
|
||||
block: 'a','b'..., current block label, used for generating layer names
|
||||
'''
|
||||
nb_filter1, nb_filter2, nb_filter3 = filters
|
||||
if K.image_dim_ordering() == 'tf':
|
||||
bn_axis = 3
|
||||
else:
|
||||
bn_axis = 1
|
||||
conv_name_base = 'res' + str(stage) + block + '_branch'
|
||||
bn_name_base = 'bn' + str(stage) + block + '_branch'
|
||||
|
||||
x = Convolution2D(nb_filter1, 1, 1, name=conv_name_base + '2a')(input_tensor)
|
||||
x = BatchNormalization(axis=bn_axis, name=bn_name_base + '2a')(x)
|
||||
x = Activation('relu')(x)
|
||||
|
||||
x = Convolution2D(nb_filter2, kernel_size, kernel_size,
|
||||
border_mode='same', name=conv_name_base + '2b')(x)
|
||||
x = BatchNormalization(axis=bn_axis, name=bn_name_base + '2b')(x)
|
||||
x = Activation('relu')(x)
|
||||
|
||||
x = Convolution2D(nb_filter3, 1, 1, name=conv_name_base + '2c')(x)
|
||||
x = BatchNormalization(axis=bn_axis, name=bn_name_base + '2c')(x)
|
||||
|
||||
x = merge([x, input_tensor], mode='sum')
|
||||
x = Activation('relu')(x)
|
||||
return x
|
||||
|
||||
|
||||
def conv_block(input_tensor, kernel_size, filters, stage, block, strides=(2, 2)):
|
||||
'''conv_block is the block that has a conv layer at shortcut
|
||||
|
||||
# Arguments
|
||||
input_tensor: input tensor
|
||||
kernel_size: defualt 3, the kernel size of middle conv layer at main path
|
||||
filters: list of integers, the nb_filters of 3 conv layer at main path
|
||||
stage: integer, current stage label, used for generating layer names
|
||||
block: 'a','b'..., current block label, used for generating layer names
|
||||
|
||||
Note that from stage 3, the first conv layer at main path is with subsample=(2,2)
|
||||
And the shortcut should have subsample=(2,2) as well
|
||||
'''
|
||||
nb_filter1, nb_filter2, nb_filter3 = filters
|
||||
if K.image_dim_ordering() == 'tf':
|
||||
bn_axis = 3
|
||||
else:
|
||||
bn_axis = 1
|
||||
conv_name_base = 'res' + str(stage) + block + '_branch'
|
||||
bn_name_base = 'bn' + str(stage) + block + '_branch'
|
||||
|
||||
x = Convolution2D(nb_filter1, 1, 1, subsample=strides,
|
||||
name=conv_name_base + '2a')(input_tensor)
|
||||
x = BatchNormalization(axis=bn_axis, name=bn_name_base + '2a')(x)
|
||||
x = Activation('relu')(x)
|
||||
|
||||
x = Convolution2D(nb_filter2, kernel_size, kernel_size, border_mode='same',
|
||||
name=conv_name_base + '2b')(x)
|
||||
x = BatchNormalization(axis=bn_axis, name=bn_name_base + '2b')(x)
|
||||
x = Activation('relu')(x)
|
||||
|
||||
x = Convolution2D(nb_filter3, 1, 1, name=conv_name_base + '2c')(x)
|
||||
x = BatchNormalization(axis=bn_axis, name=bn_name_base + '2c')(x)
|
||||
|
||||
shortcut = Convolution2D(nb_filter3, 1, 1, subsample=strides,
|
||||
name=conv_name_base + '1')(input_tensor)
|
||||
shortcut = BatchNormalization(axis=bn_axis, name=bn_name_base + '1')(shortcut)
|
||||
|
||||
x = merge([x, shortcut], mode='sum')
|
||||
x = Activation('relu')(x)
|
||||
return x
|
||||
|
||||
|
||||
def ResNet50(include_top=True, weights='imagenet',
|
||||
input_tensor=None):
|
||||
'''Instantiate the ResNet50 architecture,
|
||||
optionally loading weights pre-trained
|
||||
on ImageNet. Note that when using TensorFlow,
|
||||
for best performance you should set
|
||||
`image_dim_ordering="tf"` in your Keras config
|
||||
at ~/.keras/keras.json.
|
||||
|
||||
The model and the weights are compatible with both
|
||||
TensorFlow and Theano. The dimension ordering
|
||||
convention used by the model is the one
|
||||
specified in your Keras config file.
|
||||
|
||||
# Arguments
|
||||
include_top: whether to include the 3 fully-connected
|
||||
layers at the top of the network.
|
||||
weights: one of `None` (random initialization)
|
||||
or "imagenet" (pre-training on ImageNet).
|
||||
input_tensor: optional Keras tensor (i.e. xput of `layers.Input()`)
|
||||
to use as image input for the model.
|
||||
|
||||
# Returns
|
||||
A Keras model instance.
|
||||
'''
|
||||
if weights not in {'imagenet', None}:
|
||||
raise ValueError('The `weights` argument should be either '
|
||||
'`None` (random initialization) or `imagenet` '
|
||||
'(pre-training on ImageNet).')
|
||||
# Determine proper input shape
|
||||
if K.image_dim_ordering() == 'th':
|
||||
if include_top:
|
||||
input_shape = (3, 224, 224)
|
||||
else:
|
||||
input_shape = (3, None, None)
|
||||
else:
|
||||
if include_top:
|
||||
input_shape = (224, 224, 3)
|
||||
else:
|
||||
input_shape = (None, None, 3)
|
||||
|
||||
if input_tensor is None:
|
||||
img_input = Input(shape=input_shape)
|
||||
else:
|
||||
if not K.is_keras_tensor(input_tensor):
|
||||
img_input = Input(tensor=input_tensor)
|
||||
else:
|
||||
img_input = input_tensor
|
||||
if K.image_dim_ordering() == 'tf':
|
||||
bn_axis = 3
|
||||
else:
|
||||
bn_axis = 1
|
||||
|
||||
x = ZeroPadding2D((3, 3))(img_input)
|
||||
x = Convolution2D(64, 7, 7, subsample=(2, 2), name='conv1')(x)
|
||||
x = BatchNormalization(axis=bn_axis, name='bn_conv1')(x)
|
||||
x = Activation('relu')(x)
|
||||
x = MaxPooling2D((3, 3), strides=(2, 2))(x)
|
||||
|
||||
x = conv_block(x, 3, [64, 64, 256], stage=2, block='a', strides=(1, 1))
|
||||
x = identity_block(x, 3, [64, 64, 256], stage=2, block='b')
|
||||
x = identity_block(x, 3, [64, 64, 256], stage=2, block='c')
|
||||
|
||||
x = conv_block(x, 3, [128, 128, 512], stage=3, block='a')
|
||||
x = identity_block(x, 3, [128, 128, 512], stage=3, block='b')
|
||||
x = identity_block(x, 3, [128, 128, 512], stage=3, block='c')
|
||||
x = identity_block(x, 3, [128, 128, 512], stage=3, block='d')
|
||||
|
||||
x = conv_block(x, 3, [256, 256, 1024], stage=4, block='a')
|
||||
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='b')
|
||||
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='c')
|
||||
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='d')
|
||||
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='e')
|
||||
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='f')
|
||||
|
||||
x = conv_block(x, 3, [512, 512, 2048], stage=5, block='a')
|
||||
x = identity_block(x, 3, [512, 512, 2048], stage=5, block='b')
|
||||
x = identity_block(x, 3, [512, 512, 2048], stage=5, block='c')
|
||||
|
||||
x = AveragePooling2D((7, 7), name='avg_pool')(x)
|
||||
|
||||
if include_top:
|
||||
x = Flatten()(x)
|
||||
x = Dense(1000, activation='softmax', name='fc1000')(x)
|
||||
|
||||
model = Model(img_input, x)
|
||||
|
||||
# load weights
|
||||
if weights == 'imagenet':
|
||||
if K.image_dim_ordering() == 'th':
|
||||
if include_top:
|
||||
weights_path = get_file('resnet50_weights_th_dim_ordering_th_kernels.h5',
|
||||
TH_WEIGHTS_PATH,
|
||||
cache_subdir='models',
|
||||
md5_hash='1c1f8f5b0c8ee28fe9d950625a230e1c')
|
||||
else:
|
||||
weights_path = get_file('resnet50_weights_th_dim_ordering_th_kernels_notop.h5',
|
||||
TH_WEIGHTS_PATH_NO_TOP,
|
||||
cache_subdir='models',
|
||||
md5_hash='f64f049c92468c9affcd44b0976cdafe')
|
||||
model.load_weights(weights_path)
|
||||
if K.backend() == 'tensorflow':
|
||||
warnings.warn('You are using the TensorFlow backend, yet you '
|
||||
'are using the Theano '
|
||||
'image dimension ordering convention '
|
||||
'(`image_dim_ordering="th"`). '
|
||||
'For best performance, set '
|
||||
'`image_dim_ordering="tf"` in '
|
||||
'your Keras config '
|
||||
'at ~/.keras/keras.json.')
|
||||
convert_all_kernels_in_model(model)
|
||||
else:
|
||||
if include_top:
|
||||
weights_path = get_file('resnet50_weights_tf_dim_ordering_tf_kernels.h5',
|
||||
TF_WEIGHTS_PATH,
|
||||
cache_subdir='models',
|
||||
md5_hash='a7b3fe01876f51b976af0dea6bc144eb')
|
||||
else:
|
||||
weights_path = get_file('resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5',
|
||||
TF_WEIGHTS_PATH_NO_TOP,
|
||||
cache_subdir='models',
|
||||
md5_hash='a268eb855778b3df3c7506639542a6af')
|
||||
model.load_weights(weights_path)
|
||||
if K.backend() == 'theano':
|
||||
convert_all_kernels_in_model(model)
|
||||
return model
|
149
keras/applications/vgg16.py
Normal file
149
keras/applications/vgg16.py
Normal file
@ -0,0 +1,149 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
'''VGG16 model for Keras.
|
||||
|
||||
# Reference:
|
||||
|
||||
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://arxiv.org/abs/1409.1556)
|
||||
|
||||
'''
|
||||
from __future__ import print_function
|
||||
from __future__ import absolute_import
|
||||
|
||||
import warnings
|
||||
|
||||
from ..models import Model
|
||||
from ..layers import Flatten, Dense, Input
|
||||
from ..layers import Convolution2D, MaxPooling2D
|
||||
from ..utils.layer_utils import convert_all_kernels_in_model
|
||||
from ..utils.data_utils import get_file
|
||||
from .. import backend as K
|
||||
from .imagenet_utils import decode_predictions, preprocess_input
|
||||
|
||||
|
||||
TH_WEIGHTS_PATH = 'https://github.com/fchollet/deep-learning-models/releases/download/v0.1/vgg16_weights_th_dim_ordering_th_kernels.h5'
|
||||
TF_WEIGHTS_PATH = 'https://github.com/fchollet/deep-learning-models/releases/download/v0.1/vgg16_weights_tf_dim_ordering_tf_kernels.h5'
|
||||
TH_WEIGHTS_PATH_NO_TOP = 'https://github.com/fchollet/deep-learning-models/releases/download/v0.1/vgg16_weights_th_dim_ordering_th_kernels_notop.h5'
|
||||
TF_WEIGHTS_PATH_NO_TOP = 'https://github.com/fchollet/deep-learning-models/releases/download/v0.1/vgg16_weights_tf_dim_ordering_tf_kernels_notop.h5'
|
||||
|
||||
|
||||
def VGG16(include_top=True, weights='imagenet',
|
||||
input_tensor=None):
|
||||
'''Instantiate the VGG16 architecture,
|
||||
optionally loading weights pre-trained
|
||||
on ImageNet. Note that when using TensorFlow,
|
||||
for best performance you should set
|
||||
`image_dim_ordering="tf"` in your Keras config
|
||||
at ~/.keras/keras.json.
|
||||
|
||||
The model and the weights are compatible with both
|
||||
TensorFlow and Theano. The dimension ordering
|
||||
convention used by the model is the one
|
||||
specified in your Keras config file.
|
||||
|
||||
# Arguments
|
||||
include_top: whether to include the 3 fully-connected
|
||||
layers at the top of the network.
|
||||
weights: one of `None` (random initialization)
|
||||
or "imagenet" (pre-training on ImageNet).
|
||||
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
|
||||
to use as image input for the model.
|
||||
|
||||
# Returns
|
||||
A Keras model instance.
|
||||
'''
|
||||
if weights not in {'imagenet', None}:
|
||||
raise ValueError('The `weights` argument should be either '
|
||||
'`None` (random initialization) or `imagenet` '
|
||||
'(pre-training on ImageNet).')
|
||||
# Determine proper input shape
|
||||
if K.image_dim_ordering() == 'th':
|
||||
if include_top:
|
||||
input_shape = (3, 224, 224)
|
||||
else:
|
||||
input_shape = (3, None, None)
|
||||
else:
|
||||
if include_top:
|
||||
input_shape = (224, 224, 3)
|
||||
else:
|
||||
input_shape = (None, None, 3)
|
||||
|
||||
if input_tensor is None:
|
||||
img_input = Input(shape=input_shape)
|
||||
else:
|
||||
if not K.is_keras_tensor(input_tensor):
|
||||
img_input = Input(tensor=input_tensor)
|
||||
else:
|
||||
img_input = input_tensor
|
||||
# Block 1
|
||||
x = Convolution2D(64, 3, 3, activation='relu', border_mode='same', name='block1_conv1')(img_input)
|
||||
x = Convolution2D(64, 3, 3, activation='relu', border_mode='same', name='block1_conv2')(x)
|
||||
x = MaxPooling2D((2, 2), strides=(2, 2), name='block1_pool')(x)
|
||||
|
||||
# Block 2
|
||||
x = Convolution2D(128, 3, 3, activation='relu', border_mode='same', name='block2_conv1')(x)
|
||||
x = Convolution2D(128, 3, 3, activation='relu', border_mode='same', name='block2_conv2')(x)
|
||||
x = MaxPooling2D((2, 2), strides=(2, 2), name='block2_pool')(x)
|
||||
|
||||
# Block 3
|
||||
x = Convolution2D(256, 3, 3, activation='relu', border_mode='same', name='block3_conv1')(x)
|
||||
x = Convolution2D(256, 3, 3, activation='relu', border_mode='same', name='block3_conv2')(x)
|
||||
x = Convolution2D(256, 3, 3, activation='relu', border_mode='same', name='block3_conv3')(x)
|
||||
x = MaxPooling2D((2, 2), strides=(2, 2), name='block3_pool')(x)
|
||||
|
||||
# Block 4
|
||||
x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block4_conv1')(x)
|
||||
x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block4_conv2')(x)
|
||||
x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block4_conv3')(x)
|
||||
x = MaxPooling2D((2, 2), strides=(2, 2), name='block4_pool')(x)
|
||||
|
||||
# Block 5
|
||||
x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block5_conv1')(x)
|
||||
x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block5_conv2')(x)
|
||||
x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block5_conv3')(x)
|
||||
x = MaxPooling2D((2, 2), strides=(2, 2), name='block5_pool')(x)
|
||||
|
||||
if include_top:
|
||||
# Classification block
|
||||
x = Flatten(name='flatten')(x)
|
||||
x = Dense(4096, activation='relu', name='fc1')(x)
|
||||
x = Dense(4096, activation='relu', name='fc2')(x)
|
||||
x = Dense(1000, activation='softmax', name='predictions')(x)
|
||||
|
||||
# Create model
|
||||
model = Model(img_input, x)
|
||||
|
||||
# load weights
|
||||
if weights == 'imagenet':
|
||||
if K.image_dim_ordering() == 'th':
|
||||
if include_top:
|
||||
weights_path = get_file('vgg16_weights_th_dim_ordering_th_kernels.h5',
|
||||
TH_WEIGHTS_PATH,
|
||||
cache_subdir='models')
|
||||
else:
|
||||
weights_path = get_file('vgg16_weights_th_dim_ordering_th_kernels_notop.h5',
|
||||
TH_WEIGHTS_PATH_NO_TOP,
|
||||
cache_subdir='models')
|
||||
model.load_weights(weights_path)
|
||||
if K.backend() == 'tensorflow':
|
||||
warnings.warn('You are using the TensorFlow backend, yet you '
|
||||
'are using the Theano '
|
||||
'image dimension ordering convention '
|
||||
'(`image_dim_ordering="th"`). '
|
||||
'For best performance, set '
|
||||
'`image_dim_ordering="tf"` in '
|
||||
'your Keras config '
|
||||
'at ~/.keras/keras.json.')
|
||||
convert_all_kernels_in_model(model)
|
||||
else:
|
||||
if include_top:
|
||||
weights_path = get_file('vgg16_weights_tf_dim_ordering_tf_kernels.h5',
|
||||
TF_WEIGHTS_PATH,
|
||||
cache_subdir='models')
|
||||
else:
|
||||
weights_path = get_file('vgg16_weights_tf_dim_ordering_tf_kernels_notop.h5',
|
||||
TF_WEIGHTS_PATH_NO_TOP,
|
||||
cache_subdir='models')
|
||||
model.load_weights(weights_path)
|
||||
if K.backend() == 'theano':
|
||||
convert_all_kernels_in_model(model)
|
||||
return model
|
152
keras/applications/vgg19.py
Normal file
152
keras/applications/vgg19.py
Normal file
@ -0,0 +1,152 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
'''VGG19 model for Keras.
|
||||
|
||||
# Reference:
|
||||
|
||||
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://arxiv.org/abs/1409.1556)
|
||||
|
||||
'''
|
||||
from __future__ import print_function
|
||||
from __future__ import absolute_import
|
||||
|
||||
import warnings
|
||||
|
||||
from ..models import Model
|
||||
from ..layers import Flatten, Dense, Input
|
||||
from ..layers import Convolution2D, MaxPooling2D
|
||||
from ..utils.layer_utils import convert_all_kernels_in_model
|
||||
from ..utils.data_utils import get_file
|
||||
from .. import backend as K
|
||||
from .imagenet_utils import decode_predictions, preprocess_input
|
||||
|
||||
|
||||
TH_WEIGHTS_PATH = 'https://github.com/fchollet/deep-learning-models/releases/download/v0.1/vgg19_weights_th_dim_ordering_th_kernels.h5'
|
||||
TF_WEIGHTS_PATH = 'https://github.com/fchollet/deep-learning-models/releases/download/v0.1/vgg19_weights_tf_dim_ordering_tf_kernels.h5'
|
||||
TH_WEIGHTS_PATH_NO_TOP = 'https://github.com/fchollet/deep-learning-models/releases/download/v0.1/vgg19_weights_th_dim_ordering_th_kernels_notop.h5'
|
||||
TF_WEIGHTS_PATH_NO_TOP = 'https://github.com/fchollet/deep-learning-models/releases/download/v0.1/vgg19_weights_tf_dim_ordering_tf_kernels_notop.h5'
|
||||
|
||||
|
||||
def VGG19(include_top=True, weights='imagenet',
|
||||
input_tensor=None):
|
||||
'''Instantiate the VGG19 architecture,
|
||||
optionally loading weights pre-trained
|
||||
on ImageNet. Note that when using TensorFlow,
|
||||
for best performance you should set
|
||||
`image_dim_ordering="tf"` in your Keras config
|
||||
at ~/.keras/keras.json.
|
||||
|
||||
The model and the weights are compatible with both
|
||||
TensorFlow and Theano. The dimension ordering
|
||||
convention used by the model is the one
|
||||
specified in your Keras config file.
|
||||
|
||||
# Arguments
|
||||
include_top: whether to include the 3 fully-connected
|
||||
layers at the top of the network.
|
||||
weights: one of `None` (random initialization)
|
||||
or "imagenet" (pre-training on ImageNet).
|
||||
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
|
||||
to use as image input for the model.
|
||||
|
||||
# Returns
|
||||
A Keras model instance.
|
||||
'''
|
||||
if weights not in {'imagenet', None}:
|
||||
raise ValueError('The `weights` argument should be either '
|
||||
'`None` (random initialization) or `imagenet` '
|
||||
'(pre-training on ImageNet).')
|
||||
# Determine proper input shape
|
||||
if K.image_dim_ordering() == 'th':
|
||||
if include_top:
|
||||
input_shape = (3, 224, 224)
|
||||
else:
|
||||
input_shape = (3, None, None)
|
||||
else:
|
||||
if include_top:
|
||||
input_shape = (224, 224, 3)
|
||||
else:
|
||||
input_shape = (None, None, 3)
|
||||
|
||||
if input_tensor is None:
|
||||
img_input = Input(shape=input_shape)
|
||||
else:
|
||||
if not K.is_keras_tensor(input_tensor):
|
||||
img_input = Input(tensor=input_tensor)
|
||||
else:
|
||||
img_input = input_tensor
|
||||
# Block 1
|
||||
x = Convolution2D(64, 3, 3, activation='relu', border_mode='same', name='block1_conv1')(img_input)
|
||||
x = Convolution2D(64, 3, 3, activation='relu', border_mode='same', name='block1_conv2')(x)
|
||||
x = MaxPooling2D((2, 2), strides=(2, 2), name='block1_pool')(x)
|
||||
|
||||
# Block 2
|
||||
x = Convolution2D(128, 3, 3, activation='relu', border_mode='same', name='block2_conv1')(x)
|
||||
x = Convolution2D(128, 3, 3, activation='relu', border_mode='same', name='block2_conv2')(x)
|
||||
x = MaxPooling2D((2, 2), strides=(2, 2), name='block2_pool')(x)
|
||||
|
||||
# Block 3
|
||||
x = Convolution2D(256, 3, 3, activation='relu', border_mode='same', name='block3_conv1')(x)
|
||||
x = Convolution2D(256, 3, 3, activation='relu', border_mode='same', name='block3_conv2')(x)
|
||||
x = Convolution2D(256, 3, 3, activation='relu', border_mode='same', name='block3_conv3')(x)
|
||||
x = Convolution2D(256, 3, 3, activation='relu', border_mode='same', name='block3_conv4')(x)
|
||||
x = MaxPooling2D((2, 2), strides=(2, 2), name='block3_pool')(x)
|
||||
|
||||
# Block 4
|
||||
x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block4_conv1')(x)
|
||||
x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block4_conv2')(x)
|
||||
x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block4_conv3')(x)
|
||||
x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block4_conv4')(x)
|
||||
x = MaxPooling2D((2, 2), strides=(2, 2), name='block4_pool')(x)
|
||||
|
||||
# Block 5
|
||||
x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block5_conv1')(x)
|
||||
x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block5_conv2')(x)
|
||||
x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block5_conv3')(x)
|
||||
x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block5_conv4')(x)
|
||||
x = MaxPooling2D((2, 2), strides=(2, 2), name='block5_pool')(x)
|
||||
|
||||
if include_top:
|
||||
# Classification block
|
||||
x = Flatten(name='flatten')(x)
|
||||
x = Dense(4096, activation='relu', name='fc1')(x)
|
||||
x = Dense(4096, activation='relu', name='fc2')(x)
|
||||
x = Dense(1000, activation='softmax', name='predictions')(x)
|
||||
|
||||
# Create model
|
||||
model = Model(img_input, x)
|
||||
|
||||
# load weights
|
||||
if weights == 'imagenet':
|
||||
if K.image_dim_ordering() == 'th':
|
||||
if include_top:
|
||||
weights_path = get_file('vgg19_weights_th_dim_ordering_th_kernels.h5',
|
||||
TH_WEIGHTS_PATH,
|
||||
cache_subdir='models')
|
||||
else:
|
||||
weights_path = get_file('vgg19_weights_th_dim_ordering_th_kernels_notop.h5',
|
||||
TH_WEIGHTS_PATH_NO_TOP,
|
||||
cache_subdir='models')
|
||||
model.load_weights(weights_path)
|
||||
if K.backend() == 'tensorflow':
|
||||
warnings.warn('You are using the TensorFlow backend, yet you '
|
||||
'are using the Theano '
|
||||
'image dimension ordering convention '
|
||||
'(`image_dim_ordering="th"`). '
|
||||
'For best performance, set '
|
||||
'`image_dim_ordering="tf"` in '
|
||||
'your Keras config '
|
||||
'at ~/.keras/keras.json.')
|
||||
convert_all_kernels_in_model(model)
|
||||
else:
|
||||
if include_top:
|
||||
weights_path = get_file('vgg19_weights_tf_dim_ordering_tf_kernels.h5',
|
||||
TF_WEIGHTS_PATH,
|
||||
cache_subdir='models')
|
||||
else:
|
||||
weights_path = get_file('vgg19_weights_tf_dim_ordering_tf_kernels_notop.h5',
|
||||
TF_WEIGHTS_PATH_NO_TOP,
|
||||
cache_subdir='models')
|
||||
model.load_weights(weights_path)
|
||||
if K.backend() == 'theano':
|
||||
convert_all_kernels_in_model(model)
|
||||
return model
|
Loading…
Reference in New Issue
Block a user