-
-
Save kgrm/67555890a3e07cab709a7a81cc487c31 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from __future__ import print_function | |
from scipy.misc import imsave | |
import numpy as np | |
import time | |
import sys, os | |
from keras.models import Sequential | |
from keras.layers import Convolution2D, ZeroPadding2D, Dropout, Flatten | |
from keras.layers import BatchNormalization, MaxPooling2D, Dense | |
from keras import backend as K | |
def alexnet_for_conv_vis(N_classes, weights_path=None, inshape=(3, 224, 224)): | |
m = Sequential() | |
m.add(Convolution2D(96, 11, 11, subsample=(4,4), activation="relu", | |
batch_input_shape=(1,3,224,224))) | |
first_layer = m.layers[-1] | |
input_img = first_layer.input | |
m.add(MaxPooling2D()) | |
m.add(BatchNormalization(mode=0, axis=1)) | |
m.add(ZeroPadding2D((2,2))) | |
m.add(Convolution2D(256, 5, 5, activation="relu")) | |
m.add(MaxPooling2D()) | |
m.add(BatchNormalization(mode=0, axis=1)) | |
m.add(ZeroPadding2D((1,1))) | |
m.add(Convolution2D(384, 3, 3, activation="relu")) | |
m.add(ZeroPadding2D((1,1))) | |
m.add(Convolution2D(384, 3, 3, activation="relu")) | |
m.add(ZeroPadding2D((1,1))) | |
m.add(Convolution2D(256, 3, 3, activation="relu")) | |
m.add(MaxPooling2D()) | |
m.add(Flatten()) | |
m.add(Dense(4096, activation="relu")) | |
m.add(Dropout(0.5)) | |
m.add(Dense(4096, activation="relu")) | |
m.add(Dropout(0.5)) | |
m.add(Dense(N_classes, activation="softmax")) | |
if weights_path: | |
m.load_weights(weights_path) | |
return (m, input_img) | |
# dimensions of the generated pictures for each filter. | |
img_width = 224 | |
img_height = 224 | |
# path to the model weights file. | |
weights_path = '/opt/data/CASIA WebFace/tensors/alexnet_weights.h5' | |
# the name of the layer we want to visualize (see model definition below) | |
layer_name = 'convolution2d_2' | |
if len(sys.argv) >= 2: | |
layer_name = sys.argv[1] | |
filterNumDict = {"convolution2d_1": 96, | |
"convolution2d_2": 256, | |
"convolution2d_3": 384, | |
"convolution2d_4": 384, | |
"convolution2d_5": 256} | |
# util function to convert a tensor into a valid image | |
def deprocess_image(x): | |
# normalize tensor: center on 0., ensure std is 0.1 | |
x -= x.mean() | |
x /= (x.std() + 1e-5) | |
x *= 0.1 | |
# clip to [0, 1] | |
x+= 0.5 | |
x = np.clip(x, 0, 1) | |
# convert to RGB array | |
x *= 255 | |
x = x.transpose((1, 2, 0)) | |
x = np.clip(x, 0, 255).astype('uint8') | |
return x | |
model, input_img = alexnet_for_conv_vis(10575) | |
try: | |
model.load_weights(weights_path) | |
print("Weights loaded.") | |
except: | |
print("Weights not found.") | |
print('Model loaded.') | |
for layer in model.layers: print(layer.name) | |
# get the symbolic outputs of each "key" layer (we gave them unique names). | |
layer_dict = dict([(layer.name, layer) for layer in model.layers]) | |
def normalize(x): | |
# utility function to normalize a tensor by its L2 norm | |
return x / (K.sqrt(K.mean(K.square(x))) + 1e-5) | |
kept_filters = [] | |
for filter_index in range(0, filterNumDict[layer_name]): | |
# we only scan through the first 200 filters, | |
# but there are actually 512 of them | |
print('Processing filter %d' % filter_index) | |
start_time = time.time() | |
# 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, :, :]) | |
# we compute the gradient of the input picture wrt this loss | |
grads = K.gradients(loss, input_img)[0] | |
# normalization trick: we normalize the gradient | |
grads = normalize(grads) | |
# this function returns the loss and grads given the input picture | |
iterate = K.function([input_img], [loss, grads]) | |
# step size for gradient ascent | |
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. | |
# we run gradient ascent for 20 steps | |
for i in range(20): | |
loss_value, grads_value = iterate([input_img_data]) | |
input_img_data += grads_value * step | |
print('Current loss value:', loss_value) | |
if loss_value <= 0.: | |
# some filters get stuck to 0, we can skip them | |
break | |
# decode the resulting input image | |
if loss_value > 0: | |
img = deprocess_image(input_img_data[0]) | |
kept_filters.append((img, loss_value)) | |
end_time = time.time() | |
print('Filter %d processed in %ds' % (filter_index, end_time - start_time)) | |
# we will stich the best 64 filters on a 8 x 8 grid. | |
n = 8 | |
# the filters that have the highest loss are assumed to be better-looking. | |
# we will only keep the top 64 filters. | |
kept_filters.sort(key=lambda x: x[1], reverse=True) | |
kept_filters = kept_filters[:n * n] | |
# build a black picture with enough space for | |
# our 8 x 8 filters of size 128 x 128, with a 5px margin in between | |
margin = 5 | |
width = n * img_width + (n - 1) * margin | |
height = n * img_height + (n - 1) * margin | |
stitched_filters = np.zeros((width, height, 3)) | |
# fill the picture with our saved filters | |
for i in range(n): | |
for j in range(n): | |
img, loss, ind = kept_filters[i * n + j] | |
stitched_filters[(img_width + margin) * i: (img_width + margin) * i + img_width, | |
(img_height + margin) * j: (img_height + margin) * j + img_height, :] = img | |
# save the result to disk | |
name = "stitched_filters_%dx%d_%s.png" % (n, n, layer_name) | |
if len(sys.argv) > 2: | |
name = sys.argv[2] | |
imsave(name, stitched_filters) | |
with open(name[:-4] + ".txt", "w") as f: | |
for item in kept_filters: | |
s = "Filter %3d: loss value %5.3f\n" % (item[2], item[1]) | |
f.write(s) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment