0
다른 레이어에서 학습 한 기능 및 활성화를 시각화하기 위해 keras 블로그 게시물 코드를 사용하고 있습니다. 이 코드는 무작위로 차원의 회색 이미지 (1,3, img_width, img_height)를 생성하고 시각화했습니다. 여기있다 :Keras를 사용한 CNN의 기능 및 활성화 시각화보기
from __future__ import print_function
from scipy.misc import imsave
import numpy as np
import time
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
# 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):
# 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
if K.image_data_format() == 'channels_first':
x = x.transpose((1, 2, 0))
x = np.clip(x, 0, 255).astype('uint8')
return x
# 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[1:]])
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, 200):
# 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
if K.image_data_format() == 'channels_first':
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]
# 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
if K.image_data_format() == 'channels_first':
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):
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 = 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
imsave('stitched_filters_%dx%d.png' % (n, n), stitched_filters)
당신은 제가 코드에서 이러한 진술을 수정하는 방법을 알려 주시기 바랍니다 수 :
input_img_data = np.random.random((1, img_width, img_height, 3))
input_img_data = (input_img_data - 0.5) * 20 + 128
내 자신의 데이터를 삽입하고 기능을 시각화 배운 활성화하기 위해? 내 이미지는 150, 150 크기의 RGB 이미지입니다. 도움을 주셔서 감사합니다.
안녕하세요 , 고마워. 이미지를로드 한 후 이미지 모양을 변경하는 데 문제가 있습니다. K.image_data_format() == 'channels_first': input_img_data = np.random.random ((1, 3, img_width, img_height)) if 이미지를 모델에 맞게 수정해야하는지 알려주세요. 기타 : input_img_data = np.random.random ((1, img_width, img_height, 3)) input_img_data = (input_img_data - 0.5) * 20 + 128 – shiva
@shiva, 업데이트를 참조하십시오. 그 코드를이 코드로 대체하십시오. 가져 오기 선을 추가하십시오. 나를 위해 일하고. – hars
@shiva, 당신을 위해 일하고 있습니까? 그렇다면 질문을 닫을 수 있도록 대답을 수락하거나 투표 할 수 있습니까? 감사합니다 – hars