keras-vis可视化特征

提前下载： vgg16_weights_tf_dim_ordering_tf_kernels.h5

放在C:\Users\sbd01\.keras\models，改为自己电脑用户目录

Downloading data from https://github.com/fchollet/deep-learning-models/releases/download/v0.1/vgg16_weights_tf_dim_ordering_tf_kernels.h5

from keras.applications import VGG16
from vis.utils import utils
from keras import activations

# Build the VGG16 network with ImageNet weights
model = VGG16(weights='imagenet', include_top=True)

# Utility to search for layer index by name.
# Alternatively we can specify this as -1 since it corresponds to the last layer.
layer_idx = utils.find_layer_idx(model, 'predictions')

# Swap softmax with linear
model.layers[layer_idx].activation = activations.linear
model = utils.apply_modifications(model)

from vis.utils import utils
from matplotlib import pyplot as plt
# %matplotlib inline
plt.rcParams['figure.figsize'] = (18, 6)

img1 = utils.load_img('images/ouzel1.jpg', target_size=(224, 224))
img2 = utils.load_img('images/ouzel2.jpg', target_size=(224, 224))

f, ax = plt.subplots(1, 2)
ax[0].imshow(img1)
ax[1].imshow(img2)

from vis.visualization import visualize_saliency, overlay
from vis.utils import utils
from keras import activations

# Utility to search for layer index by name.
# Alternatively we can specify this as -1 since it corresponds to the last layer.
layer_idx = utils.find_layer_idx(model, 'predictions')

f, ax = plt.subplots(1, 2)
for i, img in enumerate([img1, img2]):
    # 20 is the imagenet index corresponding to `ouzel`
    grads = visualize_saliency(model, layer_idx, filter_indices=20, seed_input=img)

    # visualize grads as heatmap
    ax[i].imshow(grads, cmap='jet')

for modifier in ['guided', 'relu']:
    plt.figure()
    f, ax = plt.subplots(1, 2)
    plt.suptitle(modifier)
    for i, img in enumerate([img1, img2]):
        # 20 is the imagenet index corresponding to `ouzel`
        grads = visualize_saliency(model, layer_idx, filter_indices=20,
                                   seed_input=img, backprop_modifier=modifier)
        # Lets overlay the heatmap onto original image.
        ax[i].imshow(grads, cmap='jet')

model.summary()

import numpy as np
import matplotlib.cm as cm
from vis.visualization import visualize_cam

for modifier in [None, 'guided', 'relu']:
    plt.figure()
    f, ax = plt.subplots(1, 2)
    plt.suptitle("vanilla" if modifier is None else modifier)
    for i, img in enumerate([img1, img2]):
        # 20 is the imagenet index corresponding to `ouzel`
        grads = visualize_cam(model, layer_idx, filter_indices=20,
                              seed_input=img, backprop_modifier=modifier)
        # Lets overlay the heatmap onto original image.
        jet_heatmap = np.uint8(cm.jet(grads)[..., :3] * 255)
        ax[i].imshow(overlay(jet_heatmap, img))