-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathgradcam.py
178 lines (133 loc) · 6.16 KB
/
gradcam.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
'''
Descripttion:
version:
Author: QIU Yaowen
Date: 2022-01-05 22:53:32
LastEditors: Andy
LastEditTime: 2022-02-27 16:04:59
'''
import numpy as np
import tensorflow as tf
import matplotlib.cm as cm
import config
'''
Descripttion: Modified Grad-CAM. Extract True object from background
version:
Author: QIU Yaowen
Date: 2022-01-05 22:53:32
LastEditors: Andy
LastEditTime: 2022-02-27 16:03:43
'''
import numpy as np
import tensorflow as tf
import matplotlib.cm as cm
import config
def get_img_array(img_path, size):
# `img` is a PIL image of size 299x299
img = tf.keras.preprocessing.image.load_img(img_path, target_size=size)
# `array` is a float32 Numpy array of shape (299, 299, 3)
array = tf.keras.preprocessing.image.img_to_array(img)
# We add a dimension to transform our array into a "batch"
# of size (1, 299, 299, 3)
array = np.expand_dims(array, axis=0)
return array
def make_gradcam_heatmap(img_array, grad_model, pred_index):
# First, we create a model that maps the input image to the activations
# of the last conv layer as well as the output predictions
# Then, we compute the gradient of the top predicted class for our input image
# with respect to the activations of the last conv layer
with tf.GradientTape() as tape:
last_conv_layer_output, preds = grad_model(img_array)
# if pred_index is None:
# pred_index = tf.argmax(preds[0])
class_channel = preds[:, pred_index]
# This is the gradient of the output neuron (top predicted or chosen)
# with regard to the output feature map of the last conv layer
grads = tape.gradient(class_channel, last_conv_layer_output)
# This is a vector where each entry is the mean intensity of the gradient
# over a specific feature map channel
pooled_grads = tf.reduce_mean(grads, axis=(0, 1, 2))
# We multiply each channel in the feature map array
# by "how important this channel is" with regard to the top predicted class
# then sum all the channels to obtain the heatmap class activation
last_conv_layer_output = last_conv_layer_output[0]
heatmap = last_conv_layer_output @ pooled_grads[..., tf.newaxis]
heatmap = tf.squeeze(heatmap)
# For visualization purpose, we will also normalize the heatmap between 0 & 1
heatmap = tf.maximum(heatmap, 0) / tf.math.reduce_max(heatmap)
return heatmap.numpy()
def save_and_display_gradcam(img_path, heatmap, cam_path, threshold = 10):
# plt.figure(figsize=[12,8],dpi=200)
# Load the original image
img = tf.keras.preprocessing.image.load_img(img_path)
img = tf.keras.preprocessing.image.img_to_array(img)
# Rescale heatmap to a range 0-255
heatmap = np.uint8(255 * heatmap)
# Use jet colormap to colorize heatmap
jet = cm.get_cmap("jet")
# Use RGB values of the colormap
jet_colors = jet(np.arange(256))[:, :3]
jet_heatmap = jet_colors[heatmap]
# Create an image with RGB colorized heatmap
jet_heatmap = tf.keras.preprocessing.image.array_to_img(jet_heatmap)
jet_heatmap = jet_heatmap.resize((img.shape[1], img.shape[0]))
jet_heatmap = tf.keras.preprocessing.image.img_to_array(jet_heatmap)
img[jet_heatmap[:,:,0] < threshold] = 0
jet_heatmap[jet_heatmap[:,:,0] < threshold] = 0
# Superimpose the heatmap on original image
superimposed_img_array = jet_heatmap + img
superimposed_img = tf.keras.preprocessing.image.array_to_img(superimposed_img_array)
# Save the superimposed image
superimposed_img.save(cam_path)
# Display Grad CAM
# display(Image(cam_path))
# return superimposed_img_array
def make_gradcam_heatmap(img_array, grad_model, pred_index=None):
# First, we create a model that maps the input image to the activations
# of the last conv layer as well as the output predictions
# Then, we compute the gradient of the top predicted class for our input image
# with respect to the activations of the last conv layer
with tf.GradientTape() as tape:
last_conv_layer_output, preds = grad_model(img_array)
if pred_index is None:
pred_index = tf.argmax(preds[0])
class_channel = preds[:, pred_index]
# This is the gradient of the output neuron (top predicted or chosen)
# with regard to the output feature map of the last conv layer
grads = tape.gradient(class_channel, last_conv_layer_output)
# This is a vector where each entry is the mean intensity of the gradient
# over a specific feature map channel
pooled_grads = tf.reduce_mean(grads, axis=(0, 1, 2))
# We multiply each channel in the feature map array
# by "how important this channel is" with regard to the top predicted class
# then sum all the channels to obtain the heatmap class activation
last_conv_layer_output = last_conv_layer_output[0]
heatmap = last_conv_layer_output @ pooled_grads[..., tf.newaxis]
heatmap = tf.squeeze(heatmap)
# For visualization purpose, we will also normalize the heatmap between 0 & 1
heatmap = tf.maximum(heatmap, 0) / tf.math.reduce_max(heatmap)
return heatmap.numpy()
def save_and_display_gradcam(img_path, heatmap, cam_path=None, alpha=0.4):
# plt.figure(figsize=[12,8],dpi=200)
# Load the original image
img = tf.keras.preprocessing.image.load_img(img_path)
img = tf.keras.preprocessing.image.img_to_array(img)
# Rescale heatmap to a range 0-255
heatmap = np.uint8(255 * heatmap)
# Use jet colormap to colorize heatmap
jet = cm.get_cmap("jet")
# Use RGB values of the colormap
jet_colors = jet(np.arange(256))[:, :3]
jet_heatmap = jet_colors[heatmap]
# Create an image with RGB colorized heatmap
jet_heatmap = tf.keras.preprocessing.image.array_to_img(jet_heatmap)
jet_heatmap = jet_heatmap.resize((img.shape[1], img.shape[0]))
jet_heatmap = tf.keras.preprocessing.image.img_to_array(jet_heatmap)
# Superimpose the heatmap on original image
superimposed_img_array = jet_heatmap * alpha + img
# superimposed_img = keras.preprocessing.image.array_to_img(superimposed_img_array)
# Save the superimposed image
# superimposed_img.save(cam_path)
# Display Grad CAM
# display(Image(cam_path))
return superimposed_img_array