在 Tensorflow 2.0 中使用带引导反向传播的 Gradcam 进行迁移学习

Question

我在 TF 2.0 中使用带有迁移学习的梯度可视化时出错。梯度可视化适用于不使用迁移学习的模型。

当我运行我的代码出现错误时：

    assert str(id(x)) in tensor_dict, 'Could not compute output ' + str(x)
AssertionError: Could not compute output Tensor("block5_conv3/Identity:0", shape=(None, 14, 14, 512), dtype=float32)

当我运行下面的代码出错时。我认为命名约定或将基本模型 vgg16 的输入和输出连接到我要添加的层存在问题。非常感谢您的帮助！

"""
Broken example when grad_model is created. 
"""
!pip uninstall tensorflow
!pip install tensorflow==2.0.0
import cv2
import numpy as np
import tensorflow as tf
from tensorflow.keras import layers
import matplotlib.pyplot as plt

IMAGE_PATH = '/content/cat.3.jpg'
LAYER_NAME = 'block5_conv3'
model_layer = 'vgg16'
CAT_CLASS_INDEX = 281

imsize = (224,224,3)

img = tf.keras.preprocessing.image.load_img(IMAGE_PATH, target_size=(224, 224))
plt.figure()
plt.imshow(img)
img = tf.io.read_file(IMAGE_PATH)
img = tf.image.decode_jpeg(img)
img = tf.cast(img, dtype=tf.float32)
# img = tf.keras.preprocessing.image.img_to_array(img)
img = tf.image.resize(img, (224,224))
img = tf.reshape(img, (1, 224,224,3))

input = layers.Input(shape=(imsize[0], imsize[1], imsize[2]))
base_model = tf.keras.applications.VGG16(include_top=False, weights='imagenet',
                                          input_shape=(imsize[0], imsize[1], imsize[2]))
# base_model.trainable = False
flat = layers.Flatten()
dropped = layers.Dropout(0.5)
global_average_layer = tf.keras.layers.GlobalAveragePooling2D()

fc1 = layers.Dense(16, activation='relu', name='dense_1')
fc2 = layers.Dense(16, activation='relu', name='dense_2')
fc3 = layers.Dense(128, activation='relu', name='dense_3')
prediction = layers.Dense(2, activation='softmax', name='output')
for layr in base_model.layers:
    if ('block5' in layr.name):

        layr.trainable = True
    else:
        layr.trainable = False

x = base_model(input)
x = global_average_layer(x)
x = fc1(x)
x = fc2(x)
x = prediction(x)

model = tf.keras.models.Model(inputs = input, outputs = x)
model.compile(optimizer=tf.keras.optimizers.Adam(learning_rate=1e-4),
                  loss='binary_crossentropy',
                  metrics=['accuracy'])

这部分代码是错误所在。我不确定标记输入和输出的正确方法是什么。

# Create a graph that outputs target convolution and output
grad_model = tf.keras.models.Model(inputs = [model.input, model.get_layer(model_layer).input], 
                                   outputs=[model.get_layer(model_layer).get_layer(LAYER_NAME).output,
                                            model.output])

print(model.get_layer(model_layer).get_layer(LAYER_NAME).output)
# Get the score for target class

# Get the score for target class
with tf.GradientTape() as tape:
    conv_outputs, predictions = grad_model(img)
    loss = predictions[:, 1]

以下部分用于绘制 gradcam 的热图。

print('Prediction shape:', predictions.get_shape())
# Extract filters and gradients
output = conv_outputs[0]
grads = tape.gradient(loss, conv_outputs)[0]

# Apply guided backpropagation
gate_f = tf.cast(output > 0, 'float32')
gate_r = tf.cast(grads > 0, 'float32')
guided_grads = gate_f * gate_r * grads

# Average gradients spatially
weights = tf.reduce_mean(guided_grads, axis=(0, 1))

# Build a ponderated map of filters according to gradients importance
cam = np.ones(output.shape[0:2], dtype=np.float32)

for index, w in enumerate(weights):
    cam += w * output[:, :, index]

# Heatmap visualization
cam = cv2.resize(cam.numpy(), (224, 224))
cam = np.maximum(cam, 0)
heatmap = (cam - cam.min()) / (cam.max() - cam.min())

cam = cv2.applyColorMap(np.uint8(255 * heatmap), cv2.COLORMAP_JET)

output_image = cv2.addWeighted(cv2.cvtColor(img.astype('uint8'), cv2.COLOR_RGB2BGR), 0.5, cam, 1, 0)

plt.figure()
plt.imshow(output_image)
plt.show()

我也在 github https://github.com/tensorflow/tensorflow/issues/37680 上向 tensorflow 团队询问了这个问题。

Answer 1

我明白了。如果你设置模型扩展 vgg16 基础模型与你自己的层，而不是像层一样将基础模型插入到新模型中，那么它就可以工作。首先设置模型，一定要声明input_tensor。

inp = layers.Input(shape=(imsize[0], imsize[1], imsize[2]))
base_model = tf.keras.applications.VGG16(include_top=False, weights='imagenet', input_tensor=inp,
                                          input_shape=(imsize[0], imsize[1], imsize[2]))

这样我们就不必包含像 x=base_model(inp) 这样的行来显示我们想要输入的内容。这已经包含在 tf.keras.applications.VGG16(...).

中

与其将此 vgg16 基础模型放入另一个模型，不如通过向基础模型本身添加层来更容易地进行 gradcam。我抓取了 VGG16 最后一层的输出（去掉了顶部），也就是池化层。

block5_pool = base_model.get_layer('block5_pool')
x = global_average_layer(block5_pool.output)
x = fc1(x)
x = prediction(x)

model = tf.keras.models.Model(inputs = inp, outputs = x)
model.compile(optimizer=tf.keras.optimizers.Adam(learning_rate=1e-4),
                  loss='binary_crossentropy',
                  metrics=['accuracy'])

现在，我抓取图层进行可视化，LAYER_NAME='block5_conv3'。

# Create a graph that outputs target convolution and output
grad_model = tf.keras.models.Model(inputs = [model.input], 
                                   outputs=[model.output, model.get_layer(LAYER_NAME).output])

print(model.get_layer(LAYER_NAME).output)
# Get the score for target class

# Get the score for target class
with tf.GradientTape() as tape:
    predictions, conv_outputs = grad_model(img)
    loss = predictions[:, 1]
print('Prediction shape:', predictions.get_shape())
# Extract filters and gradients
output = conv_outputs[0]
grads = tape.gradient(loss, conv_outputs)[0]

Answer 2

我们（我和一些开发项目的团队成员）发现了一个与我们在 tutorial.

中发现的实现 Grad-CAM 的代码类似的问题

该代码不适用于由 VGG19 基本模型加上在其上添加的一些额外层组成的模型。问题是 VGG19 基础模型作为 "layer" 插入到我们的模型中，显然 GradCAM 代码不知道如何处理它 - 我们遇到了 "Graph disconnected..." 错误。然后经过一些调试（由另一个团队成员进行，而不是我），我们设法修改了原始代码，使其适用于这种包含另一个模型的模型。这个想法是将内部模型添加为 class GradCAM 的额外参数。因为这可能对其他人有帮助，所以我在下面包含修改后的代码（我们还将 GradCAM class 重命名为 My_GradCAM）。

class My_GradCAM:
    def __init__(self, model, classIdx, inner_model=None, layerName=None):
        self.model = model
        self.classIdx = classIdx
        self.inner_model = inner_model
        if self.inner_model == None:
            self.inner_model = model
        self.layerName = layerName

[...]

        gradModel = tensorflow.keras.models.Model(inputs=[self.inner_model.inputs],
                  outputs=[self.inner_model.get_layer(self.layerName).output,
                  self.inner_model.output])

然后 class 可以通过添加内部模型作为额外参数来实例化，例如：

cam = My_GradCAM(model, None, inner_model=model.get_layer("vgg19"), layerName="block5_pool")

希望对您有所帮助。

编辑： 感谢 Mirtha Lucas 进行调试并找到解决方案。

Answer 3

经过一番折腾，总结出大家使用迁移学习时绘制热图的方法。这是keras official tutorial

The issue I encounter is that when I'm trying to draw the heat map from my model, the densenet can be only seen as functional layer in my model. So the make_gradcam_heatmap can not figure out the layer that inside functional layer. As the 5th layer shows.

因此，为了模拟Keras官方文档，我只需要使用densenet作为模型进行可视化即可。这是步骤

只从你的模型中取出模型

dense_model = dense_model.get_layer('densenet121')

将权重从密集模型复制到新启动的模型

inputs = tf.keras.Input(shape=(224, 224, 3))
model = model_builder(weights="imagenet", include_top=True, input_tensor=inputs)
for layer, dense_layer in zip(model.layers[1:], dense_model.layers[1:]):
    layer.set_weights(dense_layer.get_weights())

relu = model.get_layer('relu')
x = tf.keras.layers.GlobalAveragePooling2D()(relu.output)
outputs = tf.keras.layers.Dense(5)(x)
model = tf.keras.models.Model(inputs = inputs, outputs = outputs)

绘制热图

preprocess_input = keras.applications.densenet.preprocess_input
img_array = preprocess_input(get_img_array(img_path, size=(224, 224)))
heatmap = make_gradcam_heatmap(img_array, model, 'bn')
plt.matshow(heatmap)
plt.show()

get_img_array、make_gradcam_heatmap 和 save_and_display_gradcam 保持不变。按照 keras 教程进行操作，然后你就可以开始了。

在 Tensorflow 2.0 中使用带引导反向传播的 Gradcam 进行迁移学习

Gradcam with guided backprop for transfer learning in Tensorflow 2.0

python

gradient

backpropagation

tensorflow2.0