“类激活图”（CAM）可视化问题-梯度的平均强度为零

Question

我正在使用带有tensorflow后端的Keras，并且已经基于VGG权重微调了网络的最后一个Conv层和FC层。现在，我正在使用CAM技术来可视化图像的哪些部分触发了预测，并且在特定特征图通道上的梯度平均强度得到了全零。

我有4个班级，对于我的测试样本，这些是预测：

preds_sample = model.predict(x)
output>> array([[1., 0., 0., 0.]], dtype=float32)

# This is the "sample image" entry in the prediction vector    
image_0 = model.output[:, 0]

last_conv_layer = model.get_layer('conv2d_13')
grads = K.gradients(toilet_w, last_conv_layer.output)[0]
grads.shape
output>> TensorShape([Dimension(None), Dimension(512), Dimension(14), Dimension(14)])

由于我使用theano图像排序-当我计算渐变的平均值时，我的轴是（0,2,3）

from keras import backend as K
K.set_image_dim_ordering('th')

pooled_grads = K.mean(grads, axis=(0,2,3))
pooled_grads.shape
output>> TensorShape([Dimension(512)])

iterate = K.function([model.input], [pooled_grads, last_conv_layer.output[0]])
pooled_grads_value, conv_layer_output_value = iterate([x])
pooled_grads_value.shape, conv_layer_output_value.shape
output>> ((512,), (512, 14, 14))

pooled_grads_value都为零

参考：https://github.com/fchollet/deep-learning-with-python-notebooks/blob/master/5.4-visualizing-what-convnets-learn.ipynb

我用更多的图像测试了该算法，发现它适用于某些图像。然后我注意到在最后一个转换层之后有一个退出层。我做了更多的研究https://github.com/jacobgil/keras-grad-cam/issues/2，并将代码修改为：

last_conv_layer = model.get_layer('conv2d_13')
grads = K.gradients(sample_output, last_conv_layer.output)[0]

# normalization trick: we normalize the gradient
#grads = normalize_grad(grads)

pooled_grads = K.mean(grads, axis=(0, 2, 3))
iterate = K.function([model.input, K.learning_phase()], [pooled_grads, last_conv_layer.output[0]])

pooled_grads_value, conv_layer_output_value = iterate([x, 0])

但是对于某些图像，pooled_grads仍为零。