python - 如何在Tensorflow 2.0中应用Guided BackProp？

我从Tensorflow 2.0开始，尝试实现Guided BackProp来显示Saliency Map。我首先计算图像的y_pred和y_true之间的损失，然后查找由于该损失而导致的所有图层的梯度。

with tf.GradientTape() as tape:
    logits = model(tf.cast(image_batch_val, dtype=tf.float32))
    print('`logits` has type {0}'.format(type(logits)))
    xentropy = tf.nn.softmax_cross_entropy_with_logits(labels=tf.cast(tf.one_hot(1-label_batch_val, depth=2), dtype=tf.int32), logits=logits)
    reduced = tf.reduce_mean(xentropy)
    grads = tape.gradient(reduced, model.trainable_variables)

但是，我不知道如何使用渐变来获得引导传播。

这是我的模型。我使用Keras图层创建了它:

image_input = Input((input_size, input_size, 3))

conv_0 = Conv2D(32, (3, 3), padding='SAME')(image_input)
conv_0_bn = BatchNormalization()(conv_0)
conv_0_act = Activation('relu')(conv_0_bn)
conv_0_pool = MaxPool2D((2, 2))(conv_0_act)

conv_1 = Conv2D(64, (3, 3), padding='SAME')(conv_0_pool)
conv_1_bn = BatchNormalization()(conv_1)
conv_1_act = Activation('relu')(conv_1_bn)
conv_1_pool = MaxPool2D((2, 2))(conv_1_act)

conv_2 = Conv2D(64, (3, 3), padding='SAME')(conv_1_pool)
conv_2_bn = BatchNormalization()(conv_2)
conv_2_act = Activation('relu')(conv_2_bn)
conv_2_pool = MaxPool2D((2, 2))(conv_2_act)

conv_3 = Conv2D(128, (3, 3), padding='SAME')(conv_2_pool)
conv_3_bn = BatchNormalization()(conv_3)
conv_3_act = Activation('relu')(conv_3_bn)

conv_4 = Conv2D(128, (3, 3), padding='SAME')(conv_3_act)
conv_4_bn = BatchNormalization()(conv_4)
conv_4_act = Activation('relu')(conv_4_bn)
conv_4_pool = MaxPool2D((2, 2))(conv_4_act)

conv_5 = Conv2D(128, (3, 3), padding='SAME')(conv_4_pool)
conv_5_bn = BatchNormalization()(conv_5)
conv_5_act = Activation('relu')(conv_5_bn)

conv_6 = Conv2D(128, (3, 3), padding='SAME')(conv_5_act)
conv_6_bn = BatchNormalization()(conv_6)
conv_6_act = Activation('relu')(conv_6_bn)

flat = Flatten()(conv_6_act)

fc_0 = Dense(64, activation='relu')(flat)
fc_0_bn = BatchNormalization()(fc_0)

fc_1 = Dense(32, activation='relu')(fc_0_bn)
fc_1_drop = Dropout(0.5)(fc_1)

output = Dense(2, activation='softmax')(fc_1_drop)

model = models.Model(inputs=image_input, outputs=output)

如果需要，我很高兴提供更多代码。

最佳答案

首先，您必须通过ReLU(即)更改梯度的计算

这里是paper的图形示例。

可以使用以下代码来实现此公式:

@tf.RegisterGradient("GuidedRelu")
def _GuidedReluGrad(op, grad):
   gate_f = tf.cast(op.outputs[0] > 0, "float32") #for f^l > 0
   gate_R = tf.cast(grad > 0, "float32") #for R^l+1 > 0
   return gate_f * gate_R * grad

现在，您必须使用以下方法覆盖ReLU的原始TF实现:

with tf.compat.v1.get_default_graph().gradient_override_map({'Relu': 'GuidedRelu'}):
   #put here the code for computing the gradient

计算梯度后，您可以可视化结果。
但是，最后一句话。您为单个类计算可视化效果。这意味着，您将激活所选神经元，并将其他神经元的所有激活都设置为零作为Guided BackProp的输入。