Caffe2相当于Caffe的Net.backward（）？

Question

我正在尝试获取相对于输入图像的损失渐变。在Caffe（原文）中，以下代码实现了我的目标：

### Load image into net's data layer
img = caffe.io.load_image(jpg_file)
transformed_image = transformer.preprocess('data', img)
net.blobs['data'].data[...] = transformed_image    # copy image data into memory for net

...

### Form the final label vector (one hot vector)
finalLabelVector = np.zeros((1,num_classes))
finalLabelVector[0,ground_truth_label] = 1

### Do a backward pass using finalLabelVector
# must have 'force_backward: true' set in deploy prototxt
backwardpassData = net.backward(**{net.outputs[0]: finalLabelVector})

# Get the derivative with respect to the input (data layer)
delta = backwardpassData['data']

使用Caffe2 Python界面计算与上面相同的delta，我该怎么办？