如何为PyTorch中的组合网络获得正确的梯度？

我使用由FAIR和我自己的分类器预先训练的ESM变压器组成的组合网络。我应该提到，我将transformer的第一层更改为identity层，因为我想用Embedded计算嵌入。为了以后能够对它们进行操作，请将此变压器的层分开。 我想为输入计算梯度，但是，当我使用torch autograd时，我得到了一个错误的梯度。我通过使用f（x+e）-f（x-e））/2e手动计算一个位置的梯度来检查它，其中f-是我的组合网络，x-输入的特定位置，e-小增量。我不确定我的自动差速器到底出了什么问题。 这是我的密码：

# ======== split the transformer model in two, getting access to the embedding layer=====
splitted_model = []
for name, module in transformer.named_children():
    splitted_model.append(module)

# take the first layer
embedding_layer = splitted_model[0]
embedding = embedding_layer(input_tokens)
#replace the embedding layer with an Identity layer
identity_layer = torch.nn.Identity()
transformer.embed_tokens = identity_layer
#set token dropout to False
transformer.args.token_dropout=False

# this will be an input to my combined network
input_embedding = embedding_layer(input_tokens)

# ========. combine transformer and my classifier. ==============
# create class
class FullModel(nn.Module):
    def __init__(self, transformer, classifier_nn):
        super(FullModel, self).__init__()
        self.transformer = transformer
        self.classifier_nn = classifier_nn
        
    def forward(self, x):
# calculate representation matrix of a shape L, E. L - length on input sequence, E - length of feature verctor. token 0 is a start-of-sequence token, so the first symbol of input is token 1
        x1 = self.transformer(x, repr_layers=[34])["representations"][34][0,1 : len(x[0]) + 1]
# average over L to get representation vector of length E
        x2 = torch.mean(x1, dim=0)
# use it for the classification
        x3 = self.classifier_nn(x2)
        return x3
# combine
transformer_model = transformer
classifier_nn = my_classifier
final_model = FullModel(transformer_model, classifier_nn)

# ======== compute gradient =========
# define for which output class i want to get gradient
external = torch.tensor([1,0,0]) #1st out of 3 possible

x = Variable(input_embedding, requires_grad=True)
pred = final_model(x)
pred.backward(gradient=external)
input_gradient = x.grad