[英]How to translate the neural network of MLP from tensorflow to pytorch
I have built up an MLP neural network using 'Tensorflow', which is stated as follow:我已经使用“Tensorflow”建立了一个 MLP 神经网络,如下所示:
model_mlp=Sequential()
model_mlp.add(Dense(units=35, input_dim=train_X.shape[1], kernel_initializer='normal', activation='relu'))
model_mlp.add(Dense(units=86, kernel_initializer='normal', activation='relu'))
model_mlp.add(Dense(units=86, kernel_initializer='normal', activation='relu'))
model_mlp.add(Dense(units=10, kernel_initializer='normal', activation='relu'))
model_mlp.add(Dense(units=1))
I want to convert the above MLP code using pytorch.我想使用 pytorch 转换上述 MLP 代码。 How to do it?怎么做? I try to do it as follows:我尝试按如下方式进行:
class MLP(nn.Module):
def __init__(self):
super(MLP, self).__init__()
self.fc1 = nn.Linear(train_X.shape[1],35)
self.fc2 = nn.Linear(35, 86)
self.fc3 = nn.Linear(86, 86)
self.fc4 = nn.Linear(86, 10)
self.fc5 = nn.Linear(10, 1)
def forward(self, x):
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
x = F.relu(self.fc3(x))
x = F.relu(self.fc4(x))
x = self.fc5(x)
return x
def predict(self, x_test):
x_test = torch.from_numpy(x_test).float()
x_test = self.forward(x_test)
return x_test.view(-1).data.numpy()
model = MLP()
I use the same dataset but the two codes give two different answers.我使用相同的数据集,但两个代码给出了两个不同的答案。 Code written in Tensorflow always produce a much better results than using the code written in Pytorch.用 Tensorflow 编写的代码总是比使用 Pytorch 编写的代码产生更好的结果。 I wonder if my code in pytorch is not correct.我想知道我在 pytorch 中的代码是否不正确。 In case my written code in PyTorch is correct, I wonder how to explain the differences.如果我在 PyTorch 中编写的代码是正确的,我想知道如何解释这些差异。 I am looking forward to any replies.我期待着任何答复。
Welcome to pytorch!欢迎来到 pytorch!
I guess the problem is with the initialization of your network.我想问题出在网络的初始化上。 That is how I would do it:我就是这样做的:
def init_weights(m):
if type(m) == nn.Linear:
torch.nn.init.xavier_normal(m.weight) # initialize with xaver normal (called gorot in tensorflow)
m.bias.data.fill_(0.01) # initialize bias with a constant
class MLP(nn.Module):
def __init__(self, input_dim):
super(MLP, self).__init__()
self.mlp = nn.Sequential(nn.Linear(input_dim ,35), nn.ReLU(),
nn.Linear(35, 86), nn.ReLU(),
nn.Linear(86, 86), nn.ReLU(),
nn.Linear(86, 10), nn.ReLU(),
nn.Linear(10, 1), nn.ReLU())
def forward(self, x):
y =self.mlp(x)
return y
model = MLP(input_dim)
model.apply(init_weights)
optimizer = Adam(model.parameters())
loss_func = BCEWithLogistLoss()
# training loop
for data, label in dataloader:
optimizer.zero_grad()
pred = model(data)
loss = loss_func(pred, lable)
loss.backward()
optimizer.step()
Notice that in pytorch we do not call model.forward(x)
, but model(x)
.请注意,在 pytorch 中,我们不调用model.forward(x)
,而是调用model(x)
。 That is because nn.Module
applies hooks in .__call__()
that are used in the backward pass.这是因为nn.Module
在.__call__()
中应用了后向传递中使用的钩子。
You can check the documentation of weight initialization here: https://pytorch.org/docs/stable/nn.init.html您可以在此处查看权重初始化的文档: https://pytorch.org/docs/stable/nn.init.html
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.