自定义分类器pytorch，我想添加softmax

Question

我有这个分类器：

input_dim = 25088
h1_dim = 4096
h2_dim = 2048
h3_dim = 1024
h4_dim = 512
output_dim = len(cat_to_name) # 102
drop_prob = 0.2
model.classifier = nn.Sequential(nn.Linear(input_dim, h1_dim),
nn.ReLU(),
nn.Dropout(drop_prob),
nn.Linear(h1_dim, h2_dim),
nn.ReLU(),
nn.Dropout(drop_prob),
nn.Linear(h2_dim, h3_dim),
nn.ReLU(),
nn.Dropout(drop_prob),
nn.Linear(h3_dim, h4_dim),
nn.ReLU(),
nn.Dropout(drop_prob),
nn.Linear(h4_dim, output_dim),
)

我选择了CrossEntropyLoss作为标准。在验证和测试中，我如何添加Softmax？这是验证循环：

model.eval()
with torch.no_grad():
for images, labels in valid_loader:
images, labels = images.to(device), labels.to(device)
images.requires_grad = True
logits = model.forward(images)
batch_loss = criterion(logits, labels)
valid_loss += batch_loss.item()


ps = torch.exp(logits)
top_p, top_class = ps.topk(1, dim=1)
equals = top_class == labels.view(*top_class.shape)

Answer 1

• CrossEntropyLoss已应用softmax函数。从Pytorch文档：

注意，这种情况等效于LogSoftmax和NLLLoss。

因此，如果您只想使用交叉熵损失，则无需事先应用SoftMax。

• 如果您确实想使用SoftMax功能，您可以执行以下操作：

m = nn.Softmax(dim=1)
output = m(logits)

假设你的logits是(batch_size, number_classes)的形状

您可以检查：https://pytorch.org/docs/stable/generated/torch.nn.Softmax.htmlhttps://pytorch.org/docs/stable/generated/torch.nn.CrossEntropyLoss.html