Question

我正在尝试使用PyTorch website中的示例代码来转换python模型，以便在PyTorch c ++ api（LibTorch）中使用。

Converting to Torch Script via Tracing
To convert a PyTorch model to Torch Script via tracing, you must pass an instance of your model along with an example input to the torch.jit.trace function. This will produce a torch.jit.ScriptModule object with the trace of your model evaluation embedded in the module’s forward method:

import torch
import torchvision

# An instance of your model.
model = torchvision.models.resnet18()

# An example input you would normally provide to your model's forward() method.
example = torch.rand(1, 3, 224, 224)

# Use torch.jit.trace to generate a torch.jit.ScriptModule via tracing.
traced_script_module = torch.jit.trace(model, example)
traced_script_module.save("model.pt")

此示例工作正常，并按预期保存了文件。当我切换到该模型时：

model = models.segmentation.deeplabv3_resnet101(pretrained=True)

它给我以下错误：

File "convert.py", line 14, in <module>
    traced_script_module = torch.jit.trace(model, example)
  File "C:\Python37\lib\site-packages\torch\jit\__init__.py", line 636, in trace
          raise ValueError('Expected more than 1 value per channel when training, got input size {}'.format(size))
ValueError: Expected more than 1 value per channel when training, got input size torch.Size([1, 256, 1, 1])

我认为这是因为example格式错误，但是如何获得正确的格式呢？

根据下面的评论，我的新代码是：

import torch
import torchvision
from torchvision import models


model = models.segmentation.deeplabv3_resnet101(pretrained=True)
model.eval()


# An example input you would normally provide to your model's forward() method.
example = torch.rand(1, 3, 224, 224)

# Use torch.jit.trace to generate a torch.jit.ScriptModule via tracing.
traced_script_module = torch.jit.trace(model, example)

traced_script_module.save("model.pt")

现在我得到了错误：

File "convert.py", line 15, in <module>
    traced_script_module = torch.jit.trace(model, example)
  File "C:\Python37\lib\site-packages\torch\jit\__init__.py", line 636, in trace
    var_lookup_fn, _force_outplace)
RuntimeError: Only tensors and (possibly nested) tuples of tensors are supported as inputs or outputs of traced functions (toIValue at C:\a\w\1\s\windows\pytorch\torch/csrc/jit/pybind_utils.h:91)
(no backtrace available)

Answer 1

您的问题出在BatchNorm层。如果每个通道需要个以上的值，则您的模型处于训练模式。您可以在模型上调用https://pytorch.org/cppdocs/api/classtorch_1_1nn_1_1_module.html#_CPPv4N5torch2nn6Module4evalEv并查看是否有改进吗？

否则，您也可以尝试生成一个批次中有多个实例的随机数据，即example = torch.rand(5, 3, 224, 224)。

此外，您应该注意正确规范化数据，但是，这不会引起错误。

Answer 2

（来自pytorch论坛）

trace仅支持将张量或张量元组作为输出的模块。根据deeplabv3的实现，其输出为OrderedDict。那是个问题。为了解决这个问题，制作一个包装模块

class wrapper(torch.nn.Module):
    def __init__(self, model):
        super(wrapper, self).__init__()
        self.model = model

    def forward(self, input):
        results = []
        output = self.model(input)
        for k, v in output.items():
            results.append(v)
        return tuple(results)

model = wrapper(deeplap_model)
#trace...

是否保存了我的模型。

LibTorch，将deeplabv3_resnet101转换为C ++

2 个答案: