为什么我在为 PyTorch 模型进行静态量化时收到"断言错误：找不到定影器方法："错误

Question

在尝试对模型应用静态量化时，出现以下错误。错误在代码的保险丝部分：torch.quantization.fuse_modules(model, modules_to_fuse):

model = torch.quantization.fuse_modules(model, modules_to_fuse)
File "/Users/celik/PycharmProjects/GFPGAN/colorization/lib/python3.8/site-packages/torch/ao/quantization/fuse_modules.py", line 146, in fuse_modules
_fuse_modules(model, module_list, fuser_func, fuse_custom_config_dict)
File "/Users/celik/PycharmProjects/GFPGAN/colorization/lib/python3.8/site-packages/torch/ao/quantization/fuse_modules.py", line 77, in _fuse_modules
new_mod_list = fuser_func(mod_list, additional_fuser_method_mapping)
File "/Users/celik/PycharmProjects/GFPGAN/colorization/lib/python3.8/site-packages/torch/ao/quantization/fuse_modules.py", line 45, in fuse_known_modules
fuser_method = get_fuser_method(types, additional_fuser_method_mapping)
File "/Users/celik/PycharmProjects/GFPGAN/colorization/lib/python3.8/site-packages/torch/ao/quantization/fuser_method_mappings.py", line 132, in get_fuser_method
assert fuser_method is not None, "did not find fuser method for: {} ".format(op_list)
AssertionError: did not find fuser method for: (<class 'torch.nn.modules.conv.Conv2d'>,) 

Answer 1

modules_to_fuse列表应遵守以下规则：

Fuses only the following sequence of modules:
conv, bn
conv, bn, relu
conv, relu
linear, relu
bn, relu
All other sequences are left unchanged.
For these sequences, replaces the first item in the list
with the fused module, replacing the rest of the modules
with identity.

我无法为'torch.nn.modules.conv.Conv2d'融合一个模型。它应该与类似的"；圆锥体，bn"；或"；conv，bn，relu"；或"；conv、relu"；其他组合不起作用。使用上面的列表来准备你的融合列表。它对我有效。

这里还有另一个融合方法列表：

DEFAULT_OP_LIST_TO_FUSER_METHOD : Dict[Tuple, Union[nn.Sequential, Callable]] = {
(nn.Conv1d, nn.BatchNorm1d): fuse_conv_bn,
(nn.Conv1d, nn.BatchNorm1d, nn.ReLU): fuse_conv_bn_relu,
(nn.Conv2d, nn.BatchNorm2d): fuse_conv_bn,
(nn.Conv2d, nn.BatchNorm2d, nn.ReLU): fuse_conv_bn_relu,
(nn.Conv3d, nn.BatchNorm3d): fuse_conv_bn,
(nn.Conv3d, nn.BatchNorm3d, nn.ReLU): fuse_conv_bn_relu,
(nn.Conv1d, nn.ReLU): nni.ConvReLU1d,
(nn.Conv2d, nn.ReLU): nni.ConvReLU2d,
(nn.Conv3d, nn.ReLU): nni.ConvReLU3d,
(nn.Linear, nn.BatchNorm1d): fuse_linear_bn,
(nn.Linear, nn.ReLU): nni.LinearReLU,
(nn.BatchNorm2d, nn.ReLU): nni.BNReLU2d,
(nn.BatchNorm3d, nn.ReLU): nni.BNReLU3d,}