cinastanbean/pytorch-onnx-tensorflow-pb

Converting A PyTorch Model to Tensorflow pb using ONNX

pytorch-onnx-tensorflow-pb's Issues

onnx和pytorch同一输入不同输出？

你好！我把pytorch模型转换成onnx后，用同一个输入，两个模型输出的结果不一致该怎么办呢？torch.onnx.export中的参数model应该是没有问题的，会是因为其他参数吗？

RuntimeError: Resize coordinate_transformation_mode=pytorch_half_pixel is not supported in Tensorflow.

onnx转pb模型的时候，报这个错误：
Traceback (most recent call last):
File "onnx2pb.py", line 45, in
onnx2pb_2(onnx_input_path)
File "onnx2pb.py", line 14, in onnx2pb_2
tf_rep = prepare(model)
File "/home/fffan/下载/onnx-tensorflow-rel-1.6.0/onnx_tf/backend.py", line 66, in prepare
return cls.onnx_model_to_tensorflow_rep(model, strict)
File "/home/fffan/下载/onnx-tensorflow-rel-1.6.0/onnx_tf/backend.py", line 86, in onnx_model_to_tensorflow_rep
return cls._onnx_graph_to_tensorflow_rep(model.graph, opset_import, strict)
File "/home/fffan/下载/onnx-tensorflow-rel-1.6.0/onnx_tf/backend.py", line 147, in _onnx_graph_to_tensorflow_rep
strict=strict)
File "/home/fffan/下载/onnx-tensorflow-rel-1.6.0/onnx_tf/backend.py", line 252, in _onnx_node_to_tensorflow_op
return handler.handle(node, tensor_dict=tensor_dict, strict=strict)
File "/home/fffan/下载/onnx-tensorflow-rel-1.6.0/onnx_tf/handlers/handler.py", line 59, in handle
cls.args_check(node, **kwargs)
File "/home/fffan/下载/onnx-tensorflow-rel-1.6.0/onnx_tf/handlers/backend/resize.py", line 89, in args_check
"Tensorflow")
File "/home/fffan/下载/onnx-tensorflow-rel-1.6.0/onnx_tf/common/exception.py", line 49, in call
raise self._func(self.get_message(op, framework))
RuntimeError: Resize coordinate_transformation_mode=pytorch_half_pixel is not supported in Tensorflow.
请问这个问题该怎么解决啊

If loading model weights with Error....

@cinastanbean
thanks for your great job,but i can't find the model_best_checkpoint_resnet18.pth.tar ,it's different with it,can you post this weights,looking for your replay,thanks very much.

有没有tensorflow 转 pytorch的