search

MTLab / onnx2caffe

pytorch to caffe by onnx
MIT License
367 stars 102 forks source link

shufflenet v2 model onnx to caffe failed #39

Open wxhqw opened 4 years ago

wxhqw commented 4 years ago

Traceback (most recent call last): File "convertCaffe.py", line 112, in convertToCaffe(graph, prototxt_path, caffemodel_path) File "convertCaffe.py", line 58, in convertToCaffe layer = converter_fn(node,graph,err) File "/data00/huqingwen.huqwen/workspace/npu/caffe2pb2tflite/gesture/hand-gestures/apu/pytorch2onnx2caffe2tf/onnx2caffe/_operators.py", line 194, in _convert_Reshape return err.unsupported_op_configuration(node, "Reshape dimention number shall be 2 or 4") File "/data00/huqingwen.huqwen/workspace/npu/caffe2pb2tflite/gesture/hand-gestures/apu/pytorch2onnx2caffe2tf/onnx2caffe/_error_utils.py", line 46, in unsupported_op_configuration "Error while converting op of type: {}. Error message: {}\n".format(node.op_type, err_message, ) TypeError: Error while converting op of type: Reshape. Error message: Reshape dimention number shall be 2 or 4

northeastsquare commented 4 years ago

@MTlab I also met this problem, when convert pytorch yolov3 to onnx, then convert to caffe 我也遇到这个问题，在用yolov3转换到onnx, 再转换到caffe

RichardSong-dev commented 3 years ago

@MTlab I also met this problem, when convert pytorch yolov3 to onnx, then convert to caffe 我也遇到这个问题，在用yolov3转换到onnx, 再转换到caffe

所以老哥问题解决了吗？我估计和你情况一样，pytorch->onnx->caffe。用opset9就报这个错，opset11在转upsample时报KeyError: 'height_scale'。

songh11 commented 3 years ago

@MTlab I also met this problem, when convert pytorch yolov3 to onnx, then convert to caffe 我也遇到这个问题，在用yolov3转换到onnx, 再转换到caffe

所以老哥问题解决了吗？我估计和你情况一样，pytorch->onnx->caffe。用opset9就报这个错，opset11在转upsample时报KeyError: 'height_scale'。

请问有解决方法么，我pytorch1.5->onnx->caffe时也会报Reshape的错，在opset9时简化模型，会报Upsample的错