MTLab/onnx2caffe

onnx2caffe segfaults

Opened this issue · 1 comments

This Framework segfaults when I try to convert my onnx model to a caffemodel. Any leads on how to progress with the situation?

I tried converting a LeNet ONNX model to a protoxt and caffemodel equivalent

I have tested LeNet and it works well. I think it might be caused by the implicit between your torch and onnx, could you comment code about pytorch like this in convertCaffe.py and try it again?

from __future__ import print_function
#import torch
#import torch.nn

import sys
import onnx
import numpy as np
import caffe
from caffe.proto import caffe_pb2