Dear @kitstar,
Sorry for the inconvenience, I run your mentioned command (with new argument), and I got this result:

return f(*args, **kwds)
[(1278, 0.48384374), (1277, 0.26611671), (282, 0.1002832), (1224, 0.027631452), (1282, 0.025890373)]
Traceback (most recent call last):
  File "/home/karami/anaconda3/lib/python3.6/runpy.py", line 193, in _run_module_as_main
    "__main__", mod_spec)
  File "/home/karami/anaconda3/lib/python3.6/runpy.py", line 85, in _run_code
    exec(code, run_globals)
  File "/home/karami/anaconda3/lib/python3.6/site-packages/mmdnn/conversion/examples/pytorch/imagenet_test.py", line 66, in <module>
    tester.inference(tester.args.image)
  File "/home/karami/anaconda3/lib/python3.6/site-packages/mmdnn/conversion/examples/pytorch/imagenet_test.py", line 51, in inference
    self.test_truth()
  File "/home/karami/anaconda3/lib/python3.6/site-packages/mmdnn/conversion/examples/imagenet_test.py", line 192, in test_truth
    assert np.isclose(this_truth[index][1], i[1], atol = 1e-6)
AssertionError

Unfortunately, I got error again! and another amazing thing that the produced results on my machine is a little different from your reported results!!

My System Results:
[(1278, 0.48384374), (1277, 0.26611671), (282, 0.1002832), (1224, 0.027631452), (1282, 0.025890373)]
Your Reported Results:
[(1278, 0.49070838), (1277, 0.21392572), (282, 0.12979434), (1282, 0.066355459), (1224, 0.022040628)]

Convert Model from MXNet to PyTorch #6

Description

ahkaramiopenedon Nov 29, 2017

Metadata

Assignees

Labels

Type

Projects

Milestone

Relationships

Development

Issue actions

ahkarami
openedon Nov 29, 2017