Open Jason-xin opened 5 years ago
I 'm also Confusion about it, maybe the author didn't provide the code to test. Have you solved it?
@stoneeve415 No.... /(ㄒoㄒ)/~~
@Jason-xin @stoneeve415 I want to know how to use the test_net.py too. The results I got is clearly wrong.
2019-03-21 17:19:01,079 maskrcnn_benchmark.inference INFO: OrderedDict([('bbox', OrderedDict([('AP', 9.300105363128172e-09), ('AP50', 6.022500060225e-08), ('AP75', 0.0), ('APs', 9.522348740812624e-09), ('APm', 0.0), ('APl', 0.0)])), ('segm', OrderedDict([('AP', 1.4857428119762759e-08), ('AP50', 5.942971247905103e-08), ('AP75', 0.0), ('APs', 1.519675543192826e-08), ('APm', 0.0), ('APl', 0.0)]))])
I have put the model after training in the corresponding link which can be found in README. For testing one image, you can follow the original maskrcnn-benchmark https://github.com/facebookresearch/maskrcnn-benchmark/tree/master/demo
I have put the model after training in the corresponding link which can be found in README. For testing one image, you can follow the original maskrcnn-benchmark https://github.com/facebookresearch/maskrcnn-benchmark/tree/master/demo
thank you! i got it
hello,Can you tell me how to do it? @stoneeve415
@zhuliqian https://github.com/XiaoLaoDi/maskscoring_rcnn here I provide the demo.py and pretrained models, hoping can help you.
I just want to test one image, and show its mask result.... Can you tell me what should I do?? Maybe "tests/test_data_samplers.py", but I don't known how to run it? Thanks!