JayLee15

测试了多张图片发现依然存在上述问题 不开启mkldnn结果： {'boxes': array([[0.0000000e+00, 2.9145604e-01, 2.6589603e+02, 3.6681244e+02, 3.0432248e+02, 4.1769321e+02], [1.1000000e+01, 1.1651322e-01, 7.1439152e+00, 3.7374794e+01, 4.2610181e+02, 5.0756027e+02], [7.3000000e+01, 3.3812910e-01, 7.8442383e-01, 3.6608387e+01, 4.4896344e+02, 5.0576721e+02], [7.4000000e+01, 1.3708681e-01, 4.1523376e+00, 4.0477535e+01, 4.2329196e+02, 4.9252173e+02], [7.4000000e+01, 1.4600465e-01, 2.8948755e+01,...

不开启mkldnn： {'boxes': array([[ 74. , 0.9945931 , 228.81963 , 152.98608 , 299.21884 , 223.9967 ], [ 74. , 0.95573527, 174.15001 , 180.1396 , 201.7896 , 236.1698 ]], dtype=float32), 'masks': array([[[0,...

不开启mkldnn： {'boxes': array([[7.4000000e+01, 7.0395261e-02, 3.8677655e+02, 1.3604433e+02, 4.0381525e+02, 2.9166379e+02], [7.4000000e+01, 5.1174235e-02, 3.6764462e+02, 1.8386264e+02, 3.8638199e+02, 2.4731769e+02]], dtype=float32), 'masks': array([[[0, 0, 0, ..., 0, 0, 0], [0, 0, 0, ..., 0, 0, 0],...

这个有什么进展吗？

I have modified label.pbtxt file and model training config file and generate_tf.py file. But it recognize only 1 class. Did any one finds the solution?

@leccyril Yes, I have modified the number class in pipeline.config, but it recognizes only 1 class.

> @JayLee15 @bassmaamn @leccyril @bassmaamn i have the same problem with yours. Did you solved your problem? If you solved it, how did you solved it? Can you please explain...

同问