metrics
metrics copied to clipboard
Mean of empty slice, and the reults are [nan,nan].
100% 4/4 [00:00<00:00, 257.20it/s] --[input_img_shape]: (128, 128, 3) passing through inception network ... 100% 1/1 [00:01<00:00, 2.00s/it] /usr/local/lib/python3.7/dist-packages/numpy/core/fromnumeric.py:3373: RuntimeWarning: Mean of empty slice. out=out, **kwargs) /usr/local/lib/python3.7/dist-packages/numpy/core/_methods.py:163: RuntimeWarning: invalid value encountered in true_divide ret, rcount, out=ret, casting='unsafe', subok=False) /usr/local/lib/python3.7/dist-packages/numpy/core/_methods.py:170: RuntimeWarning: invalid value encountered in true_divide ret = ret.dtype.type(ret / rcount) nan nan
100% 4/4 [00:00<00:00, 257.20it/s] --[input_img_shape]: (128, 128, 3) passing through inception network ... 100% 1/1 [00:01<00:00, 2.00s/it] /usr/local/lib/python3.7/dist-packages/numpy/core/fromnumeric.py:3373: RuntimeWarning: Mean of empty slice. out=out, **kwargs) /usr/local/lib/python3.7/dist-packages/numpy/core/_methods.py:163: RuntimeWarning: invalid value encountered in true_divide ret, rcount, out=ret, casting='unsafe', subok=False) /usr/local/lib/python3.7/dist-packages/numpy/core/_methods.py:170: RuntimeWarning: invalid value encountered in true_divide ret = ret.dtype.type(ret / rcount) nan nan
I am not sure wheather the influence of input image size, since my image size is only 128*128.