mohhao
mohhao
my image:  result:  I use the code like this: ```python d = dcrf.DenseCRF2D(640, 368, 4) prediction1 = prediction1.reshape((4, -1)) d.setUnaryEnergy(prediction1.astype(np.float32)) d.addPairwiseGaussian(sxy=3, compat=3) cv2.imwrite('test.jpg', (image[i]/.016 + 128).astype(np.uint8)) d.addPairwiseBilateral(sxy=(80, 80),...
I have trained a best model by imagenet,but code repo has given does not have test option,so how can I use the model have trained to classifier pictures with labels?