Raj-08/tensorflow-object-contour-detection

NumPy Predictions Visualizations

Opened this issue · 2 comments

Hi,

After running the eval.py file the final predictions are saved as numPy arrays using the code statement: np.save(FLAGS.save_preds+l,P)

My question is how should we visualize these predictions in images?

Thanks in advance

Read the NumPy array using: np.load then save it using cv2.imwrite

I have the same problem, and the stored NumPy array is 4D finally.(Is this correct?)
I tried to convert it to an image and store, but it does not work.
Hope to get answers, thx.