🔒 Prediction on test image is completely blank

[mystic island]

import random
test_img_number = random.randint(0, a.shape[0]-1)
test_img = a[test_img_number]
ground_truth=b[test_img_number]
#test_img_norm=test_img[:,:,0][:,:,None]
test_img_input=np.expand_dims(test_img, 0)
prediction = (model.predict(test_img_input)[0,:,:,0] > 0.5).astype(np.uint8)

plt.figure(figsize=(16, 8))
plt.subplot(231)
plt.title('Testing Image')
plt.imshow(test_img, cmap='gray')
plt.subplot(232)
plt.title('Testing Label')
plt.imshow(ground_truth[:,:,0], cmap='gray')
plt.subplot(233)
plt.title('Prediction on test image')
plt.imshow(prediction, cmap='gray')

plt.show()

whenever i run this chunk of code the prediction on test image it is completely blank. I have trained the model for 50 epochs and thresholds between 0 and 0.7 seem to be blank, however thresholds between 0.8-0.9 seem to output a white nonsense

[idle hinge]

@mystic island

Python help channel opened

Remember to:

• Ask your Python question, not if you can ask or if there's an expert who can help.
• Show a code sample as text (rather than a screenshot) and the error message, if you've got one.
• Explain what you expect to happen and what actually happens.

:warning: Do not pip install anything that isn't related to your question, especially if asked to over DMs.

Closes after a period of inactivity, or when you send !close.

[mystic island]

i also found something new, for some fucking reason when the threshold is above 0.5 it highlights the edges of the testing image rather than the testing label

[idle hinge]

@mystic island

Python help channel closed

This help channel has been closed and it's no longer possible to send messages here. If your question wasn't answered, feel free to create a new post in #1035199133436354600. To maximize your chances of getting a response, check out this guide on asking good questions.