The model predicts test image data correctly but when implementing with anvil I don't get the output

Anvil Q&A
1

I implemented the dogs vs cats code to what am working in (image classification), I followed step by step but when uploading image to get whether the image is dogs (normal) or cats (abnormal) the output doesn’t show

Code Sample:

test_img = test_img.resize((W,H), resample=PIL.Image.BICUBIC)
test_arr = img_to_array(test_img)
test_arr = np.expand_dims(test_arr, axis=0)
test_arr /= 255.0

plt.imshow(test_img)
score = model.predict(test_arr)
label = np.argmax(score,axis=1)

print(score)


if label < 0.5:
    print("Abnormal")
else:
    print("Normal")
![Capture.PNG anvil|326x286](upload://uGHCqHFuenPRcKzf3MGbJGjUnC6.png)


import anvil.server

anvil.server.connect(" ...")
 
import anvil.media

@anvil.server.callable
def classify_image(file):
    with anvil.media.TempFile(file) as filename:
        img = load_img(filename)
            
    img = img.resize((W,H), resample=PIL.image.BICUBIC)
    arr = img_to_array(img)
    arr = np.expand_dims(arr, axis=0)
    arr /= 255.0
    
    score= model.predict(arr)
    label = np.argmax(score,axis=1)
    return score, "abnormal" if label < 0.5 else "normal"

(code from my jupyter notebook)
i will really appreciate if someone helps!

Clone link:
share a copy of your app

2

You actually shared a link to run your app rather than to clone it. (You’re not alone.) Please try again to share the clone link. It would help us better diagnose your issue.