244 - 299 problem

Hello

ValueError: Input 0 of layer "model_1" is incompatible with the layer: expected shape=(None, 299, 299, 3), found shape=(None, 224, 224, 3)

im sure that my images are 299 299
i also tried :

from nsfw_detector import predict
model = predict.load_model('models/nsfw.299x299.h5')
predict.classify(model, 'test/frames/', 299)

or

from nsfw_detector import predict
model = predict.load_model('models/nsfw.299x299.h5')

# Predict single image
predict.classify(model, 'test/frames/output_0045.jpg', 299)

output :
:38] TF-TRT Warning: Could not find TensorRT
test/frames/output_0045.jpg size: (299, 299)
1/1 [==============================] - 2s 2s/step
[root@server-194-5-205-78 nsfw_model]#

but it did not print the result and only printed images name and , 299 thats all
any trick to solve it ?

Start with the predict.classify calls shown for models/nsfw.299x299.h5 and the 299x299 image paths. Reproduce the shape mismatch and inspect what predict.classify returns or prints, then verify the result is exposed for both a directory and a single image. Done means the 299x299 model accepts the input and classification output is clearly available.

Written by the indexing model from the issue text.