Converting TensorFlow Model to TensorFlow Lite (TFLite) - Human Emotions Detection

[@markkitur5326]

Kindly explain deeply on the part of runtime

[@felipecosta-pn1he]

I was doing the same step-by-step since the creation of the model, when I run the cell with: interpreter = tflite.Interpreter(model_path='/content/tflite/quantized_model/tflite_quantized_model.tflite') interpreter.allocate_tensors() input_details = interpreter.get_input_details()[0] output_details = interpreter.get_output_details()[0] interpreter.set_tensor(input_details['index'], test_image) interpreter.invoke() output = interpreter.get_tensor(output_details['index'])[0] This cell only runs when I resize the image dimension to (1, 1), more exactly -> interpreter.set_tensor(input_details['index'], test_image) Is there any idea about what is wrong?

[@neuralearn]

Hello Felipe, you have been granted access to the Notebook. Please after rerunning with the Notebook, let us know if you still face issues.

[@felipecosta-pn1he]

@@neuralearn Thanks!!!

[@neuralearn]

You're welcome :)

[@vanbap]

i face the same issue: exact image input shape in trained model .h5 is (1 , 224 , 224 , 3) but after converting to tflite, " input_details[0]['shape'] " gives me input shape: ( 1, 1, 1, 3) which is wrong. Could u help me ?