Expected str, bytes or os.PathLike object, not Sequential

Deployment
1

I am trying to deploy my Image Classification model and facing this issue while reading the selected image.

Code snippet:

def prediction(model):
    image_file = st.file_uploader("Choose a bird image..", type="jpg")
    if(image_file is not None): 
        image = Image.open(image_file)
        st.image(image, width=40, caption='Uploaded bird image', use_column_width=True)
        np_image = np.array(image).astype('float32')/255
        np_image = transform.resize(np_image, (224, 224, 3))
        np_image = np.expand_dims(np_image, axis=0)
        model = load_model(model)
        prediction = model.predict(img.reshape(1,224,224,3))
                
        if(np.argmax(prediction)==0.0):
            st.write('According to Model, it can be: COVID-19 with an Accuracy of {0:.2f}%'.format(np.max(prediction)*100))
        elif(np.argmax(prediction)==1.0):
            st.write('According to Model, it can be: Normal with an Accuracy of {0:.2f}%'.format(np.max(prediction)*100))
        elif(np.argmax(prediction)==2.0):
            st.write('According to Model, it can be: Pneumonia with an Accuracy of {0:.2f}%'.format(np.max(prediction)*100))

I executed the same code a month ago, and it worked fine—Donno why I am facing this error now.

Debug info

  • Streamlit version: 0.72.0
  • Python version: Python 3.7.5
  • Tensorflow Version: tensorflow==2.4.1
  • Keras Version: Keras==2.3.1
  • Using IDLE
  • OS version: Windows
  • Browser version: Chrome
2

Hi @Snehit_Vaddi -

Can you post the actual traceback, so I can see what line in the code Python is complaining about?

Best,
Randy