fix: use cv2 to load image, now compatible with pre-processing model

- Note that the streamlit file_uploader directly takes the bytestream,
not a file name, so we have to convert it instead of just using the
cv2 imread. see https://github.com/streamlit/streamlit/issues/888#issuecomment-568578281
- resolves #1

call_models/entry_and_hotdog.py

@@ -25,6 +25,8 @@ from transformers import AutoModelForImageClassification
 
 # setup for the ML model on huggingface (our wrapper)
 os.environ["PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION"] = "python"
+#classifier_revision = '0f9c15e2db4d64e7f622ade518854b488d8d35e6'
+classifier_revision = 'main' # default/latest version
 # and the dataset of observations (hf dataset in our space)
 dataset_id = "Saving-Willy/Happywhale-kaggle"
 data_files = "data/train-00000-of-00001.parquet"
@@ -221,7 +223,8 @@ if __name__ == "__main__":
     if tab_inference.button("Identify with cetacean classifier"):
         #pipe = pipeline("image-classification", model="Saving-Willy/cetacean-classifier", trust_remote_code=True)
         cetacean_classifier = AutoModelForImageClassification.from_pretrained("Saving-Willy/cetacean-classifier", 
-                                                                            revision='0f9c15e2db4d64e7f622ade518854b488d8d35e6', trust_remote_code=True)
+                                                                            revision=classifier_revision,
+                                                                            trust_remote_code=True)
         
         if st.session_state.image is None:
             # TODO: cleaner design to disable the button until data input done?

call_models/input_handling.py

@@ -6,6 +6,8 @@ import hashlib
 import logging
 
 import streamlit as st
+import cv2
+import numpy as np
 
 m_logger = logging.getLogger(__name__)
 # we can set the log level locally for funcs in this module
@@ -135,7 +137,12 @@ def setup_input(viewcontainer: st.delta_generator.DeltaGenerator=None, _allowed_
 
     if uploaded_filename is not None:
         # Display the uploaded image
-        image = Image.open(uploaded_filename)
+        #image = Image.open(uploaded_filename)
+        # load image using cv2 format, so it is compatible with the ML models
+        file_bytes = np.asarray(bytearray(uploaded_filename.read()), dtype=np.uint8)
+        image = cv2.imdecode(file_bytes, 1)
+
+
         viewcontainer.image(image, caption='Uploaded Image.', use_column_width=True)
         # store the image in the session state
         st.session_state.image = image