I am trying to deploy an image classification model. The streamlit app runs well locally.
But when I deploy to streamlit cloud, I keep getting errors.
I tried to upload the image model to Github but Github doesn’t allow that upload because of size.
Can you advise what I need to do ? This is my first time deploying streamlit on the cloud.
see logs below:
[08:25:41] 🐍 Python dependencies were installed from /app/maid_poc/requirements.txt using pip.
Check if streamlit is installed
Streamlit is already installed
[08:25:42] 📦 Processed dependencies!
2022-08-10 08:25:56.593542: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory
2022-08-10 08:25:56.593587: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
2022-08-10 08:25:59.332 Uncaught app exception
Traceback (most recent call last):
File "/home/appuser/venv/lib/python3.9/site-packages/streamlit/scriptrunner/script_runner.py", line 557, in _run_script
exec(code, module.__dict__)
File "app.py", line 37, in <module>
model=load_model()
File "/home/appuser/venv/lib/python3.9/site-packages/streamlit/legacy_caching/caching.py", line 573, in wrapped_func
return get_or_create_cached_value()
File "/home/appuser/venv/lib/python3.9/site-packages/streamlit/legacy_caching/caching.py", line 557, in get_or_create_cached_value
return_value = func(*args, **kwargs)
File "app.py", line 33, in load_model
model=tf.keras.models.load_model('mobilemodel3.hdf5')
File "/home/appuser/venv/lib/python3.9/site-packages/keras/utils/traceback_utils.py", line 67, in error_handler
raise e.with_traceback(filtered_tb) from None
File "/home/appuser/venv/lib/python3.9/site-packages/keras/saving/save.py", line 206, in load_model
raise IOError(f'No file or directory found at {filepath_str}')
OSError: No file or directory found at mobilemodel3.hdf5