Since we’re talking about deployment … I’m hoping someone can provide some insight into why I’m getting this error when I call learn.predict(img_bytes) in my FastAPI/Starlette project:
I’m using version 0.0.15 and the code is pretty much the same as reference examples from last week. Been wrestling with this for several days but I’m at wits end as to what is going on. I have noticed that other folks are seeing the same
File "/Users/admin/Development/_tools/anaconda/envs/fastapi_test_app/lib/python3.7/site-packages/fastai2/torch_core.py", line 213, in to_concat
if is_listy(xs[0]): return type(xs[0])([to_concat([x[i] for x in xs], dim=dim) for i in range_of(xs[0])])
IndexError: list index out of range
… error in other places, so maybe its related.
Thanks much!