Simon Mo
Simon Mo
We use adaptive batching to figure out the optimal batch size for a model. So the input to your function should be a list of str instead of just a...
We should. Can you submit a PR?
Hi Thanks for raising this issue. The import error is because the script is importing `architecture.py` and `architecture.py` is importing `block.py`. Cloupickle (package we use to serialize function) is not...
Also http://clipper.ai/tutorials/custom_model_container/ On Fri, Jan 4, 2019 at 10:33 AM Sungjun.Kim wrote: > Hello, @voodoohop . Happy new year! > First of all, thank you for your error report. Clipper...
To be a bit more clear, if you are building custom container, you don’t need to consolidate the files because when building custom containers, you can just copy the files...
is it possible to push `superresolution-model:1`to the dockerhub? To do that, - `docker tag superresolution-model:1 /superresolution-model:1
The issue is opencv: ``` Traceback (most recent call last): File "", line 1, in File "/usr/local/lib/python3.6/site-packages/cloudpickle/cloudpickle.py", line 908, in subimport __import__(name) File "/usr/local/lib/python3.6/site-packages/cv2/__init__.py", line 3, in from .cv2 import...
Not yet. I have to go inside the container and try to load the function myself to see the issue. To do that, I did: ``` docker run -it --entrypoint...
The returned type need to be a list of strings. Not dataframe type. On Wed, Jul 17, 2019 at 11:23 PM Sungjun.Kim wrote: > Hi, @kiraseed . > I think...
@rkooo567 added. try follow the instruction at https://github.com/ucbrise/clipper-website