Hi guys. @anurag’s intuition was correct. I just added the versions that are installed on my local system (on which the app was working properly ) into the requirements file, as such:
Thanks to your post I managed to deploy and run bear classificator - thanks a lot!)
However, there was a following error in the console during deployment:
May 24 03:29:12 PM INFO: Started server process [1]
May 24 03:29:12 PM INFO: Waiting for application startup.
May 24 03:29:12 PM INFO: Uvicorn running on http://0.0.0.0:5042 (Press CTRL+C to quit)
May 24 03:30:36 PM ModuleNotFoundError: No module named 'numpy.core._multiarray_umath'
May 24 03:30:36 PM ModuleNotFoundError: No module named 'numpy.core._multiarray_umath'
May 24 03:30:36 PM ModuleNotFoundError: No module named 'numpy.core._multiarray_umath'
May 24 03:30:36 PM ModuleNotFoundError: No module named 'numpy.core._multiarray_umath'
I came for the deep learning, but I stay for the software engineering tips! Like Render, which is just fantastic. I’ve now moved three apps from Heroku and the process has been a pleasure. Especially the customer support on Slack which is next level. Highly recommended.
Hello! I stuck with the similar problem. I also have an error messages in log sections at render.com related to Relu activation function (sorry, but I didn’t save the exact text). What is important - that the error was due to the fact that bears model was made using PyTorch v1.0.1 and my model was trained using PyTorch v1.1.0.
here is how I managed to resolve it:
Check what versions of libraries and packages you are using with following command in your Jupyter Notebook:
! pip list
Update requirements.txt in the repo with this information. In my case requirements.txt looks like:
So I got an error like this and I used the requirements from kaggle:
src = LabelLists.load_state(path, state.pop(‘data’))
KeyError: ‘data’
May 26 12:25:09 PM error building image: error building stage: waiting for process to exit: exit status 1
May 26 12:25:09 PM error: exit status 1
I’ve updated requirements.txt in the sample repo to pin all versions. As long as you have the same versions of fastai, torch, and torchvision installed in your Jupyter notebook where you train the model, everything should work as expected.
I’ve also updated the repo README with a command you can run to test your changes locally before deploying on Render:
Hi,I have something wrong in the web. After uploading the image it is stuck at analyzing,I have update the requirements.and I use the bears model you created.It also can’t work normally. How to solve it ?
Hi everyone thank you for the amazing thread! Learning so much from this. @anurag thank you for the wonderful service and support as well!
Wanted to ask if anyone out there has deployed a generative app in render. Nothing fancy to start with just loading an image but getting an image, rather than a class, as output.
Fantastic platform!! Super easy!! I have no first hand experience in any of this, Render platform made it a breeze for me. Thank you very much for the demo repo and replying to all the queries posted here.
As I just started with fastai lesson-1, I went full-cycle following @jeremy’s philosophy of ‘Try it out, get your hands dirty!’. First time every setting and using a Cloud platform (Google in my case), training a CNN deep-learning model and deploying it. I am psyched now
Hi @anurag ,
sorry if it was here and I did not find it…
Is there an example of a deployment on Render of the IMDB lesson? (specifically I would like to deploy a text generator)
Thanks!