So if I trained my model in kaggle, the requirements must be from kaggle, right?
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
Somebody knows how to solve it?
Oh. How did I not see that. Thanks a ton man. Worked Just fine.
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:
docker build -t fastai-v3 . && docker run --rm -it -p 5000:5000 fastai-v3
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.
Thanks in advance!
Kind regards,
Theodore.
Hi @anurag,
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
Git Repo on dogs and cats breed Render App.
Render App
https://sidpdb-dogs-cats.onrender.com/
Sample Tester, it did classify the dog!!
Moving on to lesson-2…
Amazing! Congratulations on your first live model. This is what makes fast.ai so great: real applications from day 1.
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!
Congratulations on achieving your first milestone! Plenty of more interesting things to come.
On a side note, avoid @ tagging Jeremy unless there is something super urgent.
Hi there,
just a quick question: there is no free option anymore, right? I have to pick the 5$/mo pricing plan for deploying my toy service. Is that correct?
That is correct. Every service deployed on Render is a cost to us, and to build a long term sustainable service we do need to charge for compute resources.
I absolutely understand that. I was just surprised, because Jeremy mentioned in the video that it was free. I guess you guys have updated your pricing as the service matured. That’s totally fine. I just wanted to double-check, in case I missed some kind of voucher link or something.
Ah. Jeremy was probably referring to credits that we gave out prior to public launch. Our beta testers deserved it!
Hello everyone, I am trying to deploy my first classifier on Render.
I decided to install the bear classifier example in the production section of the course first, to reduce any issues I may have when installing my app.
Unfortunately when I press the deploy button on the Render Services page I receive the following error.
Jun 8 06:33:31 AM INFO[0195] RUN python app/server.py
Jun 8 06:33:34 AM Traceback (most recent call last):
File “app/server.py”, line 9, in
from fastai.vision import *
File “/usr/local/lib/python3.7/site-packages/fastai/vision/init.py”, line 3, in
from .learner import *
File “/usr/local/lib/python3.7/site-packages/fastai/vision/learner.py”, line 6, in
from . import models
File “/usr/local/lib/python3.7/site-packages/fastai/vision/models/init.py”, line 2, in
from torchvision.models import ResNet,resnet18,resnet34,resnet50,resnet101,resnet152
File “/usr/local/lib/python3.7/site-packages/torchvision/init.py”, line 1, in
from torchvision import models
File “/usr/local/lib/python3.7/site-packages/torchvision/models/init.py”, line 11, in
from . import detection
File “/usr/local/lib/python3.7/site-packages/torchvision/models/detection/init.py”, line 1, in
from .faster_rcnn import *
File “/usr/local/lib/python3.7/site-packages/torchvision/models/detection/faster_rcnn.py”, line 7, in
from torchvision.ops import misc as misc_nn_ops
File “/usr/local/lib/python3.7/site-packages/torchvision/ops/init.py”, line 1, in
from .boxes import nms, box_iou
File “/usr/local/lib/python3.7/site-packages/torchvision/ops/boxes.py”, line 2, in
from torchvision import _C
ImportError: libcudart.so.9.0: cannot open shared object file: No such file or directory
Jun 8 06:33:35 AM error building image: error building stage: waiting for process to exit: exit status 1
Jun 8 06:33:35 AM error: exit status 1
Does anyone have the solution to this problem or can someone suggest the best approach to solving this issue?
Thanks in advance.smiley:
I was using render too, now i switched over to Google App Engine. There is a tutorial on the course website on it, and not a bad way to make use of the free compute credits Google is providing for free.
Hi,
I am trying to deploy my model on Render, but getting the following error:
File “app/server.py”, line 48, in
learn = loop.run_until_complete(asyncio.gather(*tasks))[0]
File “/usr/local/lib/python3.7/asyncio/base_events.py”, line 584, in run_until_complete
return future.result()
File “app/server.py”, line 35, in setup_learner
learn = load_learner(path, export_file_name)
File “/usr/local/lib/python3.7/site-packages/fastai/basic_train.py”, line 598, in load_learner
state = torch.load(source, map_location=‘cpu’) if defaults.device == torch.device(‘cpu’) else torch.load(source)
File “/usr/local/lib/python3.7/site-packages/torch/serialization.py”, line 387, in load
return _load(f, map_location, pickle_module, **pickle_load_args)
File “/usr/local/lib/python3.7/site-packages/torch/serialization.py”, line 564, in _load
magic_number = pickle_module.load(f, **pickle_load_args)
_pickle.UnpicklingError: invalid load key, ‘<’.
Can anybody help?
I found somewhere that the following line of code should be used for pickle error :
from functools import partial
import pickle
pickle.load = partial(pickle.load, encoding=“latin1”)
pickle.Unpickler = partial(pickle.Unpickler, encoding=“latin1”)
model = torch.load(model_file, map_location=lambda storage, loc: storage, pickle_module=pickle
However now I m getting the following error now:
Jun 11 03:41:50 PM File “app/server.py”, line 17
Jun 11 03:41:50 PM export_file_url = ‘https://drive.google.com/uc?export=download&id=1-pQHp5iT5BiuyBchBq0yBYQIzmsM9is9’
Jun 11 03:41:50 PM ^
Jun 11 03:41:50 PM error building image: error building stage: waiting for process to exit: exit status 1
Jun 11 03:41:50 PM SyntaxError: invalid syntax
Jun 11 03:41:50 PM error: exit status 1
What am I doing wrong? I have followed exactly the same instructions provided?
I had the same error.
Reuploading the model weights to drive/dropbox solved it.
I uploaded my export.pkl file to Google Drive and updated all the requisite libraries to match with the render requirements.txt and was still receiving the error:
_pickle.UnpicklingError: invalid load key, '<'.
After running the docker image locally I finally found the problem was because my .pkl file was over 25Mb. Google Drive prompts large download attempts with a warning page about virus scanning (even using that confirmation link as the download url fails!). The html warning page is downloaded instead
<!DOCTYPE html><html><head><title>Google Drive - Virus scan warning</title>
...
</html>
hence the invalid key <
!
My solution was to upload to Dropbox where I didn’t have any problems…
If you must use Google Drive, use the Drive API:
https://developers.google.com/drive/api/v3/manage-downloads