Add Replicate demo and API

[chenxwh]

Hey @KIMGEONUNG! 👋

This pull request makes it possible to run your model inside a Docker environment, which makes it easier for other people to run it. We're using an open source tool called Cog to make this process easier.

This also means we can make a web page where other people can run your model! View it here: https://replicate.com/kimgeonung/bigcolor

Replicate also have an API, so people can easily run your model from their code:

import replicate
model = replicate.models.get(‘kimgeonung/bigcolo’)
model.predict(image=open("test.jpg", "rb"))

Claim your page here so you can edit it, and we'll feature it on our website and tweet about it too.

In case you're wondering who I am, I'm from Replicate, where we're trying to make machine learning reproducible. We got frustrated that we couldn't run all the really interesting ML work being done. So, we're going round implementing models we like. 😊

[KIMGEONUNG]

Thank you for your works! I will check the additional code and merge :) Now I'm personally busy, so it needs time.

[wefyns]

@chenxwh

Not working with the latest version Cog(0.6.1) Error: CUDA 11.0 is not supported by Cog -> fixing by deleting "cuda: "11.0" " from cog.yaml Then #0 12.96 ERROR: Could not find a version that satisfies the requirement torch==1.10.1+cu111 (from versions: 1.4.0, 1.5.0, 1.5.1, 1.6.0, 1.7.0, 1.7.1, 1.8.0, 1.8.1, 1.9.0, 1.9.1, 1.10.0, 1.10.0+cu113, 1.10.1, 1.10.1+cu113, 1.10.2, 1.10.2+cu113, 1.11.0, 1.11.0+cu113, 1.12.0, 1.12.0+cu113, 1.12.1, 1.12.1+cu113, 1.13.0, 1.13.1, 2.0.0) #0 12.96 ERROR: No matching distribution found for torch==1.10.1+cu111 -> fixing by upgrading " - "torch==1.10.1" " to " - "torch==1.8.0" " in cog.yaml

here is fixed cog.yaml

build: gpu: true python_version: "3.8" system_packages: - "libgl1-mesa-glx" - "libglib2.0-0" python_packages: - "numpy==1.21.5" - "torch==1.8.0" - "imageio==2.19.3" - "opencv-python==4.5.5.64" - "torch-ema==0.3" - "timm==0.6.5" - "tensorboard==2.9.1" - "pyyaml==6.0" - "tqdm==4.63.0" - "scikit-image==0.19.3" - "scipy==1.8.1"

run:

• mkdir -p /root/.cache/torch/hub/checkpoints/ && wget --output-document "/root/.cache/torch/hub/checkpoints/tf_efficientnet_l2_ns_475-bebbd00a.pth" "https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/tf_efficientnet_l2_ns_475-bebbd00a.pth"

predict: "predict.py:Predictor"