Comments (5)
@chauhang : Looks like you missed cloning the serve repo inside the docker directory before running the docker build command.
Since torchserve is currently not available in PyPi as a python package, we are currently installing by cloning the repo in docker.
Steps from Readme :
cd serve/docker
git clone https://github.com/pytorch/serve.git
cp <path_to_resnet-18_MAR_file> .
docker build -t torchserve:1.0 .
Could you please verify?
from serve.
Thanks @harshbafna Missed the step for git clone inside docker. Was able to proceed after this. Also the step for copying the resnet-16.mar is not optional, docker build fails with below error if the file is not present:
Step 16/24 : COPY resnet-18.mar /home/model-server/model-store/resnet-18.mar
COPY failed: stat /var/lib/docker/tmp/docker-builder165363248/resnet-18.mar: no such file or directory
from serve.
@chauhang : Thanks for pointing this out. Will update the documentation.
from serve.
@chauhang Can you please confirm?
from serve.
Thanks, verified.
from serve.
Related Issues (20)
- Torchserve Error: number of batch response mismatched HOT 9
- The workers works in parallelism? HOT 7
- Instructions and installation for inf2 instances are broken HOT 3
- Auto recovery failed when killing TorchServe worker processes HOT 2
- Nightly cpu benchmark failed HOT 1
- Nightly cpu benchmark failed HOT 1
- Docker Regression on ubuntu-20.04 failed HOT 1
- Docker Regression on Array failed HOT 1
- Docker Regression on ubuntu-20.04 failed HOT 1
- Docker Regression on Array failed HOT 1
- Service build successfully with Docker, but not run on GPU HOT 1
- Difference between `Custom handler with module level entry point` and `Custom handler with class level entry point` HOT 2
- Setting log level of handler HOT 2
- How can I implement batch inference in my model? HOT 5
- Low GPU utilization due to CPU-bound preprocessing HOT 2
- How torchserve uses grpc in java HOT 2
- Can i use multiple workers in single GPU? HOT 4
- How to use torchserve metrics HOT 1
- Create CPP release artifacts
- Add script to recreate unit test artifacts
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from serve.