Comments (3)
@StefanOltmann
I created a PR to use relative jar uri to generate hash. You can use the following model url to avoid multiple cache folder:
.optModelUrls("jar:/META-INF/models/retinaface.zip?ignore_real_uri=true")
from djl.
The model's cache folder is a hash of real jar URL. For example, if your program generate the jar file in the following path: /source/my_app/build/libs/my_app-0.27.0-SNAPSHOT.jar
, the URL will be: jar:file:/source/my_app/build/libs/my_app-0.27.0-SNAPSHOT.jar!/META-INF/models/retinaface.zip
. You got different hash is because, the jar file name (or location) changed 3 times during your development. Did you bump up application version?
from djl.
Yes, with each release I bump up the version.
Can I control where it will be extracted?
This hash will result in additional 100 MB retinaface.pt with every update of my app. That’s not good.
from djl.
Related Issues (20)
- When I build a project supporting DJL in Android Studio, I encounter the following error. How can I resolve it? HOT 3
- Cannot use trained gluonTS model
- Adding ppc64le support for PyTorch engine HOT 4
- Please report location when HuggingFaceTokenizer.newInstance fails with I/O error HOT 11
- How to support paddlepaddle on an aarch64 FT Phytium S2500/64 machine?
- Run tensorflow model on arm architecture HOT 2
- Could not initialize class ai.djl.onnxruntime.engine.0rtNDManager HOT 4
- NDArrays.concat has a different behaviour as np.concatenate HOT 4
- Potential Race Condition or Garbage Collection Issue during JNI Environment Usage HOT 1
- NumberFormatException: Cannot parse null string when loading inside of Docker HOT 1
- Error encountered when predicting with xgboost on Linux arm64 HOT 2
- SIGSEGV calling NDList.encode() HOT 3
- OnnxRuntime 引擎官网案例报错 HOT 9
- Missing Features Exception while inputting the custom dataset.
- Prediction from clip-ViT-B-32-multilingual-v1 incorrectly returns 768 elements rather than 512 HOT 8
- HuggingFace model multilingual-e5-small fails to open on Windows due to max path limitations HOT 4
- support dynamic quantization of pytorch
- Pytorch Engine, LSTM, [W RNN.cpp:982] Warning: RNN module weights are not part of single contiguous chunk of memory. HOT 1
- Contribute to an example for training AirPassengers model HOT 1
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 djl.