Comments (4)
This is expected behavior:
- When you use TensorFlow engine, TensorFlow create native memory. On Java side, we don't have control to make TensorFlow release memory back to system. In general, you won't see system memory usage reduce until you stop the application.
- But this doesn't mean there is memory leak, when close NDArray, TensorFlow will free up internal memory allocation, and reuse the memory to create another NDArray. Usually the total memory will stablize at peak, and won't always increase.
- You need to make sure to close NDArray (or Model, Predictor etc) to ensure no native memory leak.
from djl.
After I execute this method a few more times, the os will crash and jvm will throw an exception of "EXCEPTION_UNCAUGHT-CXX-EXCEPTION (0xe06d7363) at pc=0x00007ffd468c53ac, pid=25956, tid=27768",is this correct?
from djl.
Looks like there is something wrong with your code.
Can you take a look our springboot example: https://github.com/deepjavalibrary/djl-spring-boot-starter-demo. That project doesn't have memory leak issue.
from djl.
I understand what you're saying "But this doesn't mean there is memory leak"!
Now,My question is how to implement memory recycling?The meaning is that when I don't need to use these models, they won't take up native memory.
from djl.
Related Issues (20)
- How works the function EasyTrain.evaluateDataset() ? HOT 2
- Support for Radeon GPUs? HOT 6
- Logistic regression : Accuracy of 1.0 (is there an error in my code ?) HOT 7
- Resource Leak Issue with Files.list in ai.djl.util.Utils HOT 3
- Tokenizer.json compability with jni rust tokenizers - data did not match any variant of untagged enum HOT 2
- Support for FP8 quantization with TensorRT-LLM HOT 2
- 128 dimension face matching algo
- Is there any version of pytorch native library for cudnn9 HOT 2
- Using Llama for inference, some Chinese characters may become garbled
- how to limit OnnxRuntime cpu usage? HOT 1
- 0.27调用tensorflow的pb模型崩溃(可以加载模型,推理时崩溃) HOT 2
- TorchScript inference slower than default torch model HOT 4
- [FATAL] extensions/tokenizers/rust/src/lib.rs crashes the process HOT 1
- CUBLAS_STATUS_NOT_INITIALIZED HOT 7
- How to run FLOAT16 OnnxRuntime models HOT 3
- UnsatisfiedLinkError: 'boolean ai.djl.pytorch.jni.PyTorchLibrary.torchIsContiguous(long)' HOT 2
- How can I implement the Adaline perceptron in DJL
- pytorch-model-zoo: PtSsdTranslator.Builder.self() returns null
- TextEmbeddingTranslator fails with "EngineException: Expected all tensors to be on the same device"
- tensorrt 的demo 有吗 yolov8的
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.