Comments (1)
Two most representative models:
- https://github.com/facebookresearch/detectron2/blob/main/configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x.py
*https://github.com/facebookresearch/detectron2/blob/main/configs/COCO-Detection/retinanet_R_50_FPN_1x.py
To run training it should use 2 images per GPU. The configs are made for 8-GPU training and SOLVER.IMS_PER_BATCH
should be changed to 2 for single-GPU case.
Inference benchmark should use the pre-trained models. Random weights don't do the same computation. The model zoo API can help get them easily
https://github.com/facebookresearch/detectron2/blob/master/tools/benchmark.py is an example code that shows how to benchmark detectron2 training with less variance
from benchmark.
Related Issues (20)
- Refactor the t4 and a100 nightly workflows
- [BE] Improve tritonbench handling of built-in metrics
- Flop counter crashes with multiple compiled benchmarks HOT 3
- sam_fast model memory leak HOT 4
- V3 Performance Signal Detected by TorchBench Userbenchmark "torch-nightly" on '2.5.0.dev20240730+cu124' HOT 1
- [tritonbench] Add +/- variance to the latency metric
- Failed TorchAO nightly workflow HOT 2
- Installation issue with python 3.10 on Ubuntu 22.04 HOT 1
- V3 Performance Signal Detected by TorchBench Userbenchmark "torch-nightly" on '2.5.0.dev20240805+cu124' HOT 1
- [torchao] Dashboard numbers are missing even when the workflow is succeeded HOT 14
- [tritonbench] A better way to encode input shapes with parameters
- V3 Performance Signal Detected by TorchBench Userbenchmark "torch-nightly" on '2.5.0.dev20240816+cu124' HOT 1
- V2 Performance Signal Detected by TorchBench CI on '2.5.0.dev20240820+cu124'
- V2 Performance Signal Detected by TorchBench CI on '2.5.0.dev20240821+cu124'
- V2 Performance Signal Detected by TorchBench CI on '2.5.0.dev20240823+cu124'
- V2 Performance Signal Detected by TorchBench CI on '2.5.0.dev20240824+cu124' HOT 1
- V2 Performance Signal Detected by TorchBench CI on '2.5.0.dev20240828+cu124'
- hf_T5_generate torch.complie() failed with latest transformers==4.44.2 HOT 4
- V2 Performance Signal Detected by TorchBench CI on '2.6.0.dev20240913+cu124'
- V2 Performance Signal Detected by TorchBench CI on '2.6.0.dev20240914+cu124'
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 benchmark.