Comments (7)
Hey, I had a question about what training methodology was used to pre-train the yolox baseline models. I added the images from DET dataset with similar classes as the VID dataset and trained yolox-s model but I was not able to replicate your results. So could you elaborate on how you pretrained the yolox model?
Thanks for your attention. May I ask how many images you sampled from the VID dataset and can you please share the training log for debugging? We release our training annotation link for the baseline model in the README.MD file which contains 1/10 VID images and all DET images with the same classes. You can try this one and we are eager for your response.
from yolov.
Besides, do you use the coco pre-trained model for finetuning?
from yolov.
I sampled all the images from VID dataset and all the images from the DET dataset that has the same classes. Yes I used coco pre-trained model for finetuning. I am getting an mAP score of around 0.56 when validating on the entire VID dataset.
these are the training logs
╒══════════════════╤═══════════════════════════════╕
│ keys │ values │
╞══════════════════╪═══════════════════════════════╡
│ seed │ None │
├──────────────────┼───────────────────────────────┤
│ output_dir │ './imagenet_det_vid_baseline' │
├──────────────────┼───────────────────────────────┤
│ print_interval │ 20 │
├──────────────────┼───────────────────────────────┤
│ eval_interval │ 1 │
├──────────────────┼───────────────────────────────┤
│ num_classes │ 30 │
├──────────────────┼───────────────────────────────┤
│ depth │ 0.33 │
├──────────────────┼───────────────────────────────┤
│ width │ 0.5 │
├──────────────────┼───────────────────────────────┤
│ data_num_workers │ 4 │
├──────────────────┼───────────────────────────────┤
│ input_size │ (576, 576) │
├──────────────────┼───────────────────────────────┤
│ random_size │ (18, 32) │
├──────────────────┼───────────────────────────────┤
│ train_ann │ 'vid_det_train.json' │
├──────────────────┼───────────────────────────────┤
│ val_ann │ 'vid_det_val.json' │
├──────────────────┼───────────────────────────────┤
│ degrees │ 10.0 │
├──────────────────┼───────────────────────────────┤
│ translate │ 0.1 │
├──────────────────┼───────────────────────────────┤
│ scale │ (0.1, 2) │
├──────────────────┼───────────────────────────────┤
│ mscale │ (0.8, 1.6) │
├──────────────────┼───────────────────────────────┤
│ shear │ 2.0 │
├──────────────────┼───────────────────────────────┤
│ perspective │ 0.0 │
├──────────────────┼───────────────────────────────┤
│ enable_mixup │ True │
├──────────────────┼───────────────────────────────┤
│ warmup_epochs │ 1 │
├──────────────────┼───────────────────────────────┤
│ max_epoch │ 30 │
├──────────────────┼───────────────────────────────┤
│ warmup_lr │ 0 │
├──────────────────┼───────────────────────────────┤
│ basic_lr_per_img │ 1.5625e-05 │
├──────────────────┼───────────────────────────────┤
│ scheduler │ 'yoloxwarmcos' │
├──────────────────┼───────────────────────────────┤
│ no_aug_epochs │ 2 │
├──────────────────┼───────────────────────────────┤
│ min_lr_ratio │ 0.05 │
├──────────────────┼───────────────────────────────┤
│ ema │ True │
├──────────────────┼───────────────────────────────┤
│ weight_decay │ 0.0005 │
├──────────────────┼───────────────────────────────┤
│ momentum │ 0.9 │
├──────────────────┼───────────────────────────────┤
│ exp_name │ 'yolox_s_mix_det' │
├──────────────────┼───────────────────────────────┤
│ test_size │ (576, 576) │
├──────────────────┼───────────────────────────────┤
│ test_conf │ 0.001 │
├──────────────────┼───────────────────────────────┤
│ nmsthre │ 0.6 │
╘══════════════════╧═══════════════════════════════╛
from yolov.
sampled all the images from VID dat
Please follow our instructions and try it again.
from yolov.
My bad, I used 1/10 from VID dataset and all images from DET dataset, sorry that was a typo
from yolov.
My bad, I used 1/10 from VID dataset and all images from DET dataset, sorry that was a typo
Could you please use our annotations and try it again and keep all of other settings the same as this repo. We find that aug setting in this log has been changed (e.g. 30 epochs are too much for the small model, we use 7 by default). Hopefully, we can find out the reason.
from yolov.
@mukundkhanna123 Can you give me your small dataset from VID, the VID is hard for us to download .Thank you!!!
from yolov.
Related Issues (20)
- release backbone
- Question about the implementation of proposed A.P. HOT 2
- Questions about reproducing results on VID HOT 4
- How "use_time_emd" works? HOT 2
- Can you tell me how to solve this problem? I use a new model and pre trained weights yolov++to train my dataset HOT 4
- v++ 模型转onnx HOT 3
- 训练自己的数据集 HOT 11
- 修改基础检测器
- 大佬,训练的模型可以给一个百度网盘的链接么? HOT 4
- About vid_demo.py
- Regarding the FAM and FSM modules you proposed
- about FAM and FSM
- Error using vid_demo.py HOT 1
- 训练自己数据集
- Problem with vid_demo.py with cpu HOT 1
- 如何训练yolov_x_online的模型 HOT 4
- The problem of using yolov's algorithm ideas in yolov5/v7 HOT 3
- vid_demo.py after running, detected video as same as the original video. HOT 6
- 请问下如何改进静态目标检测器使其更适合于视频目标检测? HOT 1
- run online mode with yolov++ 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 yolov.