Comments (6)
you can train a resnet50 model and a resnet18 model first,
and then use the KD yaml to train
from centerx.
I have trained a resnet50 model with yamls/coco/centernet_res50_coco_0.5.yaml, but only get a "exp_results/coco/coco_exp_R50_SGD_0.5/inference/instances_predictions.pth", not a model_final.pth file, so what steps am I missing?
from centerx.
Have you end your training? The model_final.pth will be saved when the total training is end
from centerx.
[12/07 10:49:35 d2.utils.events]: eta: 3 days, 1:46:30 iter: 144619 total_loss: 6.227 loss_cls: 4.281 loss_box_wh: 1.738 loss_off_reg: 0.2514 time: 0.3063 data_time: 0.0710 lr: 0.01 max_mem: 4798M
[12/07 10:49:42 d2.utils.events]: eta: 3 days, 1:53:33 iter: 144639 total_loss: 6.227 loss_cls: 4.257 loss_box_wh: 1.671 loss_off_reg: 0.2595 time: 0.3063 data_time: 0.0763 lr: 0.01 max_mem: 4798M
[12/07 10:49:48 d2.utils.events]: eta: 3 days, 1:53:08 iter: 144659 total_loss: 6.302 loss_cls: 4.289 loss_box_wh: 1.86 loss_off_reg: 0.2583 time: 0.3063 data_time: 0.0554 lr: 0.01 max_mem: 4798M
^C[12/07 10:49:48 d2.engine.hooks]: Overall training speed: 144659 iterations in 12:18:32 (0.3063 s / it)
[12/07 10:49:48 d2.engine.hooks]: Total training time: 12:34:44 (0:16:11 on hooks)
[12/07 10:49:48 d2.utils.events]: eta: 3 days, 1:53:07 iter: 144661 total_loss: 6.351 loss_cls: 4.318 loss_box_wh: 1.863 loss_off_reg: 0.2583 time: 0.3063 data_time: 0.0610 lr: 0.01 max_mem: 4798M
I have trained 14w steps, still can not get model_final.pth
from centerx.
It seems you will get model_final after 3 days
It's strange that your loss is too big, and what's your mAP now? It seems you modified the batch size and don't modified the base_lr, what's your yaml ?
This is my log
from centerx.
thanks for your quick reply, I missed the lr reduced by the same times as the batch size from 64 to 8
from centerx.
Related Issues (20)
- 导出onnx之后如何转trt HOT 1
- 请问有没有训练好的权重模型?
- 自定义数据集如何使用该工程 HOT 1
- TypeError: __init__() takes 1 positional argument but 4 were given HOT 1
- TypeError: _write_metrics() missing 1 required positional argument: 'data_time' HOT 2
- AP 大于1?
- 转caffe遇到问题 HOT 2
- 自定义数据集
- 训练问题 HOT 3
- Inference/demo.py的一个小问题 HOT 1
- ttf supported?
- issues HOT 3
- SWA in vanilla Detectron2 HOT 2
- 小白提问请问这个有人体关键点检测嘛
- whyCUDA out of memory. Tried to allocate 130.00 MiB (GPU 1; 7.80 GiB total capacity; 5.91 GiB already allocated; 33.56 MiB free; 6.09 GiB reserved in total by PyTorch)
- 自己数据训练问题
- 关于对于keypoints修改的问题
- 编译detectron2出现ninja: build stopped: subcommand failed如何解决?
- N个数据集所对应的N个教师模型,在datasets中如何摆放N个数据集(每个数据集均转成COCO格式)?
- Requests for segmentation or key point detection. 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 centerx.