Comments (3)
from tsd.
Hi, the eval info per epoch should be given if you correctly give the configuration and you can also evaluate the performance through the offline manner.
The first thing to determine is whether the base model is appropriate for your training set. If your dataset is completely different from COCO, the default configuration of anchor maybe not appropriate for your training set.
If the base model can perform a satisfactory performance on your own dataset, TSD can steadily further improve performance.
If there still exists the problem for TSD, you can provide more experimental details.
from tsd.
./tools/dist_train.sh configs/faster_rcnn_x101_64x4d_fpn_TSD.py 8 --validate
from tsd.
Related Issues (20)
- Can TSD head be used on top of RetinaNet? HOT 5
- Some questions about TSD_cls and TSD_bbox HOT 9
- Question about how to set finest_scale value? HOT 2
- mmcv version HOT 2
- Why the rcnn score_thr is set 0.00 in all TSD configs?
- Should not overwrite two_stage.py HOT 1
- Spatial sensitive heatmap HOT 4
- DDP problem when migrate TSD to mmdet2.0
- How to illustrate the heatmap thermal diagram? HOT 1
- KeyError: 'TSDSharedFCBBoxHead is not in the head registry' HOT 1
- Missing 'model.CLASSES' field in the pre-trained model for the open images dataset HOT 3
- I transfer the code to mmdetection v2.0, but the result is much worse than general training pipeline. What might be the reason? HOT 3
- RuntimeError: cuda runtime error (11) : invalid argument at mmdet/ops/nms/src/nms_kernel.cu:111
- Open-Images datasets HOT 1
- TypeError "forward() missing 2 required positional arguments: 'feats' and 'rois'" in pytorch2onnx HOT 1
- Question about OpenImages evaluation
- Could you share the training log and evaluation script?
- How to use it with A100 Gpus?
- TypeError: FasterRCNN: __init__() got an unexpected keyword argument 'bbox_roi_extractor' HOT 1
- Welcome update to OpenMMLab 2.0
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 tsd.