Comments (13)
Could send me your training log?
from fewx.
Could send me your training log?
I do not train the model I just test it on coco val use the weight you provided.
from fewx.
Could send me your training log?
the code I run has been send to you email.
from fewx.
What's your detectron2 version?
from fewx.
What's your detectron2 version?
0.3
from fewx.
Please try this one to install detectron2 0.1 version
python -m pip install detectron2 -f \
https://dl.fbaipublicfiles.com/detectron2/wheels/cu101/torch1.5/index.html
from fewx.
Please try this one to install detectron2 0.1 version
python -m pip install detectron2 -f \ https://dl.fbaipublicfiles.com/detectron2/wheels/cu101/torch1.5/index.html
YOU install MD said that recommend the Pre-Built Detectron2 (Linux only) version with pytorch 1.5. I use the Pre-Built Detectron2 with CUDA 10.1 and pytorch 1.5. and I found detectron2 V0.1 just for pytorch 1.4 and use python -m pip install detectron2 -f
https://dl.fbaipublicfiles.com/detectron2/wheels/cu101/torch1.5/index.html can just install V0.3.
from fewx.
Please try this one to install detectron2 0.1 version
python -m pip install detectron2 -f \ https://dl.fbaipublicfiles.com/detectron2/wheels/cu101/torch1.5/index.html
I can just use V0.1.3 and meet /workspace/FewX-master/fewx/modeling/fsod/fsod_roi_heads.py in ()
8
9 from detectron2.config import configurable
---> 10 from detectron2.layers import ShapeSpec, nonzero_tuple
11 from detectron2.structures import Boxes, ImageList, Instances, pairwise_iou
12 from detectron2.utils.events import get_event_storage
ImportError: cannot import name 'nonzero_tuple'
from fewx.
I tried the evaluation again and I can get the reported number.
[12/30 18:13:39 fewx.evaluation.coco_evaluation]: Preparing results for COCO format ...
[12/30 18:13:39 fewx.evaluation.coco_evaluation]: Saving results to ./output/fsod/finetune_dir/R_50_C4_1x/inference/coco_instances_results.json
[12/30 18:13:39 fewx.evaluation.coco_evaluation]: Evaluating predictions ...
Loading and preparing results...
DONE (t=0.13s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
COCOeval_opt.evaluate() finished in 10.44 seconds.
Accumulating evaluation results...
COCOeval_opt.accumulate() finished in 1.24 seconds.
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.030
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.056
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.029
Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.007
Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.031
Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.052
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.047
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.066
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.066
Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.009
Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.059
Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.114
[12/30 18:13:51 fewx.evaluation.coco_evaluation]: Evaluation results for bbox:
| AP | AP50 | AP75 | APs | APm | APl |
|:-----:|:------:|:------:|:-----:|:-----:|:-----:|
| 2.989 | 5.592 | 2.948 | 0.724 | 3.057 | 5.165 |
[12/30 18:13:51 fewx.evaluation.coco_evaluation]: Evaluation results for VOC 20 categories =======> AP : 11.95
[12/30 18:13:51 fewx.evaluation.coco_evaluation]: Evaluation results for VOC 20 categories =======> AP50: 22.37
[12/30 18:13:51 fewx.evaluation.coco_evaluation]: Evaluation results for VOC 20 categories =======> AP75: 11.79
[12/30 18:13:51 fewx.evaluation.coco_evaluation]: Evaluation results for VOC 20 categories =======> APs : 2.89
[12/30 18:13:51 fewx.evaluation.coco_evaluation]: Evaluation results for VOC 20 categories =======> APm : 12.23
[12/30 18:13:51 fewx.evaluation.coco_evaluation]: Evaluation results for VOC 20 categories =======> APl : 20.66
from fewx.
I tried the evaluation again and I can get the reported number.
[12/30 18:13:39 fewx.evaluation.coco_evaluation]: Preparing results for COCO format ... [12/30 18:13:39 fewx.evaluation.coco_evaluation]: Saving results to ./output/fsod/finetune_dir/R_50_C4_1x/inference/coco_instances_results.json [12/30 18:13:39 fewx.evaluation.coco_evaluation]: Evaluating predictions ... Loading and preparing results... DONE (t=0.13s) creating index... index created! Running per image evaluation... Evaluate annotation type *bbox* COCOeval_opt.evaluate() finished in 10.44 seconds. Accumulating evaluation results... COCOeval_opt.accumulate() finished in 1.24 seconds. Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.030 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.056 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.029 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.007 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.031 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.052 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.047 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.066 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.066 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.009 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.059 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.114 [12/30 18:13:51 fewx.evaluation.coco_evaluation]: Evaluation results for bbox: | AP | AP50 | AP75 | APs | APm | APl | |:-----:|:------:|:------:|:-----:|:-----:|:-----:| | 2.989 | 5.592 | 2.948 | 0.724 | 3.057 | 5.165 | [12/30 18:13:51 fewx.evaluation.coco_evaluation]: Evaluation results for VOC 20 categories =======> AP : 11.95 [12/30 18:13:51 fewx.evaluation.coco_evaluation]: Evaluation results for VOC 20 categories =======> AP50: 22.37 [12/30 18:13:51 fewx.evaluation.coco_evaluation]: Evaluation results for VOC 20 categories =======> AP75: 11.79 [12/30 18:13:51 fewx.evaluation.coco_evaluation]: Evaluation results for VOC 20 categories =======> APs : 2.89 [12/30 18:13:51 fewx.evaluation.coco_evaluation]: Evaluation results for VOC 20 categories =======> APm : 12.23 [12/30 18:13:51 fewx.evaluation.coco_evaluation]: Evaluation results for VOC 20 categories =======> APl : 20.66
you env is pytorch 1.5 . detectron2 v0.31 ? just run all.sh can get the result?
from fewx.
I tried the evaluation again and I can get the reported number.
[12/30 18:13:39 fewx.evaluation.coco_evaluation]: Preparing results for COCO format ... [12/30 18:13:39 fewx.evaluation.coco_evaluation]: Saving results to ./output/fsod/finetune_dir/R_50_C4_1x/inference/coco_instances_results.json [12/30 18:13:39 fewx.evaluation.coco_evaluation]: Evaluating predictions ... Loading and preparing results... DONE (t=0.13s) creating index... index created! Running per image evaluation... Evaluate annotation type *bbox* COCOeval_opt.evaluate() finished in 10.44 seconds. Accumulating evaluation results... COCOeval_opt.accumulate() finished in 1.24 seconds. Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.030 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.056 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.029 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.007 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.031 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.052 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.047 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.066 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.066 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.009 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.059 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.114 [12/30 18:13:51 fewx.evaluation.coco_evaluation]: Evaluation results for bbox: | AP | AP50 | AP75 | APs | APm | APl | |:-----:|:------:|:------:|:-----:|:-----:|:-----:| | 2.989 | 5.592 | 2.948 | 0.724 | 3.057 | 5.165 | [12/30 18:13:51 fewx.evaluation.coco_evaluation]: Evaluation results for VOC 20 categories =======> AP : 11.95 [12/30 18:13:51 fewx.evaluation.coco_evaluation]: Evaluation results for VOC 20 categories =======> AP50: 22.37 [12/30 18:13:51 fewx.evaluation.coco_evaluation]: Evaluation results for VOC 20 categories =======> AP75: 11.79 [12/30 18:13:51 fewx.evaluation.coco_evaluation]: Evaluation results for VOC 20 categories =======> APs : 2.89 [12/30 18:13:51 fewx.evaluation.coco_evaluation]: Evaluation results for VOC 20 categories =======> APm : 12.23 [12/30 18:13:51 fewx.evaluation.coco_evaluation]: Evaluation results for VOC 20 categories =======> APl : 20.66
I find the problem..... In your all.sh you do delete the ./support_dir/support_feature.pkl which inference needed ... plz delete it in your all.sh and plz delete the code self.logger.info("===========inference call===========") in your fewx/modeling/fsod/fsod_rcnn.py
340
from fewx.
I tried the evaluation again and I can get the reported number.
[12/30 18:13:39 fewx.evaluation.coco_evaluation]: Preparing results for COCO format ... [12/30 18:13:39 fewx.evaluation.coco_evaluation]: Saving results to ./output/fsod/finetune_dir/R_50_C4_1x/inference/coco_instances_results.json [12/30 18:13:39 fewx.evaluation.coco_evaluation]: Evaluating predictions ... Loading and preparing results... DONE (t=0.13s) creating index... index created! Running per image evaluation... Evaluate annotation type *bbox* COCOeval_opt.evaluate() finished in 10.44 seconds. Accumulating evaluation results... COCOeval_opt.accumulate() finished in 1.24 seconds. Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.030 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.056 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.029 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.007 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.031 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.052 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.047 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.066 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.066 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.009 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.059 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.114 [12/30 18:13:51 fewx.evaluation.coco_evaluation]: Evaluation results for bbox: | AP | AP50 | AP75 | APs | APm | APl | |:-----:|:------:|:------:|:-----:|:-----:|:-----:| | 2.989 | 5.592 | 2.948 | 0.724 | 3.057 | 5.165 | [12/30 18:13:51 fewx.evaluation.coco_evaluation]: Evaluation results for VOC 20 categories =======> AP : 11.95 [12/30 18:13:51 fewx.evaluation.coco_evaluation]: Evaluation results for VOC 20 categories =======> AP50: 22.37 [12/30 18:13:51 fewx.evaluation.coco_evaluation]: Evaluation results for VOC 20 categories =======> AP75: 11.79 [12/30 18:13:51 fewx.evaluation.coco_evaluation]: Evaluation results for VOC 20 categories =======> APs : 2.89 [12/30 18:13:51 fewx.evaluation.coco_evaluation]: Evaluation results for VOC 20 categories =======> APm : 12.23 [12/30 18:13:51 fewx.evaluation.coco_evaluation]: Evaluation results for VOC 20 categories =======> APl : 20.66
after motify the result I can get below.
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.019
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.035
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.019
Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.000
Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.009
Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.041
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.036
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.041
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.041
Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.000
Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.013
Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.096
[12/31 01:46:01 fewx.evaluation.coco_evaluation]: Evaluation results for bbox:
AP | AP50 | AP75 | APs | APm | APl |
---|---|---|---|---|---|
1.939 | 3.469 | 1.948 | 0.015 | 0.889 | 4.124 |
[12/31 01:46:01 fewx.evaluation.coco_evaluation]: Evaluation results for VOC 20 categories =======> AP : 7.75 | |||||
[12/31 01:46:01 fewx.evaluation.coco_evaluation]: Evaluation results for VOC 20 categories =======> AP50: 13.88 | |||||
[12/31 01:46:01 fewx.evaluation.coco_evaluation]: Evaluation results for VOC 20 categories =======> AP75: 7.79 | |||||
[12/31 01:46:01 fewx.evaluation.coco_evaluation]: Evaluation results for VOC 20 categories =======> APs : 0.06 | |||||
[12/31 01:46:01 fewx.evaluation.coco_evaluation]: Evaluation results for VOC 20 categories =======> APm : 3.56 | |||||
[12/31 01:46:01 fewx.evaluation.coco_evaluation]: Evaluation results for VOC 20 categories =======> APl : 16.50 |
from fewx.
I know that the model generates 100 BBoxes for each class, but when I predicted that only dozens of BBoxes were generated for each class. Why not 100 and how to solve this problem?
from fewx.
Related Issues (20)
- confused about `dataset_dict` in `FewX/fewx/data/dataset_mapper.py` HOT 1
- ============ Few-shot object detetion will start. ============= HOT 3
- How to train an own model
- ValueError: Unsupported type found in checkpoint! res4_avg: <class 'dict'> HOT 1
- About query images and support images HOT 2
- random seed
- RuntimeErroe HOT 1
- Is FSVOD code available? HOT 2
- Can I train directly with VOC dataset?
- 元学习or两阶段微调 HOT 1
- About the test result
- KeyError: 'id' HOT 1
- code of cpmask
- Low performances/Wrong boxes fix
- Thanks for your great work, could you please release the code of your paper《Few-Shot Object Detection with Model Calibration》??
- The question about the 'first_stride' HOT 3
- RuntimeError: NCCL error in: /pytorch/torch/lib/c10d/ProcessGroupNCCL.cpp:32, unhandled cuda error, NCCL version 2.4.8
- episodes的训练策略
- FSVOD dataset is incomplete HOT 1
- How to understand the instruction in the step 3 when i have only 2 gpus? 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 fewx.