Comments (3)
I checked my log.txt file for few-shots and in compare with your log.txt, in my files it just run until this line:
[10/02 15:47:08] d2.data.common INFO: Serializing 130 elements to byte tensors and concatenating them all ...
[10/02 15:47:08] d2.data.common INFO: Serialized dataset takes 0.04 MiB
so it don't start evaluation:
[10/02 15:47:14] defrcn.evaluation.evaluator INFO: Start inference on 625 images
Do you know why this happens? i didn't change evaluation file on your code, and when i run it on COCO too, i have this error.
Thanks
from defrcn.
Hi @salehnia, the extract_results.py
extracts results from train&eval logs that are trained and tested correctly (just for easy viewing of the benchmark results). If there is an error in this script, I guess that the (base or novel-ft) models are not being trained or tested properly, please check the logs to make sure that the models have been saved and evaluated normally.
If you find any further issues, please let me know. Thanks!
from defrcn.
Hi thanks for reply...
I checked log.txt, result on base model are exist, train ans test did correct on it, but in few-shot Novels, evaluation didn't start and last line in log.txt is this:
[01/16 13:43:17] d2.data.common INFO: Serialized dataset takes 0.00 MiB
i have CUDA out of memory, my python version is 3.7, detectron2 -> 0.3 and cuda ->10.2
Thanks
from defrcn.
Related Issues (20)
- Question about ground truth boxes which are used in training and PrototypicalCalibrationBlock HOT 4
- How can I customize new hyperparameters in detectron2
- argument 'alpha' must be Number, not NoneType HOT 2
- 可视化
- AssertionError: Checkpoint checkpoints/voc/mydefrcn/defrcn_det_r101_base1/model_reset_remove.pth not found! HOT 6
- Why the different number of images on inference?
- How to reproduce the results in Figure4(b)? HOT 1
- Help with multi-GPU training in Google Colab HOT 1
- Guide on Fine Tuning
- TypeError: init() got an unexpected keyword argument 'first_stride' HOT 2
- Where is pascal VOC metasplit located?
- Out of memory error during evaluation but training works fine! HOT 3
- running Inference on model
- Why final checkpoint is removed in run_voc.sh script? HOT 1
- Do we need to give support image during inference? HOT 1
- cuda version HOT 2
- About the fine tune problems
- main.py: error: unrecognized arguments: --opts MODEL.WEIGHTS /public/home/jd_fky/project/DeFRCN/data/ImageNetPretrained/MSRA/R-101.pkl OUTPUT_DIR checkpoints/coco/defrcn/defrcn_det_r101_base 3 I don't know why running main.py causes this problem HOT 1
- fine-tuning on my cutsomized dataset
- OutOfMemoryError with PrototypicalCalibrationBlock HOT 5
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 defrcn.