niki-amini-naieni / countx Goto Github PK
View Code? Open in Web Editor NEWIncludes FSC-147-D and the code for training and testing the CounTX model from the paper Open-world Text-specified Object Counting.
License: MIT License
Includes FSC-147-D and the code for training and testing the CounTX model from the paper Open-world Text-specified Object Counting.
License: MIT License
Nice work!
Thanks for sharing the code!
with your train command:
the result are
val:Test MAE: 21.80, Test RMSE: 73.82
test:Test MAE: 20.23, Test RMSE: 106.87
with cuda 11.8 torch 2.0.0 GPU 4090
In you code, the MAE and RMSE for the validation set was Calculated for each epoch. but, I change it into every 20 epochs
and the batch size was set to 48, 1000 epochs.
For reproducing your accuracy, should I change the batch size into 8, and Calculate MAE and RMSE for each epoch?
So far, I followed the instructions in setting up the environment and completing the preparation steps.
Now, I am trying to run inference. I assume I have to change --im_dir
, --FSC147_anno_file
, and --data_split_file
, but am facing problems understanding what --FSC147_anno_file
and --data_split_file
are referring to and where I can get them.
Are these files that happen to be generated during training? I wanted to use the existing baseline model for inference rather than training.
python test.py --data_split "val" --output_dir "./test" --resume "./results/checkpoint-1000.pth" --img_dir "/scratch/local/hdd/nikian/images_384_VarV2" --FSC147_anno_file "/scratch/local/hdd/nikian/annotation_FSC147_384.json" --FSC147_D_anno_file "./FSC-147-D.json" --data_split_file "/scratch/local/hdd/nikian/Train_Test_Val_FSC_147.json"
This repository uses timm==0.3.2, for which a fix is needed to work with PyTorch 1.8.1+. This fix can be implemented by replacing the file timm/models/layers/helpers.py in the timm codebase with the file helpers.py provided in this repository.
how can i change this one, please help me trough
Thank you for your excellent work, could you please provide the test code of CounTX on the CARPK dataset?
Thanks for the interesting insights!
Will you be releasing the code and CLIP model weight soon? Thanks in advance!
Hello author!
Thank you very much for your contribution to the scientific research industry. Now, while running your code, in line 126 of modelscounting network.py, the variables img tokens [8512] and fim pos embedded [l, 196512] are "img_tokens=img_tokens+self. fim pos embedded"., Shape mismatch will result in an error message
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.