DM-Count

DM-Count copied to clipboard

Dataloader for UCF-CC-50

4

This is a very great work. Thanks a lot Could you also share the dataloader and experimental setting (like crop size and so on) for dataset UCF-CC-50? Currently, I am...

jingliang95

I'm trying to understand the evaluation procedure that you have used for the ShanghaiTech B dataset. Are you monitoring performance on the test set during training and then selecting the...

adrian-dalessandro

Use of dm-count on less dense smaller images

3

Hello, thanks for the great work! Do you have any advice on how to use your work with smaller images that are not technically crowds but more occlusions of two,...

samymdihi

A bug occurred while running train.py

1

train.py is not running and encounters the following problems. in pytorch 1.2 Traceback (most recent call last): File "C:/Program Files (x86)/DM-Count-master/train.py", line 64, in trainer.train() File "C:\Program Files (x86)\DM-Count-master\train_helper.py", line...

yysube

Hey [@cvlab-stonybrook](https://github.com/cvlab-stonybrook)! 👋 This pull request makes it possible to run your model inside a Docker environment, which makes it easier for other people to run it. We're using an...

vccheng2001

About the ot_loss why optimizing the dual term's derivate instead of the OT distance ?

1

Why setting the optimal target equals the dual term ""s derivate times the prediction instead of the original OT distance? It makes sense to optimize the entire OT loss term...

Lynyanyu

About the min_size, max_size in the preprocess

1

Hi, thanks for this meaningful work. I am wondering how will the min_size, max_size effects the final results or the training process? https://github.com/cvlab-stonybrook/DM-Count/blob/cc5f2132e0d1328909f31b6d665b8e0b15c30467/preprocess/preprocess_dataset_nwpu.py#L99

zhou-rui1

How to reduce the big experiment randomness?

3

Using the code, I observe very big experimental randomness. For example, on QNRF dataset, I obtain results on test set as follows (MAE and MSE): **run 1**: 87.621, 149.75 **run...

jingliang95

you just put the preprocess code in the function train_transform of "Crowd_sh".

12z34x

excellent work

3

I think the idea is very novel and the result is very good. I want to follow your work and use Optimal Transport in another task. But a problem occurs...

purse1996