search

leeyeehoo / CSRNet-pytorch

CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes
642 stars 259 forks source link

Can we use our photos and print density map? #41

Open tang0809 opened 5 years ago

tang0809 commented 5 years ago

Hello, I'm a researcher with my team at NCTU, Taipei, Taiwan. I face a problem. Whenever I want to replace the photos in the dataset with other pictures, I run make_dataset.ipynb on Jupyter Notebook. But the result is wrong, which is still the result of the previous ShaungHi'10 Expo dataset. My method is clear all the photos in the folder "image" , and replace the photos with mine. Can this action problematic?

thank you !

DanielOrtegaCar commented 5 years ago

Do you replace the .mat files also? The jupyter works if you have the image in .jpg format and the ground truth points, in .mat format. The ground_truth file is a tuple (x,y) with the position of the head, to consider in the density map You have to replace the images and the ground_truth file.

Tongzi-Zhang commented 3 months ago

Do you replace the .mat files also? The jupyter works if you have the image in .jpg format and the ground truth points, in .mat format. The ground_truth file is a tuple (x,y) with the position of the head, to consider in the density map You have to replace the images and the ground_truth file.

How to handle the json file？