elin24 / spdcn-cac

BMVC-2022 paper "Scale-Prior Deformable Convolution for Class-Agnostic Counting"(https://bmvc2022.mpi-inf.mpg.de/313)

Hi there, I'm Wei Lin

• 🔭 I’m currently pursuing the Ph.D degree from Video, Image, and Sound Analysis Lab (VISAL) at the City University of Hong Kong.

🤝🏻  Connect with Me

Email    HomePage

spdcn-cac's Issues

Inference

@Elin24
thanks for this repo and congratulation for being 3rd in Object counting LB.
Could you let me know if you posted some where inference code
secondly, do the boxes are mandatory during training as well as inference ?

mmcv issue

ModuleNotFoundError: No module named 'mmcv._ext'

@Elin24
Any idea on how to resolve this ?
I used your version mentioned for mmcv

can we replace mmcvs with torchvision.ops.DeformConv2d ?

A Error in training

Thank you for your sharing. May I ask that after data preprocessing according to the code you provided, the training program reported an error:
File "/home/counting/SPDCN-CAC-main/datasets/dataset.py", line 56, in getSample
dotmap[0, points[:, 1], points[:, 0]] = 1
IndexError: index 384 is out of bounds for axis 1 with size 384

How can i use

Hello! I have done all the steps, but how can I include the image I want in the code to process it? You didn't write this part.

demo.ipynb

Following your instructions, I used the script "demo.ipynb" for testing, but the test results are faulty.

Program syntax error

Why did I encounter this error while running gendata384x576. py

File "gendata384x576.py", line 80, in
category = cates[imid]
KeyError: '1050'