deep-high-resolution-net.pytorch

deep-high-resolution-net.pytorch copied to clipboard

When the input is of some size, such as 270x270, the following error will occur.

2

y = y + self.fuse_layers[i][j](x[j]) RuntimeError: The size of tensor a (68) must match the size of tensor b (72) at non-singleton dimension 3

CaoWGG

About the Input Image Size

8

@leoxiaobin Sorry to bother you, I have a question concerning about the size of the input image, it is mentioned in paper as "We extend the human detection box in...

eng100200

wangshicahng

cd ${POSE_ROOT}/lib make?

3

What's wrong?Help! 

angechen

Using latest torch version when i try to train HRNet_FeatureExtractor from modules.feature_extraction, i get following error one of the variables needed for gradient computation has been modified by an inplace...

mohammadalihumayun

how can i run it in win10?

4

asmallcodedog

Hi! I would like to use HRNet for pose estimation with my custom dataset. I have cloned the repository, installed all the required packages from the requirements.txt file, and adjusted...

Priyanshu-Ganwani09

Bumps [opencv-python](https://github.com/opencv/opencv-python) from 3.4.1.15 to 4.8.1.78. Release notes Sourced from opencv-python's releases. 4.8.1.78 OpenCV 4.8.1 release. Important changes: WebP security update for CVE-2023-4863 4.8.0.76 Adds cv2.typing to package. Close #869...

dependabot[bot]

/usr/bin/nvcc -I/home/tl/anaconda3/envs/TL/lib/python3.10/site-packages/numpy/core/include -I/usr/include -I/home/tl/anaconda3/envs/TL/include/python3.10 -c nms_kernel.cu -o build/temp.linux-x86_64-cpython-310/nms_kernel.o -arch=sm_35 --ptxas-options=-v -c --compiler-options '-fPIC' nvcc warning : The 'compute_35', 'compute_37', 'compute_50', 'sm_35', 'sm_37' and 'sm_50' architectures are deprecated, and may be...

LeBronBaldwin

Hello everybody, when trying it your great package on the mpii dataset I get this error (when running train.py like described in the README): ``` Traceback (most recent call last):...

marius-ne