srikarym / cctv-gun Goto Github PK

Prerequisite

• I have searched the existing and past issues but cannot get the expected help.
• I have read the FAQ documentation but cannot get the expected help.
• The bug has not been fixed in the latest version.

🐞 Describe the bug

When installing via conda, I get the error that none of the packages can be found for the packages in requirements/requirements_cctv_gun.txt

Anaconda says I need to add further channels. Pip install in a virtualenv doesn't work either. I've tried this on a local iMac as well as an AWS GPU instance. This occurs on the first command:
conda create --name myenv --file requirements/requirements_cctv_gun.txt

When I search for the channels on anaconda.org, they show up as under the conda-forge channel which is a channel that's already added.

Environment

I've installed PyTorch 1.13.1 as well as mmcls=0.25.0, mmcv-full=1.7.0 and torch=1.13.0.

The collect_env.py

Additional information

What version of anaconda did you use? I ran everything else according to the requirements file.

I use
ubuntu 20
python 3.10

I have installed these with pip on virtual environment:
mmcv-full=1.7.0
torch=1.13.0
mmcls=0.25.0,

but I get the error:
ModuleNotFoundError: No module named 'mmcv._ext'

I have tested various ways from the net, but the problem still exists

Prerequisite

• I have searched the existing and past issues but cannot get the expected help.
• I have read the FAQ documentation but cannot get the expected help.
• The bug has not been fixed in the latest version.

🐞 Describe the bug

Many thanks for releasing the annotations in CCTV-Gun, this is very realistic data with high-quality labels. Unfortunately, I am having trouble with the instructions for the UCF dataset:

following the instructions for downloading the UCF dataset and running python3 scripts/copy_images_ucf.py produces the error

FileNotFoundError: [Errno 2] No such file or directory: 'data/ucf/frames.json'

frames.json appears to be missing from the repository. What is the correct way to obtain it?

Environment

------------------- --------
contourpy           1.0.7
cycler              0.11.0
fonttools           4.39.2
importlib-resources 5.12.0
kiwisolver          1.4.4
matplotlib          3.7.1
numpy               1.24.2
opencv-python       4.7.0.72
packaging           23.0
Pillow              9.4.0
pip                 22.0.4
pyparsing           3.0.9
python-dateutil     2.8.2
setuptools          58.1.0
six                 1.16.0
zipp                3.15.0

Additional information

No response

how to run the model for testing on a single picture? Thanks!