CLIP-IQA
CLIP-IQA copied to clipboard
IceClear
[AAAI 2023] Exploring CLIP for Assessing the Look and Feel of Images
thanks for this excellent work! can you provide the csv file and the txt file for training? thanks in advance.
HI~ Thank you for your work！ I want to train a model that recognizes cars and boats, is the train config and CSV file labeled correctly?
Hi IceClear, I just try to train CLIP-IQA+ on KonIQ-10k as your instruct: ``` python tools/train.py configs/clipiqa/clipiqa_coop_koniq.py ``` But encounter the following error, it seems only PSNR/SSIM supported. Did this...
how to infer image directly not by load image form path ，it means that I just input a image array to the main function not input a image path？
After running this code：output, attributes = restoration_inference(model, os.path.join(args.file_path), return_attributes=True) output and attributes are the same. Why return the same two data? Code running result： >>>>>>>>>>>>>>attributes>>>>>>>>>>>>>>>>>> tensor([[0.9644, 0.3345, 0.9995, 0.0357, 0.2766,...
python tools/train.py configs/clipiqa/clipiqa_coop_koniq.py 2023-10-16 08:47:54,004 - mmedit - INFO - workflow: [('train', 1)], max: 500 iters 2023-10-16 08:47:54,004 - mmedit - INFO - Checkpoints will be saved to C:\Users\pdo-labuser\CLIP-IQA\work_dirs\clipiqa_coop_koniq by...
Hi, Im doing different tests with `demo/clipiqa_single_image_demo.py` and the `attribute_list = ['Quality', 'Brightness', 'Sharpness', 'Noisiness', 'Colorfulness', 'Contrast']`. First, I’ve seen that fitting a good size to the input image is...
Hi IceClear, Thank you for your impressive work! I encounter OOM issue when handle large image with clipiqa_single_image_demo.py, such as 8M/12M pictures. I want to know is there any memery...
Hi @IceClear, Thank you for open sourcing this impressive work! I have a question regarding the `clipiqa_single_image_demo.py` script. When I use this script to do inference on a single image,...
