Regarding accuracy mentioned in the paper on Chest X-ray14 dataset for different label percentage

[MdJunaidMahmood]

Hi, It was a nice experience reading your research work and browsing through the corresponding code. I tried running the code on Chest X-ray14 dataset for different labelled set training percentages. However, for every case, I am getting an accuracy that is 1% to 3% less than the accuracy mentioned in the paper. I wanted to ask whether the accuracies that you have mentioned are maximum accuracy that you have got during your work or is it average of accuracies that you got across multiple runs. In addition, I request you to tell whether there are some changes that needs to be done in the code to achieve the similar results.

Thanks!

[ttasb]

代码出错，能不能告诉我下怎么解决求求大佬了，907556021@qq.com File "main.py", line 48, in main() File "main.py", line 20, in main mp.spawn(main_worker, nprocs=ngpus_per_node, args=(ngpus_per_node, args)) File "D:\anaconda3\envs\ACPL2\lib\site-packages\torch\multiprocessing\spawn.py", line 230, in spawn return start_processes(fn, args, nprocs, join, daemon, start_method='spawn') File "D:\anaconda3\envs\ACPL2\lib\site-packages\torch\multiprocessing\spawn.py", line 188, in start_processes while not context.join(): File "D:\anaconda3\envs\ACPL2\lib\site-packages\torch\multiprocessing\spawn.py", line 150, in join raise ProcessRaisedException(msg, error_index, failed_process.pid) torch.multiprocessing.spawn.ProcessRaisedException:

-- Process 0 terminated with the following error: File "D:\ACPL代码\ACPL-main1\pl_utils.py", line 63, in build_local_graph D_ulf, I_ulf = gpu_index_ulf.search(u_embed, args.topk) File "D:\anaconda3\envs\ACPL2\lib\site-packages\faiss__init__.py", line 286, in replacement_search n, d = x.shape ValueError: not enough values to unpack (expected 2, got 1)