Donglearner
Donglearner
When I INPUT "CUDA_VISIBLE_DEVICES=1 python extract_trar_grid_feature.py --config-file configs/X-152-grid.yaml --dataset coco_2015_test --weight_path ./weight/X-152.pth --output_dir ./data/" to extract from coco test2015.zip jpg. It throws the exception like the following: **raise KeyError( KeyError:...
 When using multiple GPUs to run the code, the code throws the exception like the above picture... Now I did the following modifications: ①in train_egine.py  ②in test_egine.py Just...
Thanks for your timely reply. I will try it now. ---原始邮件--- 发件人: "Ren ***@***.***> 发送时间: 2022年9月29日(星期四) 下午5:09 收件人: ***@***.***>; 抄送: ***@***.******@***.***>; 主题: Re: [rentainhe/TRAR-VQA] --weights_path ./weight/X-152.pth wheredownload? (Issue #2) https://github.com/facebookresearch/grid-feats-vqa...
> > When I INPUT "CUDA_VISIBLE_DEVICES=1 python extract_trar_grid_feature.py --config-file configs/X-152-grid.yaml --dataset coco_2015_test --weight_path ./weight/X-152.pth --output_dir ./data/" to extract from coco test2015.zip jpg. It throws the exception like the following: >...
(pytorch) byd@sbz:~/GraphVQA$ CUDA_VISIBLE_DEVICES=0 python mainExplain_gat.py --log-name debug.log --batch-size=200 --lr_drop=90 Not using distributed mode git: sha: 16da6a024a2e8d050ad9f957449ff0670e9dc804, status: has uncommited changes, branch: master Namespace(data='./', save_dir='./', log_name='debug.log', workers=32, epochs=300, start_epoch=0, batch_size=200, lr=0.0001,...
Epoch: [199][3700/4715] Time 0.19 (0.24) Data 0.00 (0.03) Loss 1.30e-02 (1.34e-02) Acc@Program 0.00 (0.00) Acc@ProgramGroup 0.00 (0.00) Acc@ProgramNonEmpty 0.00 (0.00) Acc@Short 99.50 (99.49) Traceback (most recent call last): File "/home/anaconda3/envs/pytorch/lib/python3.9/site-packages/torch/utils/data/dataloader.py",...
> Just making sure, does this mean that the CPL training configuration files are the same as the CoCoOp training configuration files? Do you run this code successfully?
https://drive.google.com/drive/folders/1IXTsTudZtYLqmKzsXxIZbXfCnys_Izxr Because the file is larger than 20G , so google drive can not download in China. Could scholar provide another download link for it? I want to reproduce the...
The train36.h5py is not built by the method proposed Bottom Up And Top Down. And it also not built by ReGAT model. So how to get the train36.h5py???
现在连链接都是404？