SOLIDER-REID
SOLIDER-REID copied to clipboard
tinyvision
Dear cwhgn, I hope this message finds you well. I've been working on training a model for Market1501, but due to hardware limitations, I can't train for 120 epochs in...
2024-05-11 09:36:30 transreid INFO: Namespace(config_file='configs/msmt17/swin_small.yml', opts=['TEST.WEIGHT', './log/msmt17/swin_small/transformer_120.pth', 'TEST.RE_RANKING', 'True', 'MODEL.SEMANTIC_WEIGHT', '0.2']) 2024-05-11 09:36:30 transreid INFO: Loaded configuration file configs/msmt17/swin_small.yml 2024-05-11 09:36:30 transreid INFO: MODEL: PRETRAIN_HW_RATIO: 2 METRIC_LOSS_TYPE: 'triplet' IF_LABELSMOOTH: 'off'...
Tested with torch==1.11.0+cu102 torchvision==0.12.0+cu102
Dear authors, thank you for this amazing work. I'm currently using your codebase, but I would like to use the imagenet SwinTransformer weights as pre-training, instead of the Swin-SOLIDER weights....
Hi I have 2080RTX Ti and the below inference ~tooks 0,019 seconds after warmup . ~ 40 - 50 inference per second. Its look slow. How I can make it...
您好！ 请问怎么样用您的在market上预训练好的模型（swin_small_market.pth）来进行微调呢？ 我根据readme的步骤可以用swin_small.pth来微调，但是将MODEL.PRETRAIN_PATH设为swin_small_market.pth会报错 
I try to run swin_small model, and I have convert_model to teacher model, met an error like fllow: ```shell using img_triplet sampler using Transformer_type: swin_tiny_patch4_window7_224 as a backbone /home/yoyo/G/Ubuntu/PythonProject/Transformer/SOLIDER-REID/model/backbones/swin_transformer.py:1159: UserWarning:...
