Issues
- 0
能对视频进行理解吗?可以对多长的视频文件进行理解
#71 opened by hh-kai - 2
运行infer.py 输入图片后出错
#70 opened by hh-kai - 4
- 1
- 0
在`unicom/examples/`的例子中加上`model.eval()`会得到不同的结果
#19 opened by luoshmg - 0
what is 'cars_annos.mat'?
#17 opened by geshihuazhong - 2
Bug in CombinedMarginLoss implementation
#11 opened by MaroonAmor - 5
- 0
- 2
- 0
scripts for cub/cars
#25 opened by Skyy93 - 2
About kmeans clustering
#20 opened by zheng-xing - 0
未来会公开数据么
#21 opened by vanpersie32 - 3
是否会公开完整训练代码?
#6 opened by KeyaoZhao - 3
- 2
是否会公开image retrieval finetune代码
#18 opened by jyangliu - 5
Pretrained for ViT-S/14 or ViT-S/16
#12 opened by PD-Mera - 1
Training mode
#15 opened by vioanl - 1
- 0
- 2
Inter-class Prototypes
#13 opened by vioanl - 4
ERROR torchrun retrieval.py --batch_size 1 --dataset cub --epochs 1 --gradient_acc 1 --model_name ViT-B/32
#9 opened by fengminxuan - 0
- 0
- 1
行业内得数据集,是否还要用自己的数据集微调一下呢?
#5 opened by God-song - 1
Flattened features of VIT
#2 opened by Alir3za97 - 0