JosephChen

The baseline of ResNet18 on CIFAR100 is relatively lower

3

Hi, I would first appreciate your work for interpreting the relationship between the KD and LSR. However, the baseline of ResNet18 on cifar100 is much lower than the implementation [pytorch-cifar100](https://github.com/weiaicunzai/pytorch-cifar100),...

I tried to reproduce the performance based on resnet18 on Cityscapes, and I set the sample number of one batch as 4000. There is a slight difference between the official...

test resolution (输入尺度带来的增益)

3

Hi Feng, I'd like to first appreciate this implementation. However, as mentioned in issue #35 , the processing of inference is different from the original [Centernet](https://github.com/xingyizhou/CenterNet/blob/master/src/lib/detectors/ctdet.py). Specifically, the original algo....

Problem about batch size of PGSFormer

1

Hi, I meet a problem about training PGSFormer using batch size 4 per GPU, could you help me to debug this ? Error info. : ``` "openpsg/models/relation_heads/psgformer_head.py" line 501, in...

list index out of range?

3

学长你好，我尝试用这个选课，出现提示“list index out of range”，这个咋解决？

Hi, I would first like to thanks your contribution. However, I think there exist some issues of the evaluation. ``` if self.mode=='sgdet': iou_overlap = bbox_overlaps(gt_boxes, pred_boxes) if self.use_gt_filter: idx =...

FP8 training

8

does trl trainer support FP8 training? https://huggingface.co/docs/accelerate/en/usage_guides/low_precision_training