Yingxin Pei

i want to know about data set, how enlarge the ImageNet-22K datasets by 5 times to reach million images with noisy labels? just data augmentation? hoping for your replation~ thank...

关于数据增强

3

请问是否使用过数据增强去提升模型精度呢？例如mixup等？ 另外关于使用 timm 的 mixup ，target shape 会变化，314000*1 >> 314*1000 这样的话这个 mask 该怎么去计算呢？ 谢谢~

Hi, I had using mask-rcnn-swin-s model with bbox 48.2 mAP and segm 43.2 mAP as teacher,but I got result under baseline,how explain this phenomenon?

A question about object detection distill

1

Hey,bro. I wonder using two stage method like Faster-RCNN to distill one stage method like Yolo, only using neck feature to distill, will it work？what's your opinion? Thanks.

GLM-130B在设置模型超参时，ffn_hidden_size=12288 attention_head=96 layers=70，LLaMA-65B 模型超参 ffn_hidden_size=8192 attention_head=64 layers=80, GLM-130B似乎更宽，业界主流模型似乎更深？请问GLM-130B模型设计时是出于什么考虑选用这个超参的呢？谢谢！

thanks for your excellent work~ i want to train from scratch using ImageNet-22K，how can i get this file： train_dataset="scripts/22k_train.txt" can you share it？ hoping for your reply~