up-detr

up-detr copied to clipboard

backbone的build时会构建position embeding，需要用到nestedtensor的mask，请问输入tensor类型的不会报错吗，我看代码里没有做相应的分支处理 

Flyooofly

Flyooofly

Hello there! As the code for the one-shot object detection task is not available in this repository, would there be any way to access it? If not would it be...

JosephAssaker

A blog about UP-DETR

6

Hi authors, This is not about an issue :smile: UP-DETR is great! I just wrote a blog about it, see here: https://medium.com/analytics-vidhya/up-detr-unsupervised-pre-training-for-object-detection-with-transformers-paper-explained-84611e27a144 You could consider to put its link in...

HaoWei-TomTom

_IncompatibleKeys

1

Hi, Thanks your works. I use my dataset pretrial on the you provided imagenet model. Then I use my pretreaind model to finetune on my dataset. The code return _IncompatibleKeys(missing_keys=['class_embed.weight',...

xiaoerlaigeid

Unexpected key(s) in state_dict: "feature_align.layers.0.weight", "feature_align.layers.0.bias", "feature_align.layers.1.weight", "feature_align.layers.1.bias", "patch2query.weight", "patch2query.bias".

1

excuse me, I Fine-tuning in own dataset and evaluation This is mine warning after evaluation in pycharm(win 10)，pytorch==1.12.1，torchvision==0.13.1，cuda==11.7，3070ti Unexpected key(s) in state_dict: "feature_align.layers.0.weight", "feature_align.layers.0.bias", "feature_align.layers.1.weight", "feature_align.layers.1.bias", "patch2query.weight", "patch2query.bias". I dont...

Zoeun

请问微调300个epoch能收敛吗？为什么我在自己数据集微调了600个批次都收敛不了

1

Flyooofly

Flyooofly

I have the opposite situation. RuntimeError: Error(s) in loading state_dict for UPDETR: size mismatch for class_embed.weight: copying a param with shape torch.Size([3, 256]) from checkpoint, the shape in current model...

liuchengying758650786