JingyuLi

Results 12 issues of JingyuLi

When I default parameter: _python train.py --gpus 0 --id experiment-xe --geometry_relation True_ , it can run but in 6 epoch around errors occur as follows: I guess that 1. I...

Thanks for your sharing! in your resnest readme, you have reported the Deeplabv3plus+resnest200 on citycapse results achieve 83.8%miou. Can you update this part code? thanks.

thanks for your sharing codes ! in your paper, apollo dataset Validation is 10000 images, but your code vallist only have 1000 images? how about this problem? ![image](https://user-images.githubusercontent.com/45377489/85936636-2f83f500-b92f-11ea-8858-f44e2f3cc359.png)

想问一下,目前项目支持yolov3和yolov3-spp。如何修改使用yolov3-spp-pan-scale.cfg? 基础训练和稀疏训练可以支持yolov3-spp-pan-scale.cfg,在层和通道剪枝运行layer_channel_prune.py 时AttributeError: 'NoneType' object has no attribute 'reshape',如何修改这部分剪枝代码?

Thank you for your code. when I run this repo, some issues confused me. 1. for code [https://github.com/layer6ai-labs/SGG-Seq2Seq/blob/main/transformer.py#L238](url) "relation_ids" contain relation label such as tensor([[ 0, 48, 31, 48, 31,...

When we run python tools/build_dataset.py, we get this error. Do you have any ideas? ![image](https://github.com/yeliudev/ConsNet/assets/45377489/d5907d4c-e6c5-4ccc-be31-014eadbbf030)

Thanks for your excellent work. can you release the **short** descriptions for all 1,281,167 training images using [MiniGPT-4] 7B model? Can you release the **short** descriptions code?

Thanks for your work! I want to know what pre-trained model do you use? ImageNet-1K or Pre-training on ImageNet-22K and fine-tuning on ImageNet-1K, have you compared that? It would be...

非常感谢您的工作! 好像目前公开的数据集的照片是经过Resnet处理过的,请问是否可以提供原始数据集中的图片?感谢!