-
Hi, thanks for sharing this amazing work.
I used the pre-trained model provided for evaluation.
For re10k, the metric is lower than that in the paper, and I don't know why it will end early (end…
-
This is a great job and has a positive significance for the development of the IML community.
However, I have noticed that there is some confusion regarding the input image sizes for different meth…
-
Did the authors use Test-time augmentation (in consistency with other models like MeshGraphormer (ICCV21), and METRO (CVPR21)) while evaluating the model on the FreiHAND 3D Hand reconstruction dataset…
-
对于红外光来说，三个通道的数值相同。
请问，通过您channel_aug.py中的class ChannelAdapGray怎么进行通道增强啊..
结果都是返回原图..
-
### v1
```shell
# nohup torchrun --nnodes=1 --nproc_per_node=8 train_net.py --tokenizer_path /mnt/lustre/zhaolin/vln/llm/models --cfg_file tools/cfgs/datasets/s2_imgdatasets.yaml --batch_size 2 --…
-
纯讨论，有木有感觉作者原文给的这个Learnable Mask的可视化结果太细节太规整了？
-
I train a model by:
After training 98 epoch, I get the follo…
-
-
Hi,
I'm interested in how you have achieved the 2.5% OOD false positive rate on CUB from your paper. I've run your code but getting different results, here is the log output of the first 50 epochs:
…
-
Looklike submitting in [http://iccv21-mfr.com/#/submit](http://iccv21-mfr.com/#/submit) might be broken, please fix this !
Thanks.
NNDam updated
11 months ago