-
Hi, can you provide the hyperparameters for reproduce your results of resMLP? is the final results for resMLP-12 is 76.6 without distilled?
-
- AI News
- ICCV notification out: accept letter 받으신 모든 분들 축하드립니다!
- IBM Watson 의 현주소
- NYT: https://www.nytimes.com/2021/07/16/technology/what-happened-ibm-watson.html
- 국내: https://…
-
Hi, can you share the HP that your team trained it on RandAug with Timm? I have followed the same steps but still stuck on 76.9% and couldn't go any further (trained for 300 epochs should reach approx…
-
Hello,
I have read your paper and found it very interesting. I was particularly intrigued by Table 1 where you compare the throughput against other methods, including DINO with a deit_tiny and patch …
-
Be sure you've searched [the forums](https://forums.fast.ai) for the error message you received. Also, unless you're an experienced fastai developer, first ask on the forums to see if someone else has…
-
优化器参数设置，训练cascade rcnn模型，使用默认优化器并没有问题，换成Adam训练到一半就出问题了
OptimizerBuilder:
optimizer:
type: Adam
regularizer:
factor: 0.0
type: L2
-
When use
`python3 -m torch.distributed.launch --nproc_per_node 8 --master_port 12345 main.py --eval --cfg ./configs/swin_tiny_patch4_window7_224.yaml --resume ./official/swin_tiny_patch4_window7_224.…
-
Dear contributors,
Thanks for releasing your code. We used your codebase to run ConViT-Ti on the ImageNet dataset and achieved 72.5% Top-1 Accuracy, which is 0.6% lower than you reported. Could yo…
-
### Solved :tada:
Starting from [v1.10.0](https://github.com/pytorch/pytorch/releases/tag/v1.10.0), `torch.nn.CrossEntropy()`has an arg `label_smoothing=0.0` - [API link](https://pytorch.org/docs/1…
-
Hello Keras Team! I want to contribute to the coding example at keras.io by implementing CutMix implementation for image classification with Keras. Can anyone assign me or may I directly work on it an…