-
### Search before asking
- [X] I had searched in the [issues](https://github.com/ray-project/ray/issues) and found no similar feature requirement.
### Description
Hi, I have utilized ray tune to d…
-
The follow-up research from PaLM switched in Flan-PaLM to the encoder-decoder t5 architecture. How would it be possible to also add an encoder to this implementation?
-
Hi, thank you for releasing such a good project. I have several questions during running your code. Could you help me, please?
First, I'm wondering if your code is doing whole pre-train task during t…
-
Dear Author, Thanks for your great work! I read the paper you have do the experiments about the swin-tiny with and
w/o ImageNet-21k pretraining and distillation. Can you share the config and code her…
-
The original papers mentioned: `` Specifically, let T denote a set of teacher layers that we use to distill knowledge to the student model.''
And the code in trainer provides ``[2, 5, 8, 11]'' only, …
-
Hi, compared to the newest performance of yolor, yolov7 is still a little lower on mAP.
Tested on img-szie=1280, yolor-d6 mAP is 58.2%, and yolov7-e6e mAP is 56.8%.
Are there some strong training tr…
-
@danielgoldelman will explain the above (and whatever else is relevant) in the readme of this repo.
(Here is the [overview](https://docs.google.com/drawings/d/1hVR1TosCTINKbo0nAad3-Ju3yYyyKEdRE1yj…
-
By directly using your script for 1 IPC of CIFAR100, I got 27.7 acc (+0.5 compared to the paper). However, I only got 39.9 (-1.4) acc on 10 IPC of cifaCIFAR100100 when I directly use the hyperparamet…
-
Iwslt14 data (it is obtained from the data processing script in Fairseq, which is on knowledge distillation for this dataset. There is only 4.2 BLEU on this method. Is there no knowledge distillation?…
-
请提供下述完整信息以便快速定位问题/Please provide the following information to quickly locate the problem
- 系统环境/System Environment：**ubuntu18.04**
- 版本号/Version：Paddle：**2.3.0** PaddleOCR：**release2.6** 问题相关组件/R…