-
1. [1st Place Solution to Google Landmark Retrieval 2020](https://storage.googleapis.com/kaggle-forum-message-attachments/978542/16699/1st_Place_Solution_to_Google_Landmark_Retrieval_2020_modified.pdf…
-
### 論文へのリンク
[[arXiv:2009.08453] MEAL V2: Boosting Vanilla ResNet-50 to 80%+ Top-1 Accuracy on ImageNet without Tricks](https://arxiv.org/abs/2009.08453)
### 著者・所属機関
Zhiqiang Shen, Marios Savv…
-
It says that this repo contains the PyTorch implementation of the paper but there are no files here.
-
## Reference
- [Github repo](https://github.com/AlexeyAB/darknet)
- [How to train (to detect your custom objects)](https://github.com/AlexeyAB/darknet#how-to-train-to-detect-your-custom-objects)
…
-
感谢您优秀的工作！我首先下载了您提供的预训练权重进行了验证并很好的达到了和您一样的效果，然后我尝试进行了重新训练，但是结果并未达到您给出的预训练权重一样的精度，我使用了wce_two_stage配置，设备是一张4090，batchsize为6，我的精度如下：0.6021805，使用了TTA精度提升至0.6215877，这让我有些苦恼，请问在训练的时候还有什么需要注意的吗，感谢您的回复，谢谢
-
I tried to sweep with timm([pytorch-image-models](https://github.com/huggingface/pytorch-image-models)) training script.
I can clearly see from the terminal output that the parameters configs are no…
-
load Sadtalker Checkpoints from .\extensions\SadTalker\checkpoints
Error executing callback ui_tabs_callback for E:\autmatic1111\stable-diffusion-webui-directml\extensions\SadTalker\scripts\extension…
-
Hi,
Thank you for the code release and the continuous support.
In the main paper (Sec 4.2.3) you mention FT experiments following the FT protocol in "Training
data-efficient image transformers & di…
-
## 一言でいうと
Supervised に、Sphere Embeddingを学習（phase1）。phase1後に、Linearな分類機を学習する（phase2)。
] [[Code](https://github.com/facebookresearch/d…