-
I am attempting to convert a tensorflow CoATnet model but the gelu activation function is not supported. I notice in the previous version of the toolkit (rknn-toolkit) there is [documentation](https:/…
-
I tried to train your ViT implementation and other different backbones (like ConvNeXt, MaxViT, NFNet, CoAtNet, etc.) with the ArcFace loss function, and the loss and accuracies do not seem to converge…
-
There are many possible vision arch to try other than the Donut choice of swin v1 or the common choice of vanilla (or modified) vit. Should make an effort to explore the options as we run experiments.…
-
Hi,
I tried to train CoAtNet_0 with tiny image net from cs231n (200 classes). Seems the model does not converge.
Could it be that the implementation is not 100% correct? For example, the positi…
-
model = coatnet_3()
criterion = nn.CrossEntropyLoss()
learning_rate = 1e-3
optimizer = optim.Adam( model.parameters(), lr=learning_rate, weight_decay=1e-5,)
logs = train(model, train_loader=tr…
-
If I want to use Mobilevit in Cifar10, how should I set the parameters?
Because I changed the input size, but the parameters don't match.
For example:
----------------------------------------…
-
## 🚀 Feature
Adding new models to the models section.
## Motivation
Many new models have been proposed in the recent years and do not exist in the models module.
For example, the EfficientNets…
-
paper, code, and tool for super-resolution
-
## 🤷 작업할 기능 소개
> 작업할 기능에 대해 간략히 소개
K-fold validation 구현하기
## 🔨 상세 작업 내용
> 상세 내용 열거
- [x] To-do 1 coatnet3 (승철)을 이용하기
- [x] To-do 2 efficient net 이용하기
## 📄 참고 사항
> 참고사항 정리
-
CoAtNet_0 model defined in paper has 5 repeating RelTransformer blocks in stage S3, where as timm implementation has 7.
![image](https://github.com/user-attachments/assets/4be49ae1-7312-4e94-9a20-…