-
https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet
https://ai.googleblog.com/2019/05/efficientnet-improving-accuracy-and.html
https://www.youtube.com/watch?v=3svIm5UC94I
T…
-
In the code, if image A is mixed with image B, and A and B have same label, their lam value will be summed up, while calculating loss also seperately. This is my understanding from the code while I di…
-
Are there any references?
-
I have ran your codes 5 times in the below environment.
```
Two V100 GPUs
Python 3.6.7
PyTorch 1.0.0
Cuda 9.0
```
The command I used is this :
```
python train.py \
--net_type pyramidn…
-
Hello @AlexeyAB
I'm trying to use **Mosaic Augmentation** for image classification. But I'm facing an issue to create the augmented class label. As the methodology is inspired by your work, I need…
innat updated
3 years ago
-
I am having issues with this error and, from what I read, it is a memory issue.
![im…
-
1. 分割网络修改网络输入尺寸
2. 分类网络切换backbone
3. segnet换成代码形式
4. 检测网络修改anchors
5. 数据增强方法修改（对现有方法进行排列组合）
6. 数据增强修改resize_type参数
-
Hi, really nice codebase!
We have tried to understand the details of your implementation and find the usage of the loss mask a little bit confusing (as shown below).
https://github.com/Britefury…
-
hi, could you tell me whether the code in object detection should be same as that in classification?
-
Hi! Thanks for your great work and I want to try to use it in my work!
But, I do not understand why the model needs Consistency Regularization, although I have read the paper carefully.
For example,…