UniFormer
UniFormer copied to clipboard
Sense-X
[ICLR2022] official implementation of UniFormer
I'm hesitating asking this basic question, but what's the correct way using the token label models for basic image classification? I followed your instruction in [huggingface.co uniformer_image](https://huggingface.co/Sense-X/uniformer_image), but the result...
hello, i got the erro, Please tell me how to solve? raise RuntimeError('Unknown model (%s)' % model_name) RuntimeError: Unknown model (uniformer_large_ls)
Hi , When i try to run the "uniformer_b32x4_k600", could find that provided script file "run.sh" contains "python tools/submit.py" BUT there is no files name like it in the 'tools'...
The picture has to be pre-trained, how do I change the parameters of the 2D convolution into the parameters of the 3D convolution
Hello, please ask how to load the pre-training weights when mmdet does object detection, I see that the profile pretrained=none
Firstly, thanks for your excellent work. But I am wondering how to train uniformer on my own video dataset. Can you give me some key steps like how to construct...
I found your paper extremely interesting and I am very interested in it. I would like to use it for feature extraction. I saw that you provided a demo here...
Hi, I was wondering what precision these models were trained at? Float32? Float16? Bfloat16? With mixed precision? Thanks.
大佬您好，我想问一下，关于UniFormer，如果只准备了解模型架构的话，代码是不是只用看这个文件[https://github.com/Sense-X/UniFormer/blob/main/video_classification/slowfast/models/uniformer.py](https://link.zhihu.com/?target=https%3A//github.com/Sense-X/UniFormer/blob/main/video_classification/slowfast/models/uniformer.py)就可以了
this pr will mainly add 3 methods to the uniformer model * `save_pretrained` * `push_to_hub` * `from_pretrained` : initialize and load the model weights allowing your model to be easily...
