Yiming Ma

Results 11 issues of Yiming Ma

## Description Is it possible to enable the width of the sidebar to be automatically adjusted to titles? ![image](https://user-images.githubusercontent.com/45311510/136569033-5e7d05b0-b45c-4a1d-966b-053864360a32.png) In the example above, "image" is not shown, i.e. it should...

Hi @sacmehta, First I'd like to thank you for your contribution of MobileViTs. But I have the code in this repo very unfriendly for downstream tasks. I cannot find which...

Hi @chinhsuanwu, Could you please update your model by adding initialisation code? And apple has released the [weights](https://github.com/apple/ml-cvnets/blob/main/docs/source/en/general/README-model-zoo.md) for MobileViTs, could you also please add option to load pre-trained weights?...

Hi @okankop , I think you might have made an error in the code for validation/testing. It seems that the value of threshold is determined by the results on validation/testing....

Hi Zhaoyi et al, I am using your [Crowd Surveillance dataset](https://ai.baidu.com/broad/introduction), but I got some memory problems when using `cv2.fillPoly`. Would you mind sharing the whole part of ignoring regions?...

Hi @andrewluchen, Thanks for providing the TensorFlow code for FindIt. I am wondering if it possible to also provide a PyTorch implementation of the wonderful model FindIt? Also, could you...

**Describe the bug** For ViT, the returned total mult-adds from torchinfo.summary is much smaller than that reported in other websites. **To Reproduce** Code snippet: ```python from torchinfo import summary from...

Hi, I tried to upgrade `font-lxgw-heartseri` on Homebrew but got this error message: ``` ==> Updating Homebrew... Already up-to-date. ==> Upgrading 1 outdated package: homebrew/cask-fonts/font-lxgw-heartserif 0.920.3 -> 0.920.5 ==> Upgrading...

Hi, Thanks for your great efforts and contribution! Is there any way to find out the category name of the objects of interests in your dataset? For example, suppose we...

Hi, Could you please also add your dataset to https://paperswithcode.com/contribute/dataset/new ? This can help improve its exposability and increase your citations. Thanks, Yiming