-
Small passage about VRAM info would be nice :)
-
As a public user, I want to
* view all editorial information available for a selected ecosystem group
so I can better understand its characteristics and significance
---
The available inf…
-
The new dataset API is now stable enough to start porting more datasets from the old API. For the `0.13.0` release planned for 2022H2 we want to achieve at least feature parity for the new API. If you…
-
I am very interested in this work, but I only know that you utilized _DenseCap_ on selecting video thumbnails, I wonder how to use the DenseCap results on this task, classification or ranking?
Is the…
-
I tried to speed up the serving program and found three solutions :
-1 Replace `dlib.get_frontal_face_detector` with Face Detection from Yeephycho's SSD Mobilenet (https://github.com/yeephycho/tenso…
-
由于Windows系统不支持ParallelExecutor这个API，在window环境下跑模型训练，很多都会报如下错误：
包括：face_detection、cycle_…
-
## Problem
To do any sort of computer vision classification we will need to have training data consisting of our annotations and video. Video streams currently do not let us download video, only prov…
-
# Reference
- 2021-01 A Survey on Visual Transformer [[Paper](https://arxiv.org/pdf/2012.12556.pdf)]
- [论文笔记 - 0809zheng](https://0809zheng.github.io/2021/02/10/visual-transformer.html)
# Brief
- …
-
How can i test with the model obtained if i give him a video and see if is fight or not fight ?
-
Hi, I have trained on K400 dataset according to this repository, during training the loss and top1-err(top5-err) decline normally, however, after 300 epochs' training, the final top1 accuracy is 16.…