jason_w
jason_w
@tzjtatata Use MatConvNet 1.0-beta24
> @DIAMONDWHILE @AlexeyAB can you share the implemented source code of the following idea shared in this link Note: The **convolution layers in YOLO don’t actually use bias**, so b...
Hi @ZwwWayne In the description of 'class SSDAnchorGenerator': > scale_major (bool): Whether to multiply scales first when generating base anchors. If true, the anchors in the same row will have...
https://github.com/yeahkun/caffe-yolo/blob/eea92bf3ddfe4d0ff6b0b3ba9b15c029a83ed9a3/src/caffe/layers/box_data_layer.cpp#L144 ``` int locations = pow(side, 2); CHECK_EQ(count, locations * 7)
I think that when using `scale_ranges`, we will focus on the mAP of each `scale_range`, rather than the mAP of the `whole range`.
`cap.set()`设置宽高不知道有没有成功哦。 我之前也封装了OpenCV的VideoCapture，转Image之后，是可以正常工作的。
```bash pip install --upgrade --force-reinstall numpy==1.26.4 ```
你这路径不对吧
> > 你这路径不对吧 > > 请问下我这个路径是什么地方有问题呢 `/apollo` 和 `~/apollo`？ 一般 `bazel-bin`就是链接的项目当前目录中的`.cache`
我没在docker里面弄。实在不行，自己重新build一下呗。