-
-
there are my log
from n params module arguments
0 -1 1 464 models.common.conv_bn_hswish …
-
@AlexeyAB hi
I want to use YOLOv4 for detection on the mobile terminal, using MobileNetv3/GhostNet backbone network, but I don’t know how to use it.
Where does the source code need to be modified…
-
Importing `PHash` causes the import of the `CNN` class and triggers the download of the Mobilenet model from `torchvision`.
Although very small, it's just and extra log that can be distracting …
-
Acoording to Searching for MobileNetV3, there is a connection from feature 1/8 to the end of the segmentation head. Is it implemented? I did not find a shortcut.
:
if min_…
-
博主，您好，非常感谢您很有意义的工作！
我想请教一下，对于您的mobilenetv3_voc网络中您采用mobilenetv3作为yolov3的backbone网络，从网络结构上看，您是对mobilenetv3网络结构进行了裁剪去掉了部分网络层吧，并没有用原始的mobilenetv3，同时yoloV3你也只是采用两种特征图大小进行输出，去掉了54×52的输出特征图。麻烦博主帮我解答一下，谢谢！
-
Hi,
When I try to load pretrained weights of MobileNetV3 (either -S or -L) to BiSeNetV1, this error appears.
```RuntimeError: Error(s) in loading state_dict for MobileNetV3:
size mismatch for fe…