-
To make a mish tiny cfg which of the leaky layers would I need to set to mish?
Thanks
-
Hi.everyone.
I train just 5 class from VOK2012 dataset
training result is ...
step: more than 14000
loss: The value is continuously changed between 2 and 3.
and then I created my-yolo.pb …
-
Hi,
great work. I'm also trying to use yolov3 in openvino. Have you checked the inference accuracy for the converted yolov3 model? I trained my own dataset with new model(based on the structure of yo…
-
I have already converted ckpt to pb file. The size of pb file is 248.2MB. Then I want to use the pb file for inference. I find this sample code
https://github.com/github2016-yuan/tensorflow-yolov3/b…
-
Thanks for your great work!
I train (Gaussian+GIOU+YOLOv3) in this repository.
Which command should I use to calculate mAP for (Gaussian+GIOU+YOLOv3) after finishing training in this repository,
I…
-
I am working on object detection using a large scale autonomous dataset (BDD100K). My end goal is to detect common road objects using a Jetson TX2. Currently, I'm training this dataset on 2x1080Ti GPU…
-
I am trying to implement a forward pass of Tiny Yolo 3 in C and am stuck on upsampling and detection layers and wanted to get an idea on how darknet stores tensors in 1d c arrays. So that I can implem…
-
How does one input custom anchors that do not follow the same trend as the original anchors (xx60)?
For reference: Img size = `1280x736`
### Original Anchors :
```
anchors = 12, 16, 19, 36, 40…
-
I used the command : ./darknet detector calc_anchors data/voc.data -num_of_clusters 9 -width 416 -height 416 to recaculate the anchors about my dataset.
But the result is there no outpu…
-
While training, I mentioned a lower epoch number, so I want to resume from the last checkpoint.