-
I want to convert my custom yolov4 model int8,
but it appears the keyerror
I test the default yolov4.cfg ,it works.
```
root@aaeon-desktop:/workspace/lym/tensorrt_demos/yolo# python yolo_to_onn…
-
I was running a custom training on Yolov4
`darknet detector train ./training/custom_training/sa_20200616_18:26:34/config/obj.data training/custom_training/sa_20200616_18:26:34/config/yolov4.cfg trai…
-
thanks for your amazing paper . follow the paper. I set the beta = 1. what number the cutmix_prob should i set?
-
## 🚀 Feature
Batch transforms can help us finding the biggest image on the batch so we can pad the others and maintain the aspect ratio. Some newer transforms like CutMix also need a batch transfor…
lgvaz updated
4 years ago
-
Hi,
Great good. Congrats.
I would like to train your model on this fruits dataset: [https://www.kaggle.com/moltean/fruits](https://www.kaggle.com/moltean/fruits )
It has about 80K images, 10…
-
This is a question, not a bug. @AlexeyAB is there a way to incorporate the "Visually Coherent Image Mixup" augmentation strategy? Amazon recently published a paper that claims that this approach resul…
-
我是跑昆虫数据集的voc格式，提示这个
%run tools/train.py -c configs/dcn/yolov3_r50vd_dcn_db_obj365_pretrained_coco.yml
运行时长: 5秒802毫秒
结束时间: 2020-08-25 18:11:09
-------------------------------------------------…
-
If in the mini batch random sampling, when the sample pairs combine new data, image a and image B are background regions in the clipping region, and the background regions are almost similar, rather t…
-
Hello,
I'm training darknet to detect my custom objects. The process looks fine without error after loading, and during training. However, after a number of iterations (~1000), the process is kille…
zrion updated
3 years ago
-
I trained the model with the following two scripts. Both result nan loss after 1 epoch training. Any thought to address this issue?
CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 ./distributed_train.sh 8 p…