-
请问博主在yolox的源码基础上用了yolov4哪些tricks，对比了网络结构代码，没发现什么不同，训练结果对比源码却提升很多
-
Hi,
Yolov4 and v5 are out now and their benchmark are outstanding compared to Yolov3.
Are you going to update FairMOT with the last version of Yolo ?
Does it mean retraining all your model ?
…
-
你好，我这边下载百度云的yolov4_maskdetect_weights1.pth在torch.load()的时候报错了，可能是模型有点问题，
请问还有其他模型下载路径吗。
-
D:\app\anaconda3\envs\Yet-Another-EfficientDet-Pytorch\python.exe E:/PycharmProjects/pytorch-YOLOv4/train.py
log file path:log\log_2020-10-13_17-06-25.txt
2020-10-13 17:06:25,341 train.py[line:611] …
-
I came across this,
for training for both small and large objects use modified models:
YOLOv4: 3 yolo layers: https://raw.githubusercontent.com/AlexeyAB/darknet/master/cfg/yolov4-custom.cfg
A bit…
-
作者您好，请问SE，CBAM这些权重（.pth）是作者你自己训练出来的吗？是载入预训练权重（yolov4_tiny_weights_voc.pth）然后在VOC07+12训练集上训练出来的吗？
-
Hello, I trained custom tiny yolov4 model and convert it into onnx model. I cloned the demo from GitHub and replace yolo model with my model. But when I run the application it gives me Error: invalid …
-
I've recently set up a new machine and am unable to train the program from scratch. Each time I run the program using the train command it errors saying:
`train.py: error: argument --weights: expecte…
-
I tried to run models/export.py to covert the model to torchscript. The command I used is:
`python3 export.py --weights ../runs/exp3_yolov4-csp/weights/best.pt --img-size 640 640 --batch-size 1`
…
-
I am trying to connect a robot's base_link (fixed) to the OAK-D's `oak-d_frame`. I can calculate the base_link distance from the camera in the 3D manually. Which is the reference frame, `oak-d_frame` …