-
hi alexry, i trained for 7 object with the last stable master branch, the training finished but the model only detect 2 of the 7 categoies, I already checked the labels, and all of them exist. on the …
-
Hi @AlexeyAB ,
I only have one class, so I changed the line max_batches to 4000, and changed the line step to 3200,3600.
But when I change the "max_batches" and "step", it can't training.
![im…
-
Flot has had many contributions, and the code has become a mish-mash of different styles. Maintaining and contributing to the library would be easier if we adopted a unified code style. The proposed…
-
This below error occur when I run export.py. Could you check it? Thank you very much!
TorchScript export failure:
Could not export Python function call 'MishCudaFunction'. Remove calls to Python f…
-
4000张图片 使用两块2080ti 迭代一次需要4分钟 使用的u3版本yolov4 如果按照这个速度训练到5000次,需要15天训练完。。想问一下作者为什么会这么慢？？谢谢
-
* `batch=1 (sync-mode)`
* CPU, VPU
* OpenCV 4.2.0 (master-branch 21 Mar 2020)
* OpenVINO 2020.1.033
* GPU
* CUDA 10.0
* cuDNN 7.4.2
* Darknet (Mar 22, 2020) GPU=1 CUDNN=1 CU…
-
-
/usr/local/cuda/bin/nvcc -Iexternal -I/opt/conda/lib/python3.6/site-packages/torch/include -I/opt/conda/lib/python3.6/site-packages/torch/include/torch/csrc/api/include -I/opt/conda/lib/python3.6/site…
-
cuda10.0,cudnn7.4,opencv4.0.
the cfg file is the same as yolov4.cfg and I use yolov4.conv137.
-
Hi, everyone,
I have a problem when I train my own data. Even I have trained for about 13708 iterations, the average loss is still about 30 to 40. When the iteration is about 2000, the average …