Heitor Rapela Medeiros
Heitor Rapela Medeiros
"Chainer 2.0.0+" I`m using Chainer 4.3.1 and Cupy 4.1.0
Good question, I updated and run the baseline but I had to stop the training. I need to run for 1200 epochs? With 35 I was having good results on...
@Jongchan , I didn't finish the training. But it seems to be good the result that you got.
@KelvinHuang666 You need to search for the best config. of params for your dataset. For the number of epochs I suggest that you put a high number of epochs and...
@betterhalfwzm try to add some early stopping and save the best model on validation loss (split the data in train / val / test ).
@czzbb, your training loss is still decreasing while your validation loss is still on a plateau. It means that your model adapts the weights too much for the training set...
I saw that here you have test other versions of yolo. I have these results with the yolov5l (version 7.0) (commit: [bfa1f23](https://github.com/ultralytics/yolov5/tree/bfa1f23045c7c4136a9b8ced9d6be8249ed72692)) on llvip infrared trained with the hparams from...
Hello. Any updates on how to do it easily with the output provided by the detectors? For instance, I am training yolov5, and it would be interesting to reproduce the...
> pip install numpy==1.23.5 yapf==0.40.1 I had the same problem, but I solved with this pip install. Thanks.
> `flash_attn = False` on your Unet Thanks, it worked :)