-
Have you try to evaluate your DANet on pascal voc 2012? I did an experiment on that dataset but I did not get some gains.
-
hi @unsky,
have u tested `focal loss` in pascal voc dataset? btw, can u share your parameters? like the hyperparamter in `solver.prototxt` and some parameters of `rpn` and `fast rcnn`?
thanks.
-
Hi, thanks for your codes! But when I run `sh experiments/scripts/faster_rcnn_end2end.sh 1 VGG16 pascal_voc` I got a error :
`Traceback (most recent call last):
File "./tools/train_net.py", line 1…
-
I am annotating images and while annotating noticed that I need to specify more classes, also changing an existing class name to fit in with new classes.
Is there a way to automatically change a clas…
-
Hi,
Thanks for your amazing work, I am currently duplicate your baseline for FPN and RFCN. I noticed that you did not provide the cfg file for FPN training pascal_voc_0712. I am wondering is there an…
-
Hello! This is a question.
Does anyone know whether we have the yolov3 weights for the PASCAL VOC?
I am trying to avoid retraining yolov3 for the VOC challenge because I just want to check the …
-
Hello, I am trying to using demo to do the inferences for few-shot VOC. My code as following:
```
def main(
config_file="configs/few-shot-voc/10shot/vitl_3s.yaml",
rpn_config_fi…
-
when I run "python data_pascal_voc.py pascal_voc_setup" to get the "combined_imageset_train.txt" file, error occurs as follows:
Traceback (most recent calls WITHOUT Sacred internals):
File "data…
-
I need a resnet50 model trained on PASCAL VOC dataset. So is it better if I crop the training images based on annotations or simply feed the whole images for training on RESNET?
-
Hello,
Looking for info on how to train SSD MobileNetv2 model with negative samples. How is 'BACKGROUND' label handled for negative samples.
Here is my annotation xml for pascal voc dataset for …