-
I am getting much higher mAP score on this repo for tiny-yolov3 model.
When I am using another repo for mAP calculation, it is giving lower scores.
Both of these are based on pascal voc :
https…
-
I have trained faster rcnn on a new dataset based on pascal_VOC format. The configurations are like pascal_VOC but there are 9 classes and the training is done with **10000 iterations**. This is the r…
-
Thank you for your awesome work.
Your work might be greatly helpful to all people who interest in the MTL.
I'm about to study MTL and have one question.
I think the dataset for MTL should be in…
-
hello!
If I want to train this model with less classes just like two or three class of object
but when i change the classes in pascal_voc.py some error is happened
so what should I do to change the…
-
I have 9 classes (8 objects + background) and I want to finetune e2e mask-rcnn with my own dataset and with COCO model without training it was able to detect some objects (such as ball, cup) so I woul…
-
`AddressBook` is clearly a class from its pascal case and references like 'AddressBook objects'.
However in places like the implementation section, code fences are missing:
 but thus far have been unsuccessful. Without GPC, I can successfully build binutils, gcc (including language support for C, C…