-
Notifications
You must be signed in to change notification settings - Fork 2.5k
Object are localized but not classified #166
Comments
It looks just a visualization error. |
It isn't visualization error. I checked class names, they're correct. |
The order of the indices of the class should be the same for the training set.
and in testing
|
@ltnghia Have u success trained cityscapes? would u like to send a PR to master branch so that maskrcnn model can be trained on that ? |
@fmassa: still not find out the reason. The class name / class order for both training and testing are the same. But predictions.get_field("labels") is always wrong. |
@ltnghia Hoping for that |
@ltnghia given the results you have, I'd really expect it to be because of misaligned labels for the predictor. I'd check if the labels are actually contiguous in the training set? Maybe there is one index which is skipped? |
@fmassa: I found out my stupid mistake. I sorted labels by name instead of ID. |
|
Hello Nghĩa, bạn train maskrcnn cho cityscapes thành công ko à. Có thể share cho mình thông tin được không nhỉ? Skype: kstn_hut_hat. Cảm ơn nha |
hi, @ltnghia , did you try to do the instance segmentation task on this maskrcnn bechmark net using cityscapes? and could your results get around 36.5% segAP same as the maskrcnn paper? SOLVER: these parameters above is the official advice about training cityscapes model based on coco pretrained model with 8 gpus,so can you help me about how could i set these parameters when I only have one gpu? thanks so much. |
@ltnghia xin chào bạn, bạn cho mình hỏi là bạn sửa lại format của dataset cityscape sang format của COCO như thế nào vậy? Hay là bạn chỉnh sửa trực tiếp model để model có thể nhận cityscape luôn? |
nó có file convert sang coco đó bạn. Bạn tổ chức đúng cấu trúc thư mục là đc nhé |
@tuanhanhdmprof mình đã cố gắng sử dụng file convert này https://github.com/facebookresearch/Detectron/blob/master/tools/convert_cityscapes_to_coco.py nhưng vẫn không thành công. Bạn có thể chỉ rõ cho mình nên sắp xếp thư mục dataset như thế nào được không? |
Mình nhầm ý trên. Hướng dẫn để convert nhé:
cái thứ 3 cấu trúc lại thì sửa lại lệnh run trên là ok |
@tuanhanhdmprof |
nó là thư mục chưa mấy file json ấy bạn (chính là thông tin của các object trong ảnh ấy theo format cityscapes ban đầu) |
Can someone make a tutorial on how to convert the cityscapes dataset and put it to train a mask-rcnn model? |
Hey @luisdecker you can check out my repo, have tried to make a cityscapes dataset, similar to matterport repo. Hope this helps! |
❓ Questions and Help
I fine-tuned Faster R-CNN with backbone FPN-50 on Cityscapes dataset. Objects can be localized accurately but are always classified incorrectly, such as: all 'car' => 'bus', 'bus' => 'car' , 'person' => 'truck', 'bicycle' => 'motorcycle', etc. predictions.get_field("labels") is always incorrect. I don't know what's wrong. Please help me!
I fine-tune the network as follow:
maskrcnn_benchmark/utils/checkpoint.py is modified as:
The text was updated successfully, but these errors were encountered: