Closed brade31919 closed 8 years ago
Hi, we have not not implement a public python version of coco data provider. You can make use of the API provided by COCO. Then implementing the coco data provider is not that hard.
Thanks a lot!! I have one more little question. I can find some examples of using coco api to do evaluation in faster rcnn case. However, in that case, it needs only detection evaluation part. In MNC case, I found there are some difference between pascal_voc_det and pascal_voc_seg about evaluation. In coco api, I can find the evaluation function correspond to which in pascal_voc_det, but I can't find the function correspond to evaluation about evaluating segmentation @@ Or...do I have wrong understanding on the coco api? Thank you for answering so many question!!
Hi, the API are shared for detection and instance segmentation.
Dear @daijifeng001 @Oh233 @liyi14
Thanks a lot for sharing your marvelous project.
I just started to learn deep learning several weeks ago. I have some problem about training MNC on MS COCO dataset.
First, regarding preparing dataset, I found I should modify the code providing data (MNC_ROOT/lib/datasets/* ). Beside datasets, is there any code need to be re-implement?
Second, there are some functions to do evaluation in MNC_ROOT/lib/datasets/pascal_voc_seg.py. How can I do evaluation on MS COCO for instance-aware semantic segmentation? I can't find api to evaluate segmentation (only api for evaluating detection in COCO api @@).
Third, could you please provide your data provider of MS COCO? There are few examples about providing data for instance-aware semantic segmentation and it is quite hard for me to do this.
Sorry for asking so many questions. I am quite new to deep learning and caffe, so there are many details I don't know.
Best regards 沅