Simón Sepúlveda Osses

Results 11 comments of Simón Sepúlveda Osses

Can you post here some examples? Also have you tried increasing the confidence threshold?

Hi Have you tried [installing](https://github.com/facebookresearch/maskrcnn-benchmark/blob/master/INSTALL.md) the maskrcnn-benchmark ? Also you can trying commenting [this line](https://github.com/simaiden/Clothing-Detection/blob/master/new_image_demo.py#L6) and try using only yolov3 that doesn't need any installation.

Hi, thanks for using my project The class indexes are the same used by DeepFashion2 and Modanet, those are: **DeepFashion2** `short sleeve top long sleeve top short sleeve outwear long...

I calculated the COCO mAP, with validation subset in DeepFashion2 and a custom test dataset in modanet, because the authors never released the test and validation subsets ![imagen](https://user-images.githubusercontent.com/32749727/99414659-cc8efc80-28d5-11eb-868e-d6021e9e5f90.png) - DeepFashion2...

Hi @gkhanacer , Unfortunately I didn't train a segmentation model, but it's not quite hard to train a Mask RCNN model with Detectron2 framework, both Modanet and Deepfashion2 have annotations...

Hi, sorry for the late reply Hoy did you calculate the average precision? I used darknet to get the .json file with detections in coco format, but you can get...

Still facing the same problem, when I tried to clone using HTTP I got the following error: `Error downloading object: annotations/modanet2018_instances_train.json (b8a3fd0): Smudge error: Error downloading annotations/modanet2018_instances_train.json (b8a3fd0dcfa8d6f209a0cef88cedd76decbf593bf47b4246504f681b7fb625af): batch response:...

@cad0p Many thanks, I'll be waiting for them. I'll use modanet to train some object detections model as YOLOv3 , FasterR-CNN, and others.

Thanks for reply! Sorry about the dumb question but is `RpnHead` the `Head` in`tridentnet_r50v2c4_c5_1x.py` ? or may I have to save `roi_extractor = RoiExtractor(RoiParam)`? Thanks in advance

I have an error: `RuntimeError: num_iter_b5f728d4-dac5-4563-be3a-0a3f8a5c690a is not presented` Maybe the code you posted ir just for training? How can i get the roi feats in inference? Thanks!