Abhishek Rana

Extract 1. captions_train-val2014.zip 2. instances_train-val2014.zip 3. person_keypoints_trainval2014.zip 4. train2014.zip 5. val2014.zip Final folder structure should look like this: data/ ----coco --------annotations ------------captions_train2014.json ------------captions_val2014.json ------------instances_train2014.json ------------instances_val2014.json ------------person_keypoints_train2014.json ------------person_keypoints_val2014.json --------records --------train2014 --------val2014...

I think this is just a warning. If _mask.so is being generated correctly, this should not be an issue. You can remove _mask.so and then call python setup.py build_ext --inplace...

cd FastMaskRCNN mkdir -p output/mask_rcnn [logs.txt](https://github.com/CharlesShang/FastMaskRCNN/files/1090880/logs.txt)

You can add more heads(one for color, one for style and one for pattern) on the base model (currently there are 2 heads, classification and regression). [see model.py: line 44]...

https://drive.google.com/drive/folders/0B7EVK8r0v71pQ2FuZ0k0QnhBQnc

The link is same as the one generated by download section of http://mmlab.ie.cuhk.edu.hk/projects/DeepFashion.html. (Maybe they have password protected the dataset now)

Hi, I trained the model for 19 classes (as the entire dataset is quite big) a long time ago. Here are the weights which I could find: https://drive.google.com/open?id=12DFSzosFAw7SnuwJWnYboFUBunJMrM64 Also, these...

The current code makes many predictions for a single image. Each prediction consists of the predicted class(i.e. apparel having the highest probability), probability of that class, it's bounding box location...

In the RESULTS section of the repo, you can see that some bounding boxes enclose the entire jean ("complete ones") while some only a part of it("small regions"). The required...

The model tries to detect apparel type only for the Region of Interests (ROI) proposed by selective search algo. During training, the dataset had only one person per image and...