pg19

1

votes
0

answer
20

views

Which final layer to choose for best representative features of objects in Mask-RCNN?

I would like to extract the features from the final layer of the Mask R-CNN (https://medium.com/@jonathan_hui/image-segmentation-with-mask-r-cnn-ebe6d793272, https://github.com/matterport/Mask_RCNN, https://github.com/multimodallearning/pytorch-mask-rcnn) to feed into another network, so would it be...
pg19
0

votes
0

answer
4

views

Which layer should I take in Mask R-CNN for colour representation?

In Mask R-CNN (or R-CNN in general), which layer should I take to have a good representation of the colour of the detected objects?
pg19
1

votes
2

answer
0

views

Convert array into list for MultiLabelBinarizer

I have the following array : '['book', 'read']' '['cup', 'drink']' etc, and I would like to convert it into a list that would allow me to apply MultiLabelBinarizer. Currently it is either giving me individual characters or outputting just 0s. Y = train_labels.iloc[:, 0].values values = np.array(Y)...
pg19