chainercv
chainercv copied to clipboard
chainer
ChainerCV: a Library for Deep Learning in Computer Vision
I deleted the test for now because this requires manual downloading of the entire dataset. The test can be found below. https://github.com/chainer/chainercv/blob/bde8e36406babd375f2b80aa48e5242118b2dc0f/tests/datasets_tests/imagenet_tests/test_imagenet_det_bbox_dataset.py
It's very cool code for chainercv. By the way, are you going to extend multi-gpu training code for YOLO?
# Ongoing - [ ] YOLOv2 https://github.com/chainer/chainercv/pull/596 - [ ] YOLOv3 https://github.com/chainer/chainercv/pull/596 - [ ] Light Head R-CNN https://github.com/chainer/chainercv/pull/775 # Requested - [ ] SNIPER - [ ] RetinaNet
Are there any implementation already that would help solve the following problem. Given a sample set of images (fixed size n x n pixels) would it be possible to run...
This PR adds a dataset class for human pose dataset [FLIC](https://bensapp.github.io/flic-dataset.html). It follows the convention of keypoint dataset like `CUBKeypointDataset`.
now Chainer supports VGG19, so how about below two? - adding VGG19 to chainercv/links/model/vgg - adding its link to caffemodel to examples/vgg/caffe2npz.py
## Visualization - [x] `vis_insntace_segmentation` (#541) ## Datasets - [x] `COCOInstanceSegmentationDataset` ([draft](https://github.com/yuyu2172/coco-evaluation/blob/master/instance_segmentation/coco_instance_segmentation_dataset.py)) (#547) (#665) - [x] `VOCInstanceSegmentationDataset` (#540) - [x] `SBDInstanceSegmentationDataset` (#540) - [x] `assert_is_instance_segmentation_dataset` (#540) ## Evaluation - [x]...
Some ideas on possible tutorials to add: - [x] Object Detection Tutorial + bbox in ChainerCV + BboxDataset + Object Detection Link interface + Evaluating performance of Object Detection Link...
Currently, all images are assumed to be converted to `numpy.ndarray` right after loaded from the disk. However, this leads to unnecessary copy of images. For example, in the case when...