NEWS.md
transform_rotation wrongly using w x w for image size (@114, cregouby)tensor_image_display and tensor_image_browse now accept all tensor_image dtypes. (#115, @cregouby)transform_affine help to remove confusion with transforme_random_affine help (#116, @cregouby)qmnist_dataset() – a dataset loader for the QMNIST dataset (#153, @DerrickUnleashed)emnist_dataset() – a dataset loader for the EMNIST dataset. (#152, @DerrickUnleashed)fgvc_aircraft_dataset() – a dataset loader for the FGCV-Aircraft dataset. (#156, @DerrickUnleashed)folder_dataset() (#169, @cregouby)annotation_level = "all" in fgvc_aircraft_dataset() (#168, @DerrickUnleashed)nms()and batched_nms() Non-Maximum Suppression, and bounding-box manipulation via box_convert() (#40, @Athospd)caltech101_detection_dataset() and caltech256_detection_dataset() – for the Caltech 101 and 256 datasets. (#158, @DerrickUnleashed)fer_dataset() – a dataset loader for the FER-2013 dataset. (#154, @DerrickUnleashed)zip::unzip added in version 0.4.0. (#89)tinyimagenet-alexnet example (#90, @statist-bhfz)transform_adjust_hue() and transform_linear_transformation() (#72, #73, @sebffischer)draw_bounding_boxes() , draw_segmentation_masks() and draw_keypoints() on top of image tensors, and add a convenience tensor_image_browse() and tensor_image_display() functions to visualize image tensors respectively in browser or in X11 device (#80, @cregouby)nnf_cross_entropy for numerical stability. (#61)zip to zip::unzip the tinyimagenet dataset.torch::enumerate() from docs and tests in favor of coro::loop() (#57)torch. (#58)