文件列表:

articles (0, 2016-06-15)
articles\discriminative_deep_model.pdf (908947, 2016-06-15)
articles\joint_deep.pdf (852240, 2016-06-15)
image-preproc (0, 2016-06-15)
image-preproc\cvt_rgb2yuv.py (930, 2016-06-15)
image-preproc\extract_kitti_negatives.py (3402, 2016-06-15)
image-preproc\extract_kitti_pedestrians.py (4395, 2016-06-15)
image-preproc\prepare_images.py (5519, 2016-06-15)
joint-deep (0, 2016-06-15)
joint-deep\impl (0, 2016-06-15)
joint-deep\impl\dt.lua (1782, 2016-06-15)
joint-deep\impl\init.lua (2217, 2016-06-15)
joint-deep\impl\model.lua (8759, 2016-06-15)
joint-deep\impl\nn-init (0, 2016-06-15)
joint-deep\impl\nn-init\layer2_bias.txt (673, 2016-06-15)
joint-deep\impl\nn-init\layer2_kernels.txt (165565, 2016-06-15)
joint-deep\impl\nn-init\layer4_bias.txt (224, 2016-06-15)
joint-deep\impl\nn-init\layer4_kernels.txt (424937, 2016-06-15)
joint-deep\impl\test-out (0, 2016-06-15)
joint-deep\impl\test-out\CaltechTest (0, 2016-06-15)
joint-deep\impl\test-out\CaltechTest\caltech_train.txt (385167, 2016-06-15)
joint-deep\impl\test-out\CaltechTest\inria_train.txt (389974, 2016-06-15)
joint-deep\impl\test-out\CaltechTest\kitti.txt (385962, 2016-06-15)
joint-deep\impl\test-out\ETH (0, 2016-06-15)
joint-deep\impl\test-out\ETH\caltech_train.txt (547017, 2016-06-15)
joint-deep\impl\test-out\ETH\inria_train.txt (554551, 2016-06-15)
joint-deep\impl\test-out\ETH\kitti.txt (544985, 2016-06-15)
joint-deep\impl\test_example.lua (3201, 2016-06-15)
joint-deep\impl\torch_extra.lua (8441, 2016-06-15)
joint-deep\impl\train_example.lua (4710, 2016-06-15)
joint-deep\impl\utils.lua (478, 2016-06-15)
joint-deep\prepare-data (0, 2016-06-15)
joint-deep\prepare-data\extract_images_inria.m (1336, 2016-06-15)
joint-deep\prepare-data\extract_train_data.m (871, 2016-06-15)
joint-deep\prepare-data\get_images.m (701, 2016-06-15)
joint-deep\prepare-data\join_datasets.m (1676, 2016-06-15)
joint-deep\prepare-data\prepare_images.py (2679, 2016-06-15)
... ...

# Pedestrian detection benchmark ## What is it ITLab-Vision pedestrian detection benchmark has been created to compare the state-of-the-art pedestrian detection approaches. To be exact the benchmark oriented to deep learning methods. ## Where the training and testing data We implement the methods that described in [Caltech Pedestrian Detection Benchmark](http://www.vision.caltech.edu/Image_Datasets/CaltechPedestrians/) and we use the training and testing data that are stored in this benchmark.

近期下载者：

相关文件：

评论：[我要评论] [举报此文件]

收藏者：