Research Project

(1) put a figure and table in one row: https://tex.stackexchange.com/questions/6850/table-and-figure-side-by-side-with-independent-captions

1. Pascal VOC(eval_thre=0.5)

##---------------------------------------- 0.common summary ------------------------------------------- ## This project including two parts: /home/uni/Lab/projects/Python/pytorch-pairwise 1. py-faster-rcnn 2. pytorch-pairwise ##--------------------------------------1. PETS  dataset -------------------------------------------------- ## (1) training: (2)inference: (3) evaluation: $ faster-rcnn/ pairwise_learning/ pets / eval_dpm_dets.py ' (4)method: 1> using gt_mat to test the improved performance. $ pytorch-pairwise/ mot / pairwise_matrix.py

##---------------------------------------------------------------------------------------------------------------## dets: ( len(dets)=81, type: <class 'list'>  ) dets[categaroies][image_ids] type (dets[ 1 ][ 0 ])= <class 'numpy.ndarray'> or = <class 'list'> if len(dets[i][j])>0:    dets[i][j].shape=(n_dets, 5)   for each row, it's  x1, y1, x2, y2, score ##-------------------------------------------------------------------------------------------------------------- ## det_im_ids: ( len(det_im_ids)=82783 , type: <class 'list'>) [262118, 283985, 393193, ....... , 131067, 524286, 43645] ##---------------------------------------------------------------------------------------------------------------## cat_ids: ( len(cat_ids)=81 , type: <class 'list'>)  [-1, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 27, 28, 31, 32, 33, 34, 35, 36, 37, 38, 39, 4...

trainning: len(dataset['images'])=1696     =number of images len (dataset[ 'annotations' ])=23107 = number of detections ##==================================================================== k: categories v: [{'id': 1, 'name': 'pedestrian', 'supercategory': 'pedestrian'}] ##------------------------------------------------------------------------------------------------------- ## k: annotations v: dataset[ 'annotations' ][ 0 ] {'id': 11, 'area': 4558.0, 'iscrowd': 0, 'bbox': [719.0, 296.0, 43.0, 106.0], 'category_id': 1, 'image_id': 1} ##-------------------------------------------------------------------------------------------------------- ## k: info v: {'description': 'PETS training set: seqences S1*, S2L1, S3MF1', 'year': 1745, 'version': '1.0'} ##-----------------------------------------------------------...

1.dataset ##---------------------------------------------------------------------------------------------------------------## k: images v: : dataset[ 'images' ][ 0 ] {'file_name': 'COCO_train2014_000000057870.jpg', 'height': 480, 'flickr_url': 'http://farm4.staticflickr.com/3153/2970773875_164f0c0b83_z.jpg', 'id': 57870, 'license': 5, 'width': 640, 'date_captured': '2013-11-14 16:28:13', 'coco_url': 'http://images.cocodataset.org/train2014/COCO_train2014_000000057870.jpg'} ##---------------------------------------------------------------------------------------------------------------## k: annotations v: dataset[ 'annotations' ][ 0 ] {'id': 86, 'area': 54652.9556, 'image_id': 480023, 'bbox': [116.95, 305.86, 285.3, 266.03], 'segmentation': [[312.29, 562.89, 402.25, 511.49, 400.96, 425.38, 398.39, 372.69, 388.11, 332.8...