Python data.VOC_CLASSES Examples
The following are 30
code examples of data.VOC_CLASSES().
You can vote up the ones you like or vote down the ones you don't like,
and go to the original project or source file by following the links above each example.
You may also want to check out all available functions/classes of the module
data
, or try the search function
.
Example #1
Source File: test.py From CSD-SSD with MIT License | 6 votes |
def test_voc(): # load net num_classes = len(VOC_CLASSES) + 1 # +1 background net = build_ssd('test', 300, num_classes) # initialize SSD net.load_state_dict(torch.load(args.trained_model)) net.eval() print('Finished loading model!') # load data testset = VOCDetection(args.voc_root, [('2007', 'test')], None, VOCAnnotationTransform()) if args.cuda: net = net.cuda() cudnn.benchmark = True # evaluation test_net(args.save_folder, net, args.cuda, testset, BaseTransform(net.size, (104, 117, 123)), thresh=args.visual_threshold)
Example #2
Source File: test.py From ssd.pytorch with MIT License | 6 votes |
def test_voc(): # load net num_classes = len(VOC_CLASSES) + 1 # +1 background net = build_ssd('test', 300, num_classes) # initialize SSD net.load_state_dict(torch.load(args.trained_model)) net.eval() print('Finished loading model!') # load data testset = VOCDetection(args.voc_root, [('2007', 'test')], None, VOCAnnotationTransform()) if args.cuda: net = net.cuda() cudnn.benchmark = True # evaluation test_net(args.save_folder, net, args.cuda, testset, BaseTransform(net.size, (104, 117, 123)), thresh=args.visual_threshold)
Example #3
Source File: test.py From repulsion_loss_ssd with MIT License | 6 votes |
def test_voc(): # load net num_classes = len(VOC_CLASSES) + 1 # +1 background net = build_ssd('test', 300, num_classes) # initialize SSD net.load_state_dict(torch.load(args.trained_model)) net.eval() print('Finished loading model!') # load data testset = VOCDetection(args.voc_root, [('2007', 'test')], None, VOCAnnotationTransform()) if args.cuda: net = net.cuda() cudnn.benchmark = True # evaluation test_net(args.save_folder, net, args.cuda, testset, BaseTransform(net.size, (104, 117, 123)), thresh=args.visual_threshold)
Example #4
Source File: test.py From SSD_resnet_pytorch with MIT License | 6 votes |
def test_voc(): # load net num_classes = len(VOC_CLASSES) + 1 # +1 background net = build_ssd('test',args.model, 300, num_classes) # initialize SSD net.load_state_dict(torch.load(args.trained_model)) net.eval() print('Finished loading model!') # load data testset = VOCDetection(args.voc_root, [('2007', 'test')], None, VOCAnnotationTransform()) if args.cuda: net = net.cuda() cudnn.benchmark = True # evaluation test_net(args.save_folder, net, args.cuda, testset, BaseTransform(net.size, (104, 117, 123)), thresh=args.visual_threshold)
Example #5
Source File: eval512.py From CSD-SSD with MIT License | 5 votes |
def write_voc_results_file(all_boxes, dataset): for cls_ind, cls in enumerate(labelmap): print('Writing {:s} VOC results file'.format(cls)) filename = get_voc_results_file_template(set_type, cls) with open(filename, 'wt') as f: for im_ind, index in enumerate(dataset.ids): dets = all_boxes[cls_ind+1][im_ind] if dets == []: continue # the VOCdevkit expects 1-based indices for k in range(dets.shape[0]): f.write('{:s} {:.3f} {:.1f} {:.1f} {:.1f} {:.1f}\n'. format(index[1], dets[k, -1], dets[k, 0] + 1, dets[k, 1] + 1, dets[k, 2] + 1, dets[k, 3] + 1))
Example #6
Source File: eval_multitrident.py From multitrident with Apache License 2.0 | 5 votes |
def do_python_eval(output_dir='output', use_07=True): cachedir = os.path.join(devkit_path, 'annotations_cache') aps = [] # The PASCAL VOC metric changed in 2010 use_07_metric = use_07 print('VOC07 metric? ' + ('Yes' if use_07_metric else 'No')) if not os.path.isdir(output_dir): os.mkdir(output_dir) for i, cls in enumerate(labelmap): filename = get_voc_results_file_template(set_type, cls) rec, prec, ap = voc_eval( filename, annopath, imgsetpath.format(set_type), cls, cachedir, ovthresh=0.5, use_07_metric=use_07_metric) aps += [ap] print('AP for {} = {:.4f}'.format(cls, ap)) with open(os.path.join(output_dir, cls + '_pr.pkl'), 'wb') as f: pickle.dump({'rec': rec, 'prec': prec, 'ap': ap}, f) print('Mean AP = {:.4f}'.format(np.mean(aps))) print('~~~~~~~~') print('Results:') for ap in aps: print('{:.3f}'.format(ap)) print('{:.3f}'.format(np.mean(aps))) print('~~~~~~~~') print('') print('--------------------------------------------------------------') print('Results computed with the **unofficial** Python eval code.') print('Results should be very close to the official MATLAB eval code.') print('--------------------------------------------------------------')
Example #7
Source File: eval_multitrident.py From multitrident with Apache License 2.0 | 5 votes |
def write_voc_results_file(all_boxes, dataset): for cls_ind, cls in enumerate(labelmap): print('Writing {:s} VOC results file'.format(cls)) filename = get_voc_results_file_template(set_type, cls) with open(filename, 'wt') as f: for im_ind, index in enumerate(dataset.ids): dets = all_boxes[cls_ind+1][im_ind] if dets == []: continue # the VOCdevkit expects 1-based indices for k in range(dets.shape[0]): f.write('{:s} {:.3f} {:.1f} {:.1f} {:.1f} {:.1f}\n'. format(index[1], dets[k, -1], dets[k, 0] + 1, dets[k, 1] + 1, dets[k, 2] + 1, dets[k, 3] + 1))
Example #8
Source File: eval.py From ssd.pytorch with MIT License | 5 votes |
def do_python_eval(output_dir='output', use_07=True): cachedir = os.path.join(devkit_path, 'annotations_cache') aps = [] # The PASCAL VOC metric changed in 2010 use_07_metric = use_07 print('VOC07 metric? ' + ('Yes' if use_07_metric else 'No')) if not os.path.isdir(output_dir): os.mkdir(output_dir) for i, cls in enumerate(labelmap): filename = get_voc_results_file_template(set_type, cls) rec, prec, ap = voc_eval( filename, annopath, imgsetpath.format(set_type), cls, cachedir, ovthresh=0.5, use_07_metric=use_07_metric) aps += [ap] print('AP for {} = {:.4f}'.format(cls, ap)) with open(os.path.join(output_dir, cls + '_pr.pkl'), 'wb') as f: pickle.dump({'rec': rec, 'prec': prec, 'ap': ap}, f) print('Mean AP = {:.4f}'.format(np.mean(aps))) print('~~~~~~~~') print('Results:') for ap in aps: print('{:.3f}'.format(ap)) print('{:.3f}'.format(np.mean(aps))) print('~~~~~~~~') print('') print('--------------------------------------------------------------') print('Results computed with the **unofficial** Python eval code.') print('Results should be very close to the official MATLAB eval code.') print('--------------------------------------------------------------')
Example #9
Source File: eval.py From ssd.pytorch with MIT License | 5 votes |
def write_voc_results_file(all_boxes, dataset): for cls_ind, cls in enumerate(labelmap): print('Writing {:s} VOC results file'.format(cls)) filename = get_voc_results_file_template(set_type, cls) with open(filename, 'wt') as f: for im_ind, index in enumerate(dataset.ids): dets = all_boxes[cls_ind+1][im_ind] if dets == []: continue # the VOCdevkit expects 1-based indices for k in range(dets.shape[0]): f.write('{:s} {:.3f} {:.1f} {:.1f} {:.1f} {:.1f}\n'. format(index[1], dets[k, -1], dets[k, 0] + 1, dets[k, 1] + 1, dets[k, 2] + 1, dets[k, 3] + 1))
Example #10
Source File: eval.py From repulsion_loss_ssd with MIT License | 5 votes |
def do_python_eval(output_dir='output', use_07=True): cachedir = os.path.join(devkit_path, 'annotations_cache') aps = [] # The PASCAL VOC metric changed in 2010 use_07_metric = use_07 print('VOC07 metric? ' + ('Yes' if use_07_metric else 'No')) if not os.path.isdir(output_dir): os.mkdir(output_dir) for i, cls in enumerate(labelmap): filename = get_voc_results_file_template(set_type, cls) rec, prec, ap = voc_eval( filename, annopath, imgsetpath.format(set_type), cls, cachedir, ovthresh=0.5, use_07_metric=use_07_metric) aps += [ap] print('AP for {} = {:.4f}'.format(cls, ap)) with open(os.path.join(output_dir, cls + '_pr.pkl'), 'wb') as f: pickle.dump({'rec': rec, 'prec': prec, 'ap': ap}, f) print('Mean AP = {:.4f}'.format(np.mean(aps))) print('~~~~~~~~') print('Results:') for ap in aps: print('{:.3f}'.format(ap)) print('{:.3f}'.format(np.mean(aps))) print('~~~~~~~~') print('') print('--------------------------------------------------------------') print('Results computed with the **unofficial** Python eval code.') print('Results should be very close to the official MATLAB eval code.') print('--------------------------------------------------------------')
Example #11
Source File: eval.py From repulsion_loss_ssd with MIT License | 5 votes |
def write_voc_results_file(all_boxes, dataset): for cls_ind, cls in enumerate(labelmap): print('Writing {:s} VOC results file'.format(cls)) filename = get_voc_results_file_template(set_type, cls) with open(filename, 'wt') as f: for im_ind, index in enumerate(dataset.ids): dets = all_boxes[cls_ind+1][im_ind] if dets == []: continue # the VOCdevkit expects 1-based indices for k in range(dets.shape[0]): f.write('{:s} {:.3f} {:.1f} {:.1f} {:.1f} {:.1f}\n'. format(index[1], dets[k, -1], dets[k, 0] + 1, dets[k, 1] + 1, dets[k, 2] + 1, dets[k, 3] + 1))
Example #12
Source File: live.py From pytorch-ssd with MIT License | 5 votes |
def cv2_demo(net, transform): def predict(frame): height, width = frame.shape[:2] x = torch.from_numpy(transform(frame)[0]).permute(2, 0, 1) x = Variable(x.unsqueeze(0)) y = net(x) # forward pass detections = y.data # scale each detection back up to the image scale = torch.Tensor([width, height, width, height]) for i in range(detections.size(1)): j = 0 while detections[0, i, j, 0] >= 0.6: pt = (detections[0, i, j, 1:] * scale).cpu().numpy() cv2.rectangle(frame, (int(pt[0]), int(pt[1])), (int(pt[2]), int(pt[3])), COLORS[i % 3], 2) cv2.putText(frame, labelmap[i - 1], (int(pt[0]), int(pt[1])), FONT, 2, (255, 255, 255), 2, cv2.LINE_AA) j += 1 return frame # start video stream thread, allow buffer to fill print("[INFO] starting threaded video stream...") stream = WebcamVideoStream(src=0).start() # default camera time.sleep(1.0) # start fps timer # loop over frames from the video file stream while True: # grab next frame frame = stream.read() key = cv2.waitKey(1) & 0xFF # update FPS counter fps.update() frame = predict(frame) # keybindings for display if key == ord('p'): # pause while True: key2 = cv2.waitKey(1) or 0xff cv2.imshow('frame', frame) if key2 == ord('p'): # resume break cv2.imshow('frame', frame) if key == 27: # exit break
Example #13
Source File: eval.py From SSD_resnet_pytorch with MIT License | 5 votes |
def do_python_eval(output_dir='output', use_07=True): cachedir = os.path.join(devkit_path, 'annotations_cache') aps = [] # The PASCAL VOC metric changed in 2010 use_07_metric = use_07 print('VOC07 metric? ' + ('Yes' if use_07_metric else 'No')) if not os.path.isdir(output_dir): os.mkdir(output_dir) for i, cls in enumerate(labelmap): filename = get_voc_results_file_template(set_type, cls) rec, prec, ap = voc_eval( filename, annopath, imgsetpath.format(set_type), cls, cachedir, ovthresh=0.5, use_07_metric=use_07_metric) aps += [ap] print('AP for {} = {:.4f}'.format(cls, ap)) with open(os.path.join(output_dir, cls + '_pr.pkl'), 'wb') as f: pickle.dump({'rec': rec, 'prec': prec, 'ap': ap}, f) print('Mean AP = {:.4f}'.format(np.mean(aps))) print('~~~~~~~~') print('Results:') for ap in aps: print('{:.3f}'.format(ap)) print('{:.3f}'.format(np.mean(aps))) print('~~~~~~~~') print('') print('--------------------------------------------------------------') print('Results computed with the **unofficial** Python eval code.') print('Results should be very close to the official MATLAB eval code.') print('--------------------------------------------------------------')
Example #14
Source File: eval.py From SSD_resnet_pytorch with MIT License | 5 votes |
def write_voc_results_file(all_boxes, dataset): for cls_ind, cls in enumerate(labelmap): print('Writing {:s} VOC results file'.format(cls)) filename = get_voc_results_file_template(set_type, cls) with open(filename, 'wt') as f: for im_ind, index in enumerate(dataset.ids): dets = all_boxes[cls_ind+1][im_ind] if dets == []: continue # the VOCdevkit expects 1-based indices for k in range(dets.shape[0]): f.write('{:s} {:.3f} {:.1f} {:.1f} {:.1f} {:.1f}\n'. format(index[1], dets[k, -1], dets[k, 0] + 1, dets[k, 1] + 1, dets[k, 2] + 1, dets[k, 3] + 1))
Example #15
Source File: live.py From SSD_resnet_pytorch with MIT License | 5 votes |
def cv2_demo(net, transform): def predict(frame): height, width = frame.shape[:2] x = torch.from_numpy(transform(frame)[0]).permute(2, 0, 1) x = Variable(x.unsqueeze(0)) y = net(x) # forward pass detections = y.data # scale each detection back up to the image scale = torch.Tensor([width, height, width, height]) for i in range(detections.size(1)): j = 0 while detections[0, i, j, 0] >= 0.6: pt = (detections[0, i, j, 1:] * scale).cpu().numpy() cv2.rectangle(frame, (int(pt[0]), int(pt[1])), (int(pt[2]), int(pt[3])), COLORS[i % 3], 2) cv2.putText(frame, labelmap[i - 1], (int(pt[0]), int(pt[1])), FONT, 2, (255, 255, 255), 2, cv2.LINE_AA) j += 1 return frame # start video stream thread, allow buffer to fill print("[INFO] starting threaded video stream...") stream = WebcamVideoStream(src=0).start() # default camera time.sleep(1.0) # start fps timer # loop over frames from the video file stream while True: # grab next frame frame = stream.read() key = cv2.waitKey(1) & 0xFF # update FPS counter fps.update() frame = predict(frame) # keybindings for display if key == ord('p'): # pause while True: key2 = cv2.waitKey(1) or 0xff cv2.imshow('frame', frame) if key2 == ord('p'): # resume break cv2.imshow('frame', frame) if key == 27: # exit break
Example #16
Source File: eval_refinedet.py From RefineDet.PyTorch with MIT License | 5 votes |
def do_python_eval(output_dir='output', use_07=True): cachedir = os.path.join(devkit_path, 'annotations_cache') aps = [] # The PASCAL VOC metric changed in 2010 use_07_metric = use_07 print('VOC07 metric? ' + ('Yes' if use_07_metric else 'No')) if not os.path.isdir(output_dir): os.mkdir(output_dir) for i, cls in enumerate(labelmap): filename = get_voc_results_file_template(set_type, cls) rec, prec, ap = voc_eval( filename, annopath, imgsetpath.format(set_type), cls, cachedir, ovthresh=0.5, use_07_metric=use_07_metric) aps += [ap] print('AP for {} = {:.4f}'.format(cls, ap)) with open(os.path.join(output_dir, cls + '_pr.pkl'), 'wb') as f: pickle.dump({'rec': rec, 'prec': prec, 'ap': ap}, f) print('Mean AP = {:.4f}'.format(np.mean(aps))) print('~~~~~~~~') print('Results:') for ap in aps: print('{:.3f}'.format(ap)) print('{:.3f}'.format(np.mean(aps))) print('~~~~~~~~') print('') print('--------------------------------------------------------------') print('Results computed with the **unofficial** Python eval code.') print('Results should be very close to the official MATLAB eval code.') print('--------------------------------------------------------------')
Example #17
Source File: eval_refinedet.py From RefineDet.PyTorch with MIT License | 5 votes |
def write_voc_results_file(all_boxes, dataset): for cls_ind, cls in enumerate(labelmap): print('Writing {:s} VOC results file'.format(cls)) filename = get_voc_results_file_template(set_type, cls) with open(filename, 'wt') as f: for im_ind, index in enumerate(dataset.ids): dets = all_boxes[cls_ind+1][im_ind] if dets == []: continue # the VOCdevkit expects 1-based indices for k in range(dets.shape[0]): f.write('{:s} {:.3f} {:.1f} {:.1f} {:.1f} {:.1f}\n'. format(index[1], dets[k, -1], dets[k, 0] + 1, dets[k, 1] + 1, dets[k, 2] + 1, dets[k, 3] + 1))
Example #18
Source File: eval512.py From CSD-SSD with MIT License | 5 votes |
def do_python_eval(output_dir='output', use_07=True): cachedir = os.path.join(devkit_path, 'annotations_cache') aps = [] # The PASCAL VOC metric changed in 2010 use_07_metric = use_07 print('VOC07 metric? ' + ('Yes' if use_07_metric else 'No')) if not os.path.isdir(output_dir): os.mkdir(output_dir) for i, cls in enumerate(labelmap): filename = get_voc_results_file_template(set_type, cls) rec, prec, ap = voc_eval( filename, annopath, imgsetpath.format(set_type), cls, cachedir, ovthresh=0.5, use_07_metric=use_07_metric) aps += [ap] print('AP for {} = {:.4f}'.format(cls, ap)) with open(os.path.join(output_dir, cls + '_pr.pkl'), 'wb') as f: pickle.dump({'rec': rec, 'prec': prec, 'ap': ap}, f) print('Mean AP = {:.4f}'.format(np.mean(aps))) print('~~~~~~~~') print('Results:') for ap in aps: print('{:.3f}'.format(ap)) print('{:.3f}'.format(np.mean(aps))) print('~~~~~~~~') print('') print('--------------------------------------------------------------') print('Results computed with the **unofficial** Python eval code.') print('Results should be very close to the official MATLAB eval code.') print('--------------------------------------------------------------')
Example #19
Source File: eval_refinedetlite_voc.py From RefinedetLite.pytorch with MIT License | 5 votes |
def do_python_eval(output_dir='output', use_07=True): cachedir = os.path.join(devkit_path, 'annotations_cache') aps = [] # The PASCAL VOC metric changed in 2010 use_07_metric = use_07 print('VOC07 metric? ' + ('Yes' if use_07_metric else 'No')) if not os.path.isdir(output_dir): os.mkdir(output_dir) for i, cls in enumerate(labelmap): filename = get_voc_results_file_template(set_type, cls) rec, prec, ap = voc_eval( filename, annopath, imgsetpath.format(set_type), cls, cachedir, ovthresh=0.5, use_07_metric=use_07_metric) aps += [ap] print('AP for {} = {:.4f}'.format(cls, ap)) with open(os.path.join(output_dir, cls + '_pr.pkl'), 'wb') as f: pickle.dump({'rec': rec, 'prec': prec, 'ap': ap}, f) print('Mean AP = {:.4f}'.format(np.mean(aps))) print('~~~~~~~~') print('Results:') for ap in aps: print('{:.3f}'.format(ap)) print('{:.3f}'.format(np.mean(aps))) print('~~~~~~~~') print('') print('--------------------------------------------------------------') print('Results computed with the **unofficial** Python eval code.') print('Results should be very close to the official MATLAB eval code.') print('--------------------------------------------------------------')
Example #20
Source File: eval_refinedetlite_voc.py From RefinedetLite.pytorch with MIT License | 5 votes |
def write_voc_results_file(all_boxes, dataset): for cls_ind, cls in enumerate(labelmap): print('Writing {:s} VOC results file'.format(cls)) filename = get_voc_results_file_template(set_type, cls) with open(filename, 'wt') as f: for im_ind, index in enumerate(dataset.ids): dets = all_boxes[cls_ind+1][im_ind] if dets == []: continue # the VOCdevkit expects 1-based indices for k in range(dets.shape[0]): f.write('{:s} {:.3f} {:.1f} {:.1f} {:.1f} {:.1f}\n'. format(index[1], dets[k, -1], dets[k, 0] + 1, dets[k, 1] + 1, dets[k, 2] + 1, dets[k, 3] + 1))
Example #21
Source File: eval.py From CSD-SSD with MIT License | 5 votes |
def do_python_eval(output_dir='output', use_07=True): cachedir = os.path.join(devkit_path, 'annotations_cache') aps = [] # The PASCAL VOC metric changed in 2010 use_07_metric = use_07 print('VOC07 metric? ' + ('Yes' if use_07_metric else 'No')) if not os.path.isdir(output_dir): os.mkdir(output_dir) for i, cls in enumerate(labelmap): filename = get_voc_results_file_template(set_type, cls) rec, prec, ap = voc_eval( filename, annopath, imgsetpath.format(set_type), cls, cachedir, ovthresh=0.5, use_07_metric=use_07_metric) aps += [ap] print('AP for {} = {:.4f}'.format(cls, ap)) with open(os.path.join(output_dir, cls + '_pr.pkl'), 'wb') as f: pickle.dump({'rec': rec, 'prec': prec, 'ap': ap}, f) print('Mean AP = {:.4f}'.format(np.mean(aps))) print('~~~~~~~~') print('Results:') for ap in aps: print('{:.3f}'.format(ap)) print('{:.3f}'.format(np.mean(aps))) print('~~~~~~~~') print('') print('--------------------------------------------------------------') print('Results computed with the **unofficial** Python eval code.') print('Results should be very close to the official MATLAB eval code.') print('--------------------------------------------------------------')
Example #22
Source File: eval_multitrident.py From multitrident with Apache License 2.0 | 4 votes |
def test_net(save_folder, net, cuda, dataset, transform, top_k, im_size=300, thresh=0.05): num_images = len(dataset) # all detections are collected into: # all_boxes[cls][image] = N x 5 array of detections in # (x1, y1, x2, y2, score) all_boxes = [[[] for _ in range(num_images)] for _ in range(len(labelmap)+1)] # timers _t = {'im_detect': Timer(), 'misc': Timer()} output_dir = get_output_dir('gaijin6_175000', set_type) det_file = os.path.join(output_dir, 'detections.pkl') for i in range(num_images): im, gt, h, w = dataset.pull_item(i) x = Variable(im.unsqueeze(0)) if args.cuda: x = x.cuda() _t['im_detect'].tic() detections = net(x).data detect_time = _t['im_detect'].toc(average=False) # skip j = 0, because it's the background class for j in range(1, detections.size(1)): dets = detections[0, j, :] mask = dets[:, 0].gt(0.).expand(5, dets.size(0)).t() dets = torch.masked_select(dets, mask).view(-1, 5) if dets.size(0) == 0: continue boxes = dets[:, 1:] boxes[:, 0] *= w boxes[:, 2] *= w boxes[:, 1] *= h boxes[:, 3] *= h scores = dets[:, 0].cpu().numpy() """do threshold for scores, delet scores < thresh""" scores = scores[np.where(scores > thresh)] boxes = boxes[np.where(scores > thresh)] if boxes.size(0) == 0: continue cls_dets = np.hstack((boxes.cpu().numpy(), scores[:, np.newaxis])).astype(np.float32, copy=False) all_boxes[j][i] = cls_dets print('im_detect: {:d}/{:d} {:.3f}s'.format(i + 1, num_images, detect_time)) with open(det_file, 'wb') as f: pickle.dump(all_boxes, f, pickle.HIGHEST_PROTOCOL) print('Evaluating detections') evaluate_detections(all_boxes, output_dir, dataset)
Example #23
Source File: live.py From RefineDet.PyTorch with MIT License | 4 votes |
def cv2_demo(net, transform): def predict(frame): height, width = frame.shape[:2] x = torch.from_numpy(transform(frame)[0]).permute(2, 0, 1) x = Variable(x.unsqueeze(0)) y = net(x) # forward pass detections = y.data # scale each detection back up to the image scale = torch.Tensor([width, height, width, height]) for i in range(detections.size(1)): j = 0 while detections[0, i, j, 0] >= 0.6: pt = (detections[0, i, j, 1:] * scale).cpu().numpy() cv2.rectangle(frame, (int(pt[0]), int(pt[1])), (int(pt[2]), int(pt[3])), COLORS[i % 3], 2) cv2.putText(frame, labelmap[i - 1], (int(pt[0]), int(pt[1])), FONT, 2, (255, 255, 255), 2, cv2.LINE_AA) j += 1 return frame # start video stream thread, allow buffer to fill print("[INFO] starting threaded video stream...") stream = WebcamVideoStream(src=0).start() # default camera time.sleep(1.0) # start fps timer # loop over frames from the video file stream while True: # grab next frame frame = stream.read() key = cv2.waitKey(1) & 0xFF # update FPS counter fps.update() frame = predict(frame) # keybindings for display if key == ord('p'): # pause while True: key2 = cv2.waitKey(1) or 0xff cv2.imshow('frame', frame) if key2 == ord('p'): # resume break cv2.imshow('frame', frame) if key == 27: # exit break
Example #24
Source File: live.py From CSD-SSD with MIT License | 4 votes |
def cv2_demo(net, transform): def predict(frame): height, width = frame.shape[:2] x = torch.from_numpy(transform(frame)[0]).permute(2, 0, 1) x = Variable(x.unsqueeze(0)) y = net(x) # forward pass detections = y.data # scale each detection back up to the image scale = torch.Tensor([width, height, width, height]) for i in range(detections.size(1)): j = 0 while detections[0, i, j, 0] >= 0.6: pt = (detections[0, i, j, 1:] * scale).cpu().numpy() cv2.rectangle(frame, (int(pt[0]), int(pt[1])), (int(pt[2]), int(pt[3])), COLORS[i % 3], 2) cv2.putText(frame, labelmap[i - 1], (int(pt[0]), int(pt[1])), FONT, 2, (255, 255, 255), 2, cv2.LINE_AA) j += 1 return frame # start video stream thread, allow buffer to fill print("[INFO] starting threaded video stream...") stream = WebcamVideoStream(src=0).start() # default camera time.sleep(1.0) # start fps timer # loop over frames from the video file stream while True: # grab next frame frame = stream.read() key = cv2.waitKey(1) & 0xFF # update FPS counter fps.update() frame = predict(frame) # keybindings for display if key == ord('p'): # pause while True: key2 = cv2.waitKey(1) or 0xff cv2.imshow('frame', frame) if key2 == ord('p'): # resume break cv2.imshow('frame', frame) if key == 27: # exit break
Example #25
Source File: live.py From multitrident with Apache License 2.0 | 4 votes |
def cv2_demo(net, transform): def predict(frame): height, width = frame.shape[:2] x = torch.from_numpy(transform(frame)[0]).permute(2, 0, 1) x = Variable(x.unsqueeze(0)) y = net(x) # forward pass detections = y.data # scale each detection back up to the image scale = torch.Tensor([width, height, width, height]) for i in range(detections.size(1)): j = 0 while detections[0, i, j, 0] >= 0.6: pt = (detections[0, i, j, 1:] * scale).cpu().numpy() cv2.rectangle(frame, (int(pt[0]), int(pt[1])), (int(pt[2]), int(pt[3])), COLORS[i % 3], 2) cv2.putText(frame, labelmap[i - 1], (int(pt[0]), int(pt[1])), FONT, 2, (255, 255, 255), 2, cv2.LINE_AA) j += 1 return frame # start video stream thread, allow buffer to fill print("[INFO] starting threaded video stream...") stream = WebcamVideoStream(src=0).start() # default camera time.sleep(1.0) # start fps timer # loop over frames from the video file stream while True: # grab next frame frame = stream.read() key = cv2.waitKey(1) & 0xFF # update FPS counter fps.update() frame = predict(frame) # keybindings for display if key == ord('p'): # pause while True: key2 = cv2.waitKey(1) or 0xff cv2.imshow('frame', frame) if key2 == ord('p'): # resume break cv2.imshow('frame', frame) if key == 27: # exit break
Example #26
Source File: eval.py From ssd.pytorch with MIT License | 4 votes |
def test_net(save_folder, net, cuda, dataset, transform, top_k, im_size=300, thresh=0.05): num_images = len(dataset) # all detections are collected into: # all_boxes[cls][image] = N x 5 array of detections in # (x1, y1, x2, y2, score) all_boxes = [[[] for _ in range(num_images)] for _ in range(len(labelmap)+1)] # timers _t = {'im_detect': Timer(), 'misc': Timer()} output_dir = get_output_dir('ssd300_120000', set_type) det_file = os.path.join(output_dir, 'detections.pkl') for i in range(num_images): im, gt, h, w = dataset.pull_item(i) x = Variable(im.unsqueeze(0)) if args.cuda: x = x.cuda() _t['im_detect'].tic() detections = net(x).data detect_time = _t['im_detect'].toc(average=False) # skip j = 0, because it's the background class for j in range(1, detections.size(1)): dets = detections[0, j, :] mask = dets[:, 0].gt(0.).expand(5, dets.size(0)).t() dets = torch.masked_select(dets, mask).view(-1, 5) if dets.size(0) == 0: continue boxes = dets[:, 1:] boxes[:, 0] *= w boxes[:, 2] *= w boxes[:, 1] *= h boxes[:, 3] *= h scores = dets[:, 0].cpu().numpy() cls_dets = np.hstack((boxes.cpu().numpy(), scores[:, np.newaxis])).astype(np.float32, copy=False) all_boxes[j][i] = cls_dets print('im_detect: {:d}/{:d} {:.3f}s'.format(i + 1, num_images, detect_time)) with open(det_file, 'wb') as f: pickle.dump(all_boxes, f, pickle.HIGHEST_PROTOCOL) print('Evaluating detections') evaluate_detections(all_boxes, output_dir, dataset)
Example #27
Source File: eval512.py From CSD-SSD with MIT License | 4 votes |
def test_net(save_folder, net, cuda, dataset, transform, top_k, im_size=512, thresh=0.05): num_images = len(dataset) # all detections are collected into: # all_boxes[cls][image] = N x 5 array of detections in # (x1, y1, x2, y2, score) all_boxes = [[[] for _ in range(num_images)] for _ in range(len(labelmap)+1)] # timers _t = {'im_detect': Timer(), 'misc': Timer()} output_dir = get_output_dir('ssd300_120000', set_type) det_file = os.path.join(output_dir, 'detections.pkl') for i in range(num_images): im, gt, h, w = dataset.pull_item(i) x = Variable(im.unsqueeze(0)) if args.cuda: x = x.cuda() _t['im_detect'].tic() detections = net(x).data detect_time = _t['im_detect'].toc(average=False) # skip j = 0, because it's the background class for j in range(1, detections.size(1)): dets = detections[0, j, :] mask = dets[:, 0].gt(0.).expand(5, dets.size(0)).t() dets = torch.masked_select(dets, mask).view(-1, 5) if dets.dim() == 0: continue boxes = dets[:, 1:] boxes[:, 0] *= w boxes[:, 2] *= w boxes[:, 1] *= h boxes[:, 3] *= h scores = dets[:, 0].cpu().numpy() cls_dets = np.hstack((boxes.cpu().numpy(), scores[:, np.newaxis])).astype(np.float32, copy=False) all_boxes[j][i] = cls_dets print('im_detect: {:d}/{:d} {:.3f}s'.format(i + 1, num_images, detect_time)) with open(det_file, 'wb') as f: pickle.dump(all_boxes, f, pickle.HIGHEST_PROTOCOL) print('Evaluating detections') evaluate_detections(all_boxes, output_dir, dataset)
Example #28
Source File: eval.py From CSD-SSD with MIT License | 4 votes |
def test_net(save_folder, net, cuda, dataset, transform, top_k, im_size=300, thresh=0.05): num_images = len(dataset) # all detections are collected into: # all_boxes[cls][image] = N x 5 array of detections in # (x1, y1, x2, y2, score) all_boxes = [[[] for _ in range(num_images)] for _ in range(len(labelmap)+1)] # timers _t = {'im_detect': Timer(), 'misc': Timer()} output_dir = get_output_dir('ssd300_120000', set_type) det_file = os.path.join(output_dir, 'detections.pkl') for i in range(num_images): im, gt, h, w = dataset.pull_item(i) x = Variable(im.unsqueeze(0)) if args.cuda: x = x.cuda() _t['im_detect'].tic() detections = net(x).data detect_time = _t['im_detect'].toc(average=False) # skip j = 0, because it's the background class for j in range(1, detections.size(1)): dets = detections[0, j, :] mask = dets[:, 0].gt(0.).expand(5, dets.size(0)).t() dets = torch.masked_select(dets, mask).view(-1, 5) if dets.dim() == 0: continue boxes = dets[:, 1:] boxes[:, 0] *= w boxes[:, 2] *= w boxes[:, 1] *= h boxes[:, 3] *= h scores = dets[:, 0].cpu().numpy() cls_dets = np.hstack((boxes.cpu().numpy(), scores[:, np.newaxis])).astype(np.float32, copy=False) all_boxes[j][i] = cls_dets print('im_detect: {:d}/{:d} {:.3f}s'.format(i + 1, num_images, detect_time)) with open(det_file, 'wb') as f: pickle.dump(all_boxes, f, pickle.HIGHEST_PROTOCOL) print('Evaluating detections') evaluate_detections(all_boxes, output_dir, dataset)
Example #29
Source File: live.py From ssd.pytorch with MIT License | 4 votes |
def cv2_demo(net, transform): def predict(frame): height, width = frame.shape[:2] x = torch.from_numpy(transform(frame)[0]).permute(2, 0, 1) x = Variable(x.unsqueeze(0)) y = net(x) # forward pass detections = y.data # scale each detection back up to the image scale = torch.Tensor([width, height, width, height]) for i in range(detections.size(1)): j = 0 while detections[0, i, j, 0] >= 0.6: pt = (detections[0, i, j, 1:] * scale).cpu().numpy() cv2.rectangle(frame, (int(pt[0]), int(pt[1])), (int(pt[2]), int(pt[3])), COLORS[i % 3], 2) cv2.putText(frame, labelmap[i - 1], (int(pt[0]), int(pt[1])), FONT, 2, (255, 255, 255), 2, cv2.LINE_AA) j += 1 return frame # start video stream thread, allow buffer to fill print("[INFO] starting threaded video stream...") stream = WebcamVideoStream(src=0).start() # default camera time.sleep(1.0) # start fps timer # loop over frames from the video file stream while True: # grab next frame frame = stream.read() key = cv2.waitKey(1) & 0xFF # update FPS counter fps.update() frame = predict(frame) # keybindings for display if key == ord('p'): # pause while True: key2 = cv2.waitKey(1) or 0xff cv2.imshow('frame', frame) if key2 == ord('p'): # resume break cv2.imshow('frame', frame) if key == 27: # exit break
Example #30
Source File: eval.py From repulsion_loss_ssd with MIT License | 4 votes |
def test_net(save_folder, net, cuda, dataset, transform, top_k, im_size=300, thresh=0.05): num_images = len(dataset) # all detections are collected into: # all_boxes[cls][image] = N x 5 array of detections in # (x1, y1, x2, y2, score) all_boxes = [[[] for _ in range(num_images)] for _ in range(len(labelmap)+1)] # timers _t = {'im_detect': Timer(), 'misc': Timer()} output_dir = get_output_dir('ssd300_120000', set_type) det_file = os.path.join(output_dir, 'detections.pkl') for i in range(num_images): im, gt, h, w = dataset.pull_item(i) x = Variable(im.unsqueeze(0)) if args.cuda: x = x.cuda() _t['im_detect'].tic() detections = net(x).data detect_time = _t['im_detect'].toc(average=False) # skip j = 0, because it's the background class for j in range(1, detections.size(1)): dets = detections[0, j, :] mask = dets[:, 0].gt(0.).expand(5, dets.size(0)).t() dets = torch.masked_select(dets, mask).view(-1, 5) if dets.dim() == 0: continue boxes = dets[:, 1:] boxes[:, 0] *= w boxes[:, 2] *= w boxes[:, 1] *= h boxes[:, 3] *= h scores = dets[:, 0].cpu().numpy() cls_dets = np.hstack((boxes.cpu().numpy(), scores[:, np.newaxis])).astype(np.float32, copy=False) all_boxes[j][i] = cls_dets print('im_detect: {:d}/{:d} {:.3f}s'.format(i + 1, num_images, detect_time)) with open(det_file, 'wb') as f: pickle.dump(all_boxes, f, pickle.HIGHEST_PROTOCOL) print('Evaluating detections') evaluate_detections(all_boxes, output_dir, dataset)