def loop():
args = parse_args()
print('Called with args:')
print(args)
if torch.cuda.is_available() and not args.cuda:
print("WARNING: You have a CUDA device, so you should probably run with --cuda")
if args.dataset == "pascal_voc":
args.imdb_name = "voc_2007_test"
args.imdbval_name = "voc_2007_test"
args.set_cfgs = ['ANCHOR_SCALES', '[8, 16, 32]', 'ANCHOR_RATIOS', '[0.5,1,2]']
elif args.dataset == "pascal_voc_0712":
args.imdb_name = "voc_2007_trainval+voc_2012_trainval"
args.imdbval_name = "voc_2007_test"
args.set_cfgs = ['ANCHOR_SCALES', '[8, 16, 32]', 'ANCHOR_RATIOS', '[0.5,1,2]']
elif args.dataset == "coco":
args.imdb_name = "coco_2014_train+coco_2014_valminusminival"
args.imdbval_name = "coco_2014_minival"
args.set_cfgs = ['ANCHOR_SCALES', '[4, 8, 16, 32]', 'ANCHOR_RATIOS', '[0.5,1,2]']
elif args.dataset == "imagenet":
args.imdb_name = "imagenet_train"
args.imdbval_name = "imagenet_val"
args.set_cfgs = ['ANCHOR_SCALES', '[8, 16, 32]', 'ANCHOR_RATIOS', '[0.5,1,2]']
elif args.dataset == "vg":
args.imdb_name = "vg_150-50-50_minitrain"
args.imdbval_name = "vg_150-50-50_minival"
args.set_cfgs = ['ANCHOR_SCALES', '[4, 8, 16, 32]', 'ANCHOR_RATIOS', '[0.5,1,2]']
args.cfg_file = "cfgs/{}.yml".format(args.net)
if args.cfg_file is not None:
cfg_from_file(args.cfg_file)
if args.set_cfgs is not None:
cfg_from_list(args.set_cfgs)
print('Using config:')
pprint.pprint(cfg)
np.random.seed(cfg.RNG_SEED)
cfg.TRAIN.USE_FLIPPED = False
imdb, roidb, ratio_list, ratio_index = combined_roidb(args.imdbval_name, False)
imdb.competition_mode(on=True)
print('{:d} roidb entries'.format(len(roidb)))
# initilize the network here.
if args.net == 'vgg16':
fpn = vgg16(imdb.classes, pretrained=False, class_agnostic=args.class_agnostic)
elif args.net == 'res101':
fpn = resnet(imdb.classes, 101, pretrained=False, class_agnostic=args.class_agnostic)
elif args.net == 'res50':
fpn = resnet(imdb.classes, 50, pretrained=True, class_agnostic=args.class_agnostic)
elif args.net == 'res152':
fpn = resnet(imdb.classes, 152, pretrained=True, class_agnostic=args.class_agnostic)
else:
print("network is not defined")
pdb.set_trace()
fpn.create_architecture()
print('load model successfully!')
im_data = torch.FloatTensor(1)
im_info = torch.FloatTensor(1)
num_boxes = torch.LongTensor(1)
gt_boxes = torch.FloatTensor(1)
# ship to cuda
if args.cuda:
im_data = im_data.cuda()
im_info = im_info.cuda()
num_boxes = num_boxes.cuda()
gt_boxes = gt_boxes.cuda()
# make variable
im_data = Variable(im_data)
im_info = Variable(im_info)
num_boxes = Variable(num_boxes)
gt_boxes = Variable(gt_boxes)
if args.cuda:
cfg.CUDA = True
if args.cuda:
fpn.cuda()
start = time.time()
max_per_image = 100
vis =True #args.vis
if vis:
thresh = 0.0
else:
thresh = 0.0
save_name = 'faster_rcnn_10'
num_images = len(imdb.image_index)
all_boxes = [[[] for _ in range(num_images)]
for _ in range(imdb.num_classes)]
output_dir = get_output_dir(imdb, save_name)
for h in range(200):
dataset = roibatchLoader(roidb, ratio_list, ratio_index, args.batch_size, \
imdb.num_classes, training=False, normalize=False)
dataloader = torch.utils.data.DataLoader(dataset, batch_size=args.batch_size,
shuffle=False, num_workers=0,
pin_memory=True)
data_iter = iter(dataloader)
_t = {'im_detect': time.time(), 'misc': time.time()}
det_file = os.path.join(output_dir, 'detections.pkl')
input_dir = args.load_dir + "/" + args.net + "/" + args.dataset
if not os.path.exists(input_dir):
raise Exception('There is no input directory for loading network from ' + input_dir)
load_name = os.path.join(input_dir,
'fpn_{}_{}_{}.pth'.format(args.checksession, args.checkepoch, args.checkpoint))
print("load checkpoint %s" % (load_name))
checkpoint = torch.load(load_name)
fpn.load_state_dict(checkpoint['model'])
if 'pooling_mode' in checkpoint.keys():
cfg.POOLING_MODE = checkpoint['pooling_mode']
fpn.eval()
empty_array = np.transpose(np.array([[], [], [], [], []]), (1, 0))
for i in range(num_images):
data = data_iter.next()
im_data.data.resize_(data[0].size()).copy_(data[0])
im_info.data.resize_(data[1].size()).copy_(data[1])
gt_boxes.data.resize_(data[2].size()).copy_(data[2])
num_boxes.data.resize_(data[3].size()).copy_(data[3])
det_tic = time.time()
rois, cls_prob, bbox_pred, \
_, _, _, _, _ = fpn(im_data, im_info, gt_boxes, num_boxes)
scores = cls_prob.data # 1*300*10
boxes = rois.data[:, :, 1:5] # 1*300*4
if cfg.TEST.BBOX_REG:
# Apply bounding-box regression deltas
box_deltas = bbox_pred.data # 1*300*40
if cfg.TRAIN.BBOX_NORMALIZE_TARGETS_PRECOMPUTED:
# Optionally normalize targets by a precomputed mean and stdev
if args.class_agnostic:
box_deltas = box_deltas.view(-1, 4) * torch.FloatTensor(cfg.TRAIN.BBOX_NORMALIZE_STDS).cuda() \
+ torch.FloatTensor(cfg.TRAIN.BBOX_NORMALIZE_MEANS).cuda()
box_deltas = box_deltas.view(1, -1, 4)
else:
box_deltas = box_deltas.view(-1, 4) * torch.FloatTensor(cfg.TRAIN.BBOX_NORMALIZE_STDS).cuda() \
+ torch.FloatTensor(cfg.TRAIN.BBOX_NORMALIZE_MEANS).cuda()
box_deltas = box_deltas.view(1, -1, 4 * len(imdb.classes))
pred_boxes = bbox_transform_inv(boxes, box_deltas, 1)
pred_boxes = clip_boxes(pred_boxes, im_info.data, 1)
else:
# Simply repeat the boxes, once for each class
pred_boxes = boxes
pred_boxes /= data[1][0][2].cuda()
scores = scores.squeeze()
pred_boxes = pred_boxes.squeeze()
det_toc = time.time()
detect_time = det_toc - det_tic
misc_tic = time.time()
if vis:
im = cv2.imread(imdb.image_path_at(i))
im2show = np.copy(im)
for j in range(1, imdb.num_classes):
inds = torch.nonzero(scores[:, j] > thresh).view(-1)
# if there is det
if inds.numel() > 0:
cls_scores = scores[:, j][inds]
_, order = torch.sort(cls_scores, 0, True)
if args.class_agnostic:
cls_boxes = pred_boxes[inds, :]
else:
cls_boxes = pred_boxes[inds][:, j * 4:(j + 1) * 4]
cls_dets = torch.cat((cls_boxes, cls_scores.unsqueeze(1)), 1)
# cls_dets = torch.cat((cls_boxes, cls_scores), 1)
cls_dets = cls_dets[order]
keep = nms(cls_dets, cfg.TEST.NMS,~args.cuda)
cls_dets = cls_dets[keep.view(-1).long()]
if vis:
im2show = vis_detections(im2show, imdb.classes[j], cls_dets.cpu().numpy(), 0.3)
all_boxes[j][i] = cls_dets.cpu().numpy()
else:
all_boxes[j][i] = empty_array
# Limit to max_per_image detections *over all classes*
if max_per_image > 0:
image_scores = np.hstack([all_boxes[j][i][:, -1]
for j in range(1, imdb.num_classes)])
if len(image_scores) > max_per_image:
image_thresh = np.sort(image_scores)[-max_per_image]
for j in range(1, imdb.num_classes):
keep = np.where(all_boxes[j][i][:, -1] >= image_thresh)[0]
all_boxes[j][i] = all_boxes[j][i][keep, :]
misc_toc = time.time()
nms_time = misc_toc - misc_tic
sys.stdout.write('im_detect: {:d}/{:d} {:.3f}s {:.3f}s \r' \
.format(i + 1, num_images, detect_time, nms_time))
sys.stdout.flush()
if vis:
cv2.imwrite('images/result%d_%d.png' %(args.checkepoch,i), im2show)
#pdb.set_trace()
# cv2.imshow('test', im2show)
# cv2.waitKey(0)
del data
del pred_boxes
del scores
torch.cuda.empty_cache()
with open(det_file, 'wb') as f:
cPickle.dump(all_boxes, f, cPickle.HIGHEST_PROTOCOL)
print('Evaluating detections')
aps, clss = imdb.evaluate_detections(all_boxes, output_dir)
#print(aps)
with open("result.txt", 'a+') as f:
# print(args.checkepoch)
lp=""
cc=0
for b in clss:
if cc!=len(clss)-1:
lp=lp+"'"+str(b) + ":" + str(aps[cc])+"',"
else:
lp = lp + "'" + str(b) + ":" + str(aps[cc])+"'"
cc=cc+1
sp = "["+lp+ "] ls:" + str(args.checksession) + "_" + str(args.checkepoch)
# print(sp)
f.write(sp + "\n")
end = time.time()
print("test time: %0.4fs" % (end - start))
args.checkepoch = args.checkepoch + 1
del data_iter
del dataset
del dataloader
torch.cuda.empty_cache()
#torch.empty_cache()
gc.collect()
if torch.cuda.is_available() and not args.cuda:
print("WARNING: You have a CUDA device, so you should probably run with --cuda")
# train set
# -- Note: Use validation set and disable the flipped to enable faster loading.
cfg.TRAIN.USE_FLIPPED = False
cfg.USE_GPU_NMS = args.cuda
if args.use_det:
print("Using VID and DET datasets.")
imdb_names = args.imdb_name.split('+')
assert len(imdb_names) < 3, 'Cannot handle > 2 datasets when using VID and DET.'
# vid and det
#print(imdb_names[0])
#print(imdb_names[1])
#input()
vid_imdb, vid_roidb, vid_ratio_list, vid_ratio_index = combined_roidb(imdb_names[0])
det_imdb, det_roidb, det_ratio_list, det_ratio_index = combined_roidb(imdb_names[1])
vid_train_size, det_train_size = len(vid_roidb), len(det_roidb)
train_size = min(vid_train_size, det_train_size)
assert vid_imdb.num_classes==det_imdb.num_classes, 'VID and DET must have same number of classes.'
imdb_classes = vid_imdb.classes
else:
#print(args.imdb_name)
#input()
imdb, roidb, ratio_list, ratio_index = combined_roidb(args.imdb_name)
train_size = len(roidb)
imdb_classes = imdb.classes
print('{:d} roidb entries'.format(train_size))
output_dir = os.path.join(args.save_dir, args.arch, args.net, args.dataset)
if args.cfg_file is not None:
cfg_from_file(args.cfg_file)
# -- Note: Use validation set and disable the flipped to enable faster loading.
if args.cuda:
cfg.CUDA = True
# xxx: different from training
cfg.TRAIN.USE_FLIPPED = False
cfg.USE_GPU_NMS = True if args.cuda else False
print('Using config:')
pprint.pprint(cfg)
# np.random.seed(cfg.RNG_SEED)
# train set
imdb_name = DATASET + "_train_supervised"
imdb, roidb, ratio_list, ratio_index = combined_roidb(imdb_name)
train_size = len(roidb)
print('{:d} roidb entries'.format(train_size))
output_dir = os.path.join(args.save_dir, args.net, DATASET, 'all')
os.makedirs(output_dir, exist_ok=True)
dataset = roibatchLoader(roidb,
ratio_list,
ratio_index,
args.batch_size,
imdb.num_classes,
training=True)
dataloader = torch.utils.data.DataLoader(dataset,
batch_size=args.batch_size,
print('Using config:')
pprint.pprint(cfg)
np.random.seed(cfg.RNG_SEED)
# torch.backends.cudnn.benchmark = True
if torch.cuda.is_available() and not args.cuda:
print(
"WARNING: You have a CUDA device, so you should probably run with --cuda"
)
# train set
# -- Note: Use validation set and disable the flipped to enable faster loading.
cfg.TRAIN.USE_FLIPPED = True
cfg.USE_GPU_NMS = args.cuda
imdb, roidb, ratio_list, ratio_index = combined_roidb(args.imdb_name)
train_size = len(roidb)
print('{:d} roidb entries'.format(len(roidb)))
output_dir = args.save_dir
if not os.path.exists(output_dir):
os.makedirs(output_dir)
sampler_batch = sampler(train_size, args.batch_size)
dataset = roibatchLoader(roidb, ratio_list, ratio_index, args.batch_size, \
imdb.num_classes, training=True)
dataloader = torch.utils.data.DataLoader(dataset,
batch_size=args.batch_size,
np.random.seed(random_seed)
torch.manual_seed(random_seed)
if args.cuda:
torch.cuda.manual_seed_all(random_seed)
#torch.backends.cudnn.benchmark = True
if torch.cuda.is_available() and not args.cuda:
print(
"WARNING: You have a CUDA device, so you should probably run with --cuda"
)
# train set
cfg.USE_GPU_NMS = args.cuda
# create dataloader
imdb, roidb, ratio_list, ratio_index, query = combined_roidb(
args.imdb_name, True)
train_size = len(roidb)
print('{:d} roidb entries'.format(len(roidb)))
sampler_batch = sampler(train_size, args.batch_size)
dataset = roibatchLoader(roidb,
ratio_list,
ratio_index,
query,
args.batch_size,
imdb._classes,
training=True)
dataloader = torch.utils.data.DataLoader(dataset,
batch_size=args.batch_size,
sampler=sampler_batch,
num_workers=args.num_workers,
collate_fn=collate_tensors)
print('Using config:')
pprint.pprint(cfg)
np.random.seed(cfg.RNG_SEED)
# torch.backends.cudnn.benchmark = True
if torch.cuda.is_available() and not args.cuda:
print(
"WARNING: You have a CUDA device, so you should probably run with --cuda"
)
# train set
# -- Note: Use validation set and disable the flipped to enable faster loading.
cfg.TRAIN.USE_FLIPPED = True
cfg.USE_GPU_NMS = args.cuda
imdb, roidb = combined_roidb(args.imdb_name, root_path=args.data_root)
# imdb, roidb, ratio_list, ratio_index = combined_roidb(args.imdb_name)
train_size = len(roidb)
print('{:d} roidb entries'.format(len(roidb)))
output_dir = args.save_dir + "/" + args.net + "/" + args.dataset
if not os.path.exists(output_dir):
os.makedirs(output_dir)
# dataset = roibatchLoader(roidb, ratio_list, ratio_index, args.batch_size, \
# imdb.num_classes, training=True)
# dataset = roibatchLoader(roidb , imdb.num_classes, training=True)
dataset = Detection(roidb,
args.imdb_name = "vg_150-50-50_minitrain"
args.imdbval_name = "vg_150-50-50_minival"
args.set_cfgs = ['ANCHOR_SCALES', '[4, 8, 16, 32]', 'ANCHOR_RATIOS', '[0.5,1,2]']
args.cfg_file = "cfgs/{}_ls.yml".format(args.net) if args.large_scale else "cfgs/{}.yml".format(args.net)
if args.cfg_file is not None:
cfg_from_file(args.cfg_file)
if args.set_cfgs is not None:
cfg_from_list(args.set_cfgs)
print('Using config:')
pprint.pprint(cfg)
cfg.TRAIN.USE_FLIPPED = False
imdb, roidb, ratio_list, ratio_index = combined_roidb(args.imdbval_name, False)
imdb.competition_mode(on=True)
print('{:d} roidb entries'.format(len(roidb)))
input_dir = args.load_dir + "/" + args.net + "/" + args.dataset
if not os.path.exists(input_dir):
raise Exception('There is no input directory for loading network from ' + input_dir)
load_name = os.path.join(input_dir,
'faster_rcnn_{}_{}_{}.pth'.format(args.checksession, args.checkepoch, args.checkpoint))
# initilize the network here.
if args.net == 'vgg16':
fasterRCNN = vgg16(imdb.classes, pretrained=False, class_agnostic=args.class_agnostic)
elif args.net == 'res101':
fasterRCNN = resnet(imdb.classes, 101, pretrained=False, class_agnostic=args.class_agnostic)
def test(args, model=None):
if torch.cuda.is_available() and not args.cuda:
print(
"WARNING: You have a CUDA device, so you should probably run with --cuda"
)
# Load dataset
imdb_vu, roidb_vu, ratio_list_vu, ratio_index_vu, query_vu = combined_roidb(
args.imdbval_name, False)
imdb_vu.competition_mode(on=True)
dataset_vu = roibatchLoader(roidb_vu,
ratio_list_vu,
ratio_index_vu,
query_vu,
1,
imdb_vu._classes,
training=False)
# initilize the network here.
if not model:
if args.net == 'vgg16':
fasterRCNN = vgg16(imdb_vu.classes,
pretrained=False,
class_agnostic=args.class_agnostic)
elif args.net == 'res101':
fasterRCNN = resnet(imdb_vu.classes,
101,
pretrained=False,
class_agnostic=args.class_agnostic)
elif args.net == 'res50':
fasterRCNN = resnet(imdb_vu.classes,
50,
pretrained=False,
class_agnostic=args.class_agnostic)
elif args.net == 'res152':
fasterRCNN = resnet(imdb_vu.classes,
152,
pretrained=False,
class_agnostic=args.class_agnostic)
else:
print("network is not defined")
fasterRCNN.create_architecture()
# Load checkpoint
print("load checkpoint %s" % (args.weights))
checkpoint = torch.load(args.weights)
fasterRCNN.load_state_dict(checkpoint['model'])
if 'pooling_mode' in checkpoint.keys():
cfg.POOLING_MODE = checkpoint['pooling_mode']
print('load model successfully!')
else:
# evaluate constructed model
fasterRCNN = model
# initialize the tensor holder here.
im_data = torch.FloatTensor(1)
query = torch.FloatTensor(1)
im_info = torch.FloatTensor(1)
catgory = torch.LongTensor(1)
gt_boxes = torch.FloatTensor(1)
# ship to cuda
if args.cuda:
cfg.CUDA = True
fasterRCNN.cuda()
im_data = im_data.cuda()
query = query.cuda()
im_info = im_info.cuda()
catgory = catgory.cuda()
gt_boxes = gt_boxes.cuda()
# record time
start = time.time()
# visiualization
vis = args.vis if hasattr(args, 'vis') else None
if vis:
thresh = 0.05
else:
thresh = 0.0
max_per_image = 100
fasterRCNN.eval()
dataset_vu.query_position = 0
test_scales = cfg.TEST.SCALES
multiscale_iterators = []
for i_scale, test_scale in enumerate(test_scales):
cur_dataloader_vu = torch.utils.data.DataLoader(dataset_vu,
batch_size=1,
shuffle=False,
num_workers=0,
pin_memory=True)
cur_data_iter_vu = iter(cur_dataloader_vu)
multiscale_iterators.append(cur_data_iter_vu)
# total quantity of testing images, each images include multiple detect class
num_images_vu = len(imdb_vu.image_index)
num_detect = len(ratio_index_vu[0])
all_boxes = [[[] for _ in range(num_images_vu)]
for _ in range(imdb_vu.num_classes)]
_t = {'im_detect': time.time(), 'misc': time.time()}
for i, index in enumerate(ratio_index_vu[0]):
det_tic = time.time()
multiscale_boxes = []
multiscale_scores = []
for i_scale, (data_iter_vu, test_scale) in enumerate(
zip(multiscale_iterators, test_scales)):
# need to rewrite cfg.TRAIN.SCALES - very hacky!
BACKUP_TRAIN_SCALES = cfg.TRAIN.SCALES
cfg.TRAIN.SCALES = [test_scale]
data = next(data_iter_vu)
cfg.TRAIN.SCALES = BACKUP_TRAIN_SCALES
with torch.no_grad():
im_data.resize_(data[0].size()).copy_(data[0])
query.resize_(data[1].size()).copy_(data[1])
im_info.resize_(data[2].size()).copy_(data[2])
gt_boxes.resize_(data[3].size()).copy_(data[3])
catgory.data.resize_(data[4].size()).copy_(data[4])
# Run Testing
if not hasattr(args, "class_image_augmentation"
) or not args.class_image_augmentation:
queries = [query]
elif args.class_image_augmentation.lower() == "rotation90":
queries = [query]
for _ in range(3):
queries.append(queries[-1].rot90(1, [2, 3]))
else:
raise RuntimeError(
"Unknown class_image_augmentation: {}".format(
args.class_image_augmentation))
for q in queries:
rois, cls_prob, bbox_pred, \
rpn_loss_cls, rpn_loss_box, \
RCNN_loss_cls, _, RCNN_loss_bbox, \
rois_label, weight = fasterRCNN(im_data, q, im_info, gt_boxes, catgory)
scores = cls_prob.data
boxes = rois.data[:, :, 1:5]
# Apply bounding-box regression
if cfg.TEST.BBOX_REG:
# Apply bounding-box regression deltas
box_deltas = bbox_pred.data
if cfg.TRAIN.BBOX_NORMALIZE_TARGETS_PRECOMPUTED:
# Optionally normalize targets by a precomputed mean and stdev
if args.class_agnostic:
box_deltas = box_deltas.view(-1, 4) * torch.FloatTensor(cfg.TRAIN.BBOX_NORMALIZE_STDS).cuda() \
+ torch.FloatTensor(cfg.TRAIN.BBOX_NORMALIZE_MEANS).cuda()
box_deltas = box_deltas.view(1, -1, 4)
else:
box_deltas = box_deltas.view(-1, 4) * torch.FloatTensor(cfg.TRAIN.BBOX_NORMALIZE_STDS).cuda() \
+ torch.FloatTensor(cfg.TRAIN.BBOX_NORMALIZE_MEANS).cuda()
box_deltas = box_deltas.view(
1, -1, 4 * len(imdb_vu.classes))
pred_boxes = bbox_transform_inv(boxes, box_deltas, 1)
pred_boxes = clip_boxes(pred_boxes, im_info.data, 1)
else:
# Simply repeat the boxes, once for each class
pred_boxes = np.tile(boxes, (1, scores.shape[1]))
# Resize to original ratio
pred_boxes /= data[2][0][2].item()
# Remove batch_size dimension
scores = scores.squeeze()
pred_boxes = pred_boxes.squeeze()
multiscale_scores.append(scores)
multiscale_boxes.append(pred_boxes)
scores = torch.cat(multiscale_scores, dim=0)
pred_boxes = torch.cat(multiscale_boxes, dim=0)
# Record time
det_toc = time.time()
detect_time = det_toc - det_tic
misc_tic = time.time()
# Post processing
inds = torch.nonzero(scores > thresh).view(-1)
if inds.numel() > 0:
# remove useless indices
cls_scores = scores[inds]
cls_boxes = pred_boxes[inds, :]
cls_dets = torch.cat((cls_boxes, cls_scores.unsqueeze(1)), 1)
# rearrange order
_, order = torch.sort(cls_scores, 0, True)
cls_dets = cls_dets[order]
# NMS
keep = nms(cls_boxes[order, :], cls_scores[order], cfg.TEST.NMS)
cls_dets = cls_dets[keep.view(-1).long()]
all_boxes[catgory][index] = cls_dets.cpu().numpy()
# Limit to max_per_image detections *over all classes*
if max_per_image > 0:
try:
image_scores = all_boxes[catgory][index][:, -1]
if len(image_scores) > max_per_image:
image_thresh = np.sort(image_scores)[-max_per_image]
keep = np.where(
all_boxes[catgory][index][:,
-1] >= image_thresh)[0]
all_boxes[catgory][index] = all_boxes[catgory][index][
keep, :]
except:
pass
misc_toc = time.time()
nms_time = misc_toc - misc_tic
sys.stdout.write('im_detect: {:d}/{:d} {:.3f}s {:.3f}s \r' \
.format(i + 1, num_detect, detect_time, nms_time))
sys.stdout.flush()
# save test image
if vis and i % 1 == 0:
im2show = cv2.imread(
dataset_vu._roidb[dataset_vu.ratio_index[i]]['image'])
im2show = vis_detections(im2show, 'shot',
cls_dets.cpu().numpy(), 0.3)
o_query = data[1][0].permute(1, 2,
0).contiguous().cpu().numpy()
o_query *= [0.229, 0.224, 0.225]
o_query += [0.485, 0.456, 0.406]
o_query *= 255
o_query = o_query[:, :, ::-1]
(h, w, c) = im2show.shape
o_query = cv2.resize(o_query, (h, h),
interpolation=cv2.INTER_LINEAR)
im2show = np.concatenate((im2show, o_query), axis=1)
vis_path = "./test_img"
if not os.path.isdir(vis_path):
os.makedirs(vis_path)
cv2.imwrite(os.path.join(vis_path, "%d_d.png" % (i)), im2show)
print('Evaluating detections')
mAP = imdb_vu.evaluate_detections(all_boxes, None)
end = time.time()
print("test time: %0.4fs" % (end - start))
return mAP
def eval_result(args, logger, epoch, output_dir):
if torch.cuda.is_available() and not args.cuda:
print(
"WARNING: You have a CUDA device, so you should probably run with --cuda"
)
args.batch_size = 1
imdb, roidb, ratio_list, ratio_index = combined_roidb(
args.imdbval_name, False, root_path=args.data_root)
imdb.competition_mode(on=True)
load_name = os.path.join(output_dir,
'thundernet_epoch_{}.pth'.format(epoch, ))
layer = int(args.net.split("_")[1])
_RCNN = snet(imdb.classes,
layer,
pretrained_path=None,
class_agnostic=args.class_agnostic)
_RCNN.create_architecture()
print("load checkpoint %s" % (load_name))
if args.cuda:
checkpoint = torch.load(load_name)
else:
checkpoint = torch.load(load_name,
map_location=lambda storage, loc: storage
) # Load all tensors onto the CPU
_RCNN.load_state_dict(checkpoint['model'])
im_data = torch.FloatTensor(1)
im_info = torch.FloatTensor(1)
num_boxes = torch.LongTensor(1)
gt_boxes = torch.FloatTensor(1)
# hm = torch.FloatTensor(1)
# reg_mask = torch.LongTensor(1)
# wh = torch.FloatTensor(1)
# offset = torch.FloatTensor(1)
# ind = torch.LongTensor(1)
# ship to cuda
if args.cuda:
im_data = im_data.cuda()
im_info = im_info.cuda()
num_boxes = num_boxes.cuda()
gt_boxes = gt_boxes.cuda()
# hm = hm.cuda()
# reg_mask = reg_mask.cuda()
# wh = wh.cuda()
# offset = offset.cuda()
# ind = ind.cuda()
# make variable
with torch.no_grad():
im_data = Variable(im_data)
im_info = Variable(im_info)
num_boxes = Variable(num_boxes)
gt_boxes = Variable(gt_boxes)
# hm = Variable(hm)
# reg_mask = Variable(reg_mask)
# wh = Variable(wh)
# offset = Variable(offset)
# ind = Variable(ind)
if args.cuda:
cfg.CUDA = True
if args.cuda:
_RCNN.cuda()
start = time.time()
max_per_image = 100
vis = True
if vis:
thresh = 0.05
else:
thresh = 0.0
save_name = 'thundernet'
num_images = len(imdb.image_index)
all_boxes = [[[] for _ in xrange(num_images)]
for _ in xrange(imdb.num_classes)]
output_dir = get_output_dir(imdb, save_name)
# dataset = roibatchLoader(roidb, ratio_list, ratio_index, args.batch_size, \
# imdb.num_classes, training=False, normalize=False)
# dataset = roibatchLoader(roidb, imdb.num_classes, training=False)
dataset = Detection(roidb,
num_classes=imdb.num_classes,
transform=BaseTransform(cfg.TEST.SIZE,
cfg.PIXEL_MEANS),
training=False)
dataloader = torch.utils.data.DataLoader(dataset,
batch_size=args.batch_size,
shuffle=False,
num_workers=0,
pin_memory=True)
data_iter = iter(dataloader)
_t = {'im_detect': time.time(), 'misc': time.time()}
det_file = os.path.join(output_dir, 'detections.pkl')
_RCNN.eval()
empty_array = np.transpose(np.array([[], [], [], [], []]), (1, 0))
for i in range(num_images):
data = next(data_iter)
with torch.no_grad():
im_data.resize_(data[0].size()).copy_(data[0])
im_info.resize_(data[1].size()).copy_(data[1])
gt_boxes.resize_(data[2].size()).copy_(data[2])
num_boxes.resize_(data[3].size()).copy_(data[3])
# hm.resize_(data[4].size()).copy_(data[4])
# reg_mask.resize_(data[5].size()).copy_(data[5])
# wh.resize_(data[6].size()).copy_(data[6])
# offset.resize_(data[7].size()).copy_(data[7])
# ind.resize_(data[8].size()).copy_(data[8])
det_tic = time.time()
with torch.no_grad():
time_measure, \
rois, cls_prob, bbox_pred, \
rpn_loss_cls, rpn_loss_box, \
RCNN_loss_cls, RCNN_loss_bbox, \
rois_label = _RCNN(im_data, im_info, gt_boxes, num_boxes,
# hm,reg_mask,wh,offset,ind
)
scores = cls_prob.data
boxes = rois.data[:, :, 1:5]
if cfg.TEST.BBOX_REG:
# Apply bounding-box regression deltas
box_deltas = bbox_pred.data
if cfg.TRAIN.BBOX_NORMALIZE_TARGETS_PRECOMPUTED:
# Optionally normalize targets by a precomputed mean and stdev
if args.class_agnostic:
box_deltas = box_deltas.view(-1, 4) * torch.FloatTensor(cfg.TRAIN.BBOX_NORMALIZE_STDS).cuda() \
+ torch.FloatTensor(cfg.TRAIN.BBOX_NORMALIZE_MEANS).cuda()
box_deltas = box_deltas.view(args.batch_size, -1, 4)
else:
box_deltas = box_deltas.view(-1, 4) * torch.FloatTensor(cfg.TRAIN.BBOX_NORMALIZE_STDS).cuda() \
+ torch.FloatTensor(cfg.TRAIN.BBOX_NORMALIZE_MEANS).cuda()
box_deltas = box_deltas.view(args.batch_size, -1,
4 * len(imdb.classes))
pred_boxes = bbox_transform_inv(boxes, box_deltas, 1)
pred_boxes = clip_boxes(pred_boxes, im_info.data, 1)
else:
# Simply repeat the boxes, once for each class
pred_boxes = np.tile(boxes, (1, scores.shape[1]))
# pred_boxes /= data[1][0][2].item()
pred_boxes[:, :, 0::2] /= data[1][0][2].item()
pred_boxes[:, :, 1::2] /= data[1][0][3].item()
scores = scores.squeeze()
pred_boxes = pred_boxes.squeeze()
det_toc = time.time()
detect_time = det_toc - det_tic
misc_tic = time.time()
if vis:
im = cv2.imread(imdb.image_path_at(i))
im2show = np.copy(im)
for j in xrange(1, imdb.num_classes):
inds = torch.nonzero(scores[:, j] > thresh).view(-1)
# if there is det
if inds.numel() > 0:
cls_scores = scores[:, j][inds]
_, order = torch.sort(cls_scores, 0, True)
if args.class_agnostic:
cls_boxes = pred_boxes[inds, :]
else:
cls_boxes = pred_boxes[inds][:, j * 4:(j + 1) * 4]
cls_dets = torch.cat((cls_boxes, cls_scores.unsqueeze(1)), 1)
# cls_dets = torch.cat((cls_boxes, cls_scores), 1)
cls_dets = cls_dets[order]
keep = nms(cls_boxes[order, :], cls_scores[order],
cfg.TEST.NMS)
# keep = soft_nms(cls_dets.cpu().numpy(), Nt=0.5, method=2)
# keep = torch.as_tensor(keep, dtype=torch.long)
cls_dets = cls_dets[keep.view(-1).long()]
if vis:
vis_detections(im2show, imdb.classes[j],
color_list[j - 1].tolist(),
cls_dets.cpu().numpy(), 0.6)
all_boxes[j][i] = cls_dets.cpu().numpy()
else:
all_boxes[j][i] = empty_array
# Limit to max_per_image detections *over all classes*
if max_per_image > 0:
image_scores = np.hstack(
[all_boxes[j][i][:, -1] for j in xrange(1, imdb.num_classes)])
if len(image_scores) > max_per_image:
image_thresh = np.sort(image_scores)[-max_per_image]
for j in xrange(1, imdb.num_classes):
keep = np.where(all_boxes[j][i][:, -1] >= image_thresh)[0]
all_boxes[j][i] = all_boxes[j][i][keep, :]
misc_toc = time.time()
nms_time = misc_toc - misc_tic
sys.stdout.write(
'im_detect: {:d}/{:d}\tDetect: {:.3f}s (RPN: {:.3f}s, Pre-RoI: {:.3f}s, RoI: {:.3f}s, Subnet: {:.3f}s)\tNMS: {:.3f}s\r' \
.format(i + 1, num_images, detect_time, time_measure[0], time_measure[1], time_measure[2],
time_measure[3], nms_time))
sys.stdout.flush()
if vis and i % 200 == 0 and args.use_tfboard:
im2show = im2show[:, :, ::-1]
logger.add_image('pred_image_{}'.format(i),
trans.ToTensor()(Image.fromarray(
im2show.astype('uint8'))),
global_step=i)
# cv2.imwrite('result.png', im2show)
# pdb.set_trace()
# cv2.imshow('test', im2show)
# cv2.waitKey(0)
with open(det_file, 'wb') as f:
pickle.dump(all_boxes, f, pickle.HIGHEST_PROTOCOL)
print('Evaluating detections')
ap_50 = imdb.evaluate_detections(all_boxes, output_dir)
logger.add_scalar("map_50", ap_50, global_step=epoch)
end = time.time()
print("test time: %0.4fs" % (end - start))
def evaluation(name, net=None, vis=False, cuda=True, class_agnostic=False):
cfg.TRAIN.USE_FLIPPED = False
imdb, roidb, ratio_list, ratio_index = combined_roidb(name, False)
imdb.competition_mode(on=True)
print('{:d} roidb entries'.format(len(roidb)))
if not net:
input_dir = args.load_dir + "/" + args.net + "/" + args.dataset
# input_dir = 'weight'
if not os.path.exists(input_dir):
raise Exception(
'There is no input directory for loading network from ' +
input_dir)
# load_name = os.path.join(input_dir,
# 'faster_rcnn_{}_{}_{}.pth'.format(args.checksession, args.checkepoch, args.checkpoint))
load_name = os.path.join(
input_dir, 'faster_rcnn_{}_best.pth'.format(cfg['POOLING_MODE']))
# initilize the network here.
if args.net == 'vgg16':
fasterRCNN = vgg16(imdb.classes,
pretrained=False,
class_agnostic=args.class_agnostic)
elif args.net == 'res101':
fasterRCNN = resnet(imdb.classes,
101,
pretrained=False,
class_agnostic=args.class_agnostic)
elif args.net == 'res50':
fasterRCNN = resnet(imdb.classes,
50,
pretrained=False,
class_agnostic=args.class_agnostic)
elif args.net == 'res152':
fasterRCNN = resnet(imdb.classes,
152,
pretrained=False,
class_agnostic=args.class_agnostic)
else:
print("network is not defined")
pdb.set_trace()
fasterRCNN.create_architecture()
print("load checkpoint %s" % (load_name))
checkpoint = torch.load(load_name)
fasterRCNN.load_state_dict(checkpoint['model'])
if 'pooling_mode' in checkpoint.keys():
cfg.POOLING_MODE = checkpoint['pooling_mode']
print('load model successfully!')
else:
fasterRCNN = net
# initilize the tensor holder here.
im_data = torch.FloatTensor(1)
im_info = torch.FloatTensor(1)
num_boxes = torch.LongTensor(1)
gt_boxes = torch.FloatTensor(1)
# ship to cuda
if cuda:
im_data = im_data.cuda()
im_info = im_info.cuda()
num_boxes = num_boxes.cuda()
gt_boxes = gt_boxes.cuda()
# make variable
im_data = Variable(im_data)
im_info = Variable(im_info)
num_boxes = Variable(num_boxes)
gt_boxes = Variable(gt_boxes)
if cuda:
cfg.CUDA = True
if cuda:
fasterRCNN.cuda()
start = time.time()
max_per_image = 100
# vis = args.vis
if vis:
thresh = 0.05
else:
thresh = 0.0
save_name = 'faster_rcnn_10'
num_images = len(imdb.image_index)
all_boxes = [[[] for _ in range(num_images)]
for _ in range(imdb.num_classes)]
output_dir = get_output_dir(imdb, save_name)
dataset = roibatchLoader(roidb, ratio_list, ratio_index, 1, \
imdb.num_classes, training=False, normalize=False)
dataloader = torch.utils.data.DataLoader(dataset,
batch_size=1,
shuffle=False,
num_workers=0,
pin_memory=True)
data_iter = iter(dataloader)
_t = {'im_detect': time.time(), 'misc': time.time()}
det_file = os.path.join(output_dir, 'detections.pkl')
fasterRCNN.eval()
empty_array = np.transpose(np.array([[], [], [], [], []]), (1, 0))
for i in range(num_images):
data = next(data_iter)
with torch.no_grad():
im_data.resize_(data[0].size()).copy_(data[0])
im_info.resize_(data[1].size()).copy_(data[1])
gt_boxes.resize_(data[2].size()).copy_(data[2])
num_boxes.resize_(data[3].size()).copy_(data[3])
det_tic = time.time()
rois, cls_prob, bbox_pred, \
rpn_loss_cls, rpn_loss_box, \
RCNN_loss_cls, RCNN_loss_bbox, \
rois_label = fasterRCNN(im_data, im_info, gt_boxes, num_boxes)
scores = cls_prob.data
boxes = rois.data[:, :, 1:5]
if cfg.TEST.BBOX_REG:
# Apply bounding-box regression deltas
box_deltas = bbox_pred.data
if cfg.TRAIN.BBOX_NORMALIZE_TARGETS_PRECOMPUTED:
# Optionally normalize targets by a precomputed mean and stdev
if class_agnostic:
box_deltas = box_deltas.view(-1, 4) * torch.FloatTensor(cfg.TRAIN.BBOX_NORMALIZE_STDS).cuda() \
+ torch.FloatTensor(cfg.TRAIN.BBOX_NORMALIZE_MEANS).cuda()
box_deltas = box_deltas.view(1, -1, 4)
else:
box_deltas = box_deltas.view(-1, 4) * torch.FloatTensor(cfg.TRAIN.BBOX_NORMALIZE_STDS).cuda() \
+ torch.FloatTensor(cfg.TRAIN.BBOX_NORMALIZE_MEANS).cuda()
box_deltas = box_deltas.view(1, -1, 4 * len(imdb.classes))
pred_boxes = bbox_transform_inv(boxes, box_deltas, 1)
pred_boxes = clip_boxes(pred_boxes, im_info.data, 1)
else:
# Simply repeat the boxes, once for each class
pred_boxes = np.tile(boxes, (1, scores.shape[1]))
pred_boxes /= data[1][0][2].item()
scores = scores.squeeze()
pred_boxes = pred_boxes.squeeze()
det_toc = time.time()
detect_time = det_toc - det_tic
misc_tic = time.time()
if vis:
im = cv2.imread(imdb.image_path_at(i))
im2show = np.copy(im)
for j in range(1, imdb.num_classes):
inds = torch.nonzero(scores[:, j] > thresh).view(-1)
# if there is det
if inds.numel() > 0:
cls_scores = scores[:, j][inds]
_, order = torch.sort(cls_scores, 0, True)
if class_agnostic:
cls_boxes = pred_boxes[inds, :]
else:
cls_boxes = pred_boxes[inds][:, j * 4:(j + 1) * 4]
cls_dets = torch.cat((cls_boxes, cls_scores.unsqueeze(1)), 1)
# cls_dets = torch.cat((cls_boxes, cls_scores), 1)
cls_dets = cls_dets[order]
keep = nms(cls_boxes[order, :], cls_scores[order],
cfg.TEST.NMS)
cls_dets = cls_dets[keep.view(-1).long()]
if vis:
im2show = vis_detections(im2show, imdb.classes[j],
cls_dets.cpu().numpy(), 0.3)
all_boxes[j][i] = cls_dets.cpu().numpy()
else:
all_boxes[j][i] = empty_array
# Limit to max_per_image detections *over all classes*
if max_per_image > 0:
image_scores = np.hstack(
[all_boxes[j][i][:, -1] for j in range(1, imdb.num_classes)])
if len(image_scores) > max_per_image:
image_thresh = np.sort(image_scores)[-max_per_image]
for j in range(1, imdb.num_classes):
keep = np.where(all_boxes[j][i][:, -1] >= image_thresh)[0]
all_boxes[j][i] = all_boxes[j][i][keep, :]
misc_toc = time.time()
nms_time = misc_toc - misc_tic
sys.stdout.write('im_detect: {:d}/{:d} {:.3f}s {:.3f}s \r' \
.format(i + 1, num_images, detect_time, nms_time))
sys.stdout.flush()
if vis:
cv2.imwrite('result.png', im2show)
pdb.set_trace()
# cv2.imshow('test', im2show)
# cv2.waitKey(0)
with open(det_file, 'wb') as f:
pickle.dump(all_boxes, f, pickle.HIGHEST_PROTOCOL)
print('Evaluating detections')
map = imdb.evaluate_detections(all_boxes, output_dir)
# print(map)
end = time.time()
print("test time: %0.4fs" % (end - start))
return map
args.cfg_file = "cfgs/{}_ls.yml".format(
args.net) if args.large_scale else "cfgs/{}.yml".format(args.net)
if args.cfg_file is not None:
cfg_from_file(args.cfg_file)
if args.set_cfgs is not None:
cfg_from_list(args.set_cfgs)
print('Using config:')
pprint.pprint(cfg)
cfg.TRAIN.USE_FLIPPED = False
if args.part == 'test_s':
imdb, roidb, ratio_list, ratio_index = combined_roidb(
args.s_imdbtest_name, False)
elif args.part == 'test_t':
imdb, roidb, ratio_list, ratio_index = combined_roidb(
args.t_imdbtest_name, False)
elif args.part == 'test_all':
imdb, roidb, ratio_list, ratio_index = combined_roidb(
args.all_imdbtest_name, False)
else:
print("don't have the test part !")
# pdb.set_trace()
imdb.competition_mode(on=True)
print('{:d} roidb entries'.format(len(roidb)))
# input_dir = args.load_dir + "/" + args.net + "/" + args.dataset
if args.set_cfgs is not None:
cfg_from_list(args.set_cfgs)
print('Using config:')
pprint.pprint(cfg)
np.random.seed(cfg.RNG_SEED)
#torch.backends.cudnn.benchmark = True
if torch.cuda.is_available() and not args.cuda:
print("WARNING: You have a CUDA device, so you should probably run with --cuda")
# train set
# -- Note: Use validation set and disable the flipped to enable faster loading.
cfg.TRAIN.USE_FLIPPED = True
cfg.USE_GPU_NMS = args.cuda
imdb, roidb, ratio_list, ratio_index = combined_roidb(args.imdb_name)#imdb_name=voc_2007_trainval
train_size = len(roidb)#10022
# ratio_list[ratio_index]将各个图片的的长宽比率按照从小到大排序（根据ratio_index排好的）
# ratio_index[4 1 5 0 2 3,...] 代表第四个最小，其次第一个最小，。。（从小到大的索引）
'''
roidb：=[{},{},{},....{}]
{'boxes': array([[ 47, 239, 194, 370],
[ 7, 11, 351, 497]], dtype=uint16), 'gt_classes': array([12, 15]), 'gt_ishard': array([0, 0]), 'gt_overlaps': <2x21 sparse matrix of type '<class 'numpy.float32'>'
with 2 stored elements in Compressed Sparse Row format>, 'flipped': False, 'seg_areas': array([ 19536., 168015.], dtype=float32)}
box.shape=(n,4) n代表这张图片上有几个目标
gt_classes.shape=(n) 例如：array([12, 15]) 代表第一个目标是第12类（猫），第二个目标是第15类（人）
gt_overlaps. overlaps.shape=(n,21) 值为0或1 默认0， 如果[2,20]=1代表该张图片上第2个目标是第20类的分割
flipped= False(前5011个为false ，后5011个为True)
