def create_dataloader(imdb_name, args):
imdb, roidb, ratio_list, ratio_index = combined_roidb(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)
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,
sampler=sampler_batch,
num_workers=args.num_workers)
return dataloader, train_size, imdb
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 xrange(num_images)]
for _ in xrange(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)
im_data.data.resize_(data[0].size()).copy_(data[0])
im_info.data.resize_(data[1].size()).copy_(data[1])
s_imdb, s_roidb, s_ratio_list, s_ratio_index = combined_roidb(args.s_imdb_name)
s_train_size = len(s_roidb) # add flipped image_index*2
t_imdb, t_roidb, t_ratio_list, t_ratio_index = combined_roidb(args.t_imdb_name)
t_train_size = len(t_roidb) # add flipped image_index*2
print('source {:d} target {:d} roidb entries'.format(len(s_roidb),len(t_roidb)))
output_dir = args.save_dir + "/" + args.net + "/" + args.dataset
if not os.path.exists(output_dir):
os.makedirs(output_dir)
s_sampler_batch = sampler(s_train_size, args.batch_size)
t_sampler_batch=sampler(t_train_size,args.batch_size)
s_dataset = roibatchLoader(s_roidb, s_ratio_list, s_ratio_index, args.batch_size, \
s_imdb.num_classes, training=True)
s_dataloader = torch.utils.data.DataLoader(s_dataset, batch_size=args.batch_size,
sampler=s_sampler_batch, num_workers=args.num_workers)
t_dataset=roibatchLoader(t_roidb, t_ratio_list, t_ratio_index, args.batch_size, \
t_imdb.num_classes, training=False)
t_dataloader = torch.utils.data.DataLoader(t_dataset, batch_size=args.batch_size,
sampler=t_sampler_batch, num_workers=args.num_workers)
# initilize the tensor holder here.
im_data = torch.FloatTensor(1)
im_info = torch.FloatTensor(1)
num_boxes = torch.LongTensor(1)
# 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 + "/" + args.net + "/" + args.dataset
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,
sampler=sampler_batch, num_workers=args.num_workers)
# 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 args.cuda:
im_data = im_data.cuda()
im_info = im_info.cuda()
print("source {:d} target {:d} roidb entries".format(
len(s_roidb), len(t_roidb)))
# output_dir = args.save_dir + "/" + args.net + "/" + args.dataset
output_dir = args.save_dir
if not os.path.exists(output_dir):
os.makedirs(output_dir)
s_sampler_batch = sampler(s_train_size, args.batch_size)
t_sampler_batch = sampler(t_train_size, args.batch_size)
dataset_s = roibatchLoader(
s_roidb,
s_ratio_list,
s_ratio_index,
args.batch_size,
s_imdb.num_classes,
training=True,
)
dataloader_s = torch.utils.data.DataLoader(
dataset_s,
batch_size=args.batch_size,
sampler=s_sampler_batch,
num_workers=args.num_workers,
)
dataset_t = roibatchLoader(
t_roidb,
t_ratio_list,
t_ratio_index,
args.batch_size,