def filter_cls_data(yx_min, yx_max, mask):
if mask.numel() > 0:
_mask = torch.unsqueeze(mask, -1).repeat(1, 2) # PyTorch's bug
yx_min, yx_max = (t[_mask].view(-1, 2) for t in (yx_min, yx_max))
else: # all bboxes are difficult
yx_min = utils.ensure_device(torch.zeros(0, 2))
yx_max = utils.ensure_device(torch.zeros(0, 2))
return yx_min, yx_max
def filter_cls_data(yx_min, yx_max, mask):
if mask.numel() > 0:
_mask = torch.unsqueeze(mask, -1).repeat(1, 2) # PyTorch's bug
yx_min, yx_max = (t[_mask].view(-1, 2) for t in (yx_min, yx_max))
else: # all bboxes are difficult
yx_min = utils.ensure_device(torch.zeros(0, 2))
yx_max = utils.ensure_device(torch.zeros(0, 2))
return yx_min, yx_max
def __init__(self, args, config):
self.args = args
self.config = config
self.model_dir = utils.get_model_dir(config)
self.category = utils.get_category(config)
self.anchors = torch.from_numpy(utils.get_anchors(config)).contiguous()
self.dnn = utils.parse_attr(config.get('model',
'dnn'))(config, self.anchors,
len(self.category))
self.dnn.eval()
logging.info(
humanize.naturalsize(
sum(var.cpu().numpy().nbytes
for var in self.dnn.state_dict().values())))
if torch.cuda.is_available():
self.dnn.cuda()
self.height, self.width = tuple(
map(int,
config.get('image', 'size').split()))
output = self.dnn(
torch.autograd.Variable(
utils.ensure_device(torch.zeros(1, 3, self.height,
self.width))))
_, _, self.rows, self.cols = output.size()
self.i, self.j = self.rows // 2, self.cols // 2
self.output = output[:, :, self.i, self.j]
dataset = Dataset(self.height, self.width)
try:
workers = self.config.getint('data', 'workers')
except configparser.NoOptionError:
workers = multiprocessing.cpu_count()
self.loader = torch.utils.data.DataLoader(
dataset, batch_size=self.args.batch_size, num_workers=workers)
def conv_logits(pred):
if 'logits' in pred:
logits = pred['logits'].contiguous()
prob, cls = torch.max(F.softmax(logits, -1), -1)
else:
size = pred['iou'].size()
prob = torch.autograd.Variable(utils.ensure_device(torch.ones(*size)))
cls = torch.autograd.Variable(
utils.ensure_device(torch.zeros(*size).int()))
return prob, cls
def __call__(self):
changed = np.zeros([self.height, self.width], np.bool)
for yx in tqdm.tqdm(self.loader):
batch_size = yx.size(0)
tensor = torch.zeros(batch_size, 3, self.height, self.width)
for i, _yx in enumerate(torch.unbind(yx)):
y, x = torch.unbind(_yx)
tensor[i, :, y, x] = 1
tensor = utils.ensure_device(tensor)
output = self.dnn(torch.autograd.Variable(tensor))
output = output[:, :, self.i, self.j]
cmp = output == self.output
cmp = torch.prod(cmp, -1).data
for _yx, c in zip(torch.unbind(yx), torch.unbind(cmp)):
y, x = torch.unbind(_yx)
changed[y, x] = c
return changed
def __call__(self):
changed = np.zeros([self.height, self.width], np.bool)
for yx in tqdm.tqdm(self.loader):
batch_size = yx.size(0)
tensor = torch.zeros(batch_size, 3, self.height, self.width)
for i, _yx in enumerate(torch.unbind(yx)):
y, x = torch.unbind(_yx)
tensor[i, :, y, x] = 1
tensor = utils.ensure_device(tensor)
output = self.dnn(torch.autograd.Variable(tensor, volatile=True))
output = output[:, :, self.i, self.j]
cmp = output == self.output
cmp = torch.prod(cmp, -1).data
for _yx, c in zip(torch.unbind(yx), torch.unbind(cmp)):
y, x = torch.unbind(_yx)
changed[y, x] = c
return changed
def __init__(self, args, config):
self.args = args
self.config = config
self.model_dir = utils.get_model_dir(config)
self.category = utils.get_category(config)
self.anchors = torch.from_numpy(utils.get_anchors(config)).contiguous()
self.dnn = utils.parse_attr(config.get('model', 'dnn'))(model.ConfigChannels(config), self.anchors, len(self.category))
self.dnn.eval()
logging.info(humanize.naturalsize(sum(var.cpu().numpy().nbytes for var in self.dnn.state_dict().values())))
if torch.cuda.is_available():
self.dnn.cuda()
self.height, self.width = tuple(map(int, config.get('image', 'size').split()))
output = self.dnn(torch.autograd.Variable(utils.ensure_device(torch.zeros(1, 3, self.height, self.width)), volatile=True))
_, _, self.rows, self.cols = output.size()
self.i, self.j = self.rows // 2, self.cols // 2
self.output = output[:, :, self.i, self.j]
dataset = Dataset(self.height, self.width)
try:
workers = self.config.getint('data', 'workers')
except configparser.NoOptionError:
workers = multiprocessing.cpu_count()
self.loader = torch.utils.data.DataLoader(dataset, batch_size=self.args.batch_size, num_workers=workers)