def eval_augment_voc(input_size, device):
return augment.Compose([
augment.Resize(input_size),
augment.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225]),
augment.ToTensor(device),
])
def set_train_augment(self, augment_cfg: CN, input_size, img_path_sampler):
self.train_augment = augment.Compose([
augment.RandomHFlip(p=augment_cfg.hflip_p),
augment.RandomVFlip(p=augment_cfg.vflip_p),
augment.RandomSafeCrop(p=augment_cfg.crop_p),
augment.ColorJitter(
brightness=[-0.1, 0.1],
contrast=[0.8, 1.2],
saturation=[0.1, 2],
p=augment_cfg.color_p,
),
augment.Resize(input_size),
augment.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225]),
])
sampler = lambda: super(VOCSampleGetter, self).train(img_path_sampler(
))
self.compose_augment = augment.Compose([
augment.Mixup(sampler, p=augment_cfg.mixup_p, beta=1.5),
augment.ToTensor('cpu'),
])
# aug2 = augment.Compose([
# augment.Mosaic(sampler, p=1, size=input_size),
# augment.Mixup(sampler, p=0, beta=1.5),
# augment.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
# augment.ToTensor('cpu'),
# ])
return self
def benchmark_onnx(config, args):
torch.backends.cudnn.benchmark = True
with open(config.dataset.eval_txt_file, 'r') as fr:
files = [
line.strip() for line in fr.readlines() if len(line.strip()) != 0
][:100]
model = onnx_model_for_benchmark(args.onnx, args.device == 'cuda')
size = size_fix(args.size)
# warm up
print('warmimg up')
for _ in range(50):
model(np.random.randn(1, 3, *size).astype(np.float32))
process = augment.Compose([
augment.Resize(size),
augment.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225]),
augment.HWCtoCHW(),
])
print('loading images')
images = _prepare_images(files, process)
total_timer = tools.TicToc('TOTAL')
forward_timer = tools.TicToc('FORWARD')
convert_timer = tools.TicToc('CONVERT')
nms_timer = tools.TicToc('NMS')
input_shape = torch.FloatTensor(size).to(args.device, non_blocking=False)
threshold = args.threshold
nms_iou = args.nms_iou
for image, shape in tqdm(images):
image = image[None, ...]
shape = shape[None, ...].to(args.device)
total_timer.tic()
forward_timer.tic()
pred = model(image)
forward_timer.toc()
convert_timer.tic()
bboxes = RECOVER_BBOXES_REGISTER[args.dataset](
torch.from_numpy(pred).to(args.device), input_shape, shape)[0]
convert_timer.toc()
nms_timer.tic()
tools.torch_nms(bboxes, threshold, nms_iou)
nms_timer.toc()
total_timer.toc()
print('BENCHMARK: {} images in {} size'.format(len(images), size))
timers = [total_timer, forward_timer, convert_timer, nms_timer]
stats = [t.statistics() for t in timers]
for s in stats:
s['percent'] = s['mean'] / stats[0]['mean']
_print_statistics(s)
def process_sample(img, bboxes: np.ndarray):
process = augment.Compose([
augment.RandomHFlip(p=0.5),
augment.RandomSafeCrop(p=0.75),
augment.CutOut(p=0.8, size=30, n_holes=3),
augment.ColorJitter(
brightness=[-0.1, 0.1],
contrast=[0.8, 1.2],
saturation=[0.1, 2],
),
augment.Resize(lambda: [512, 512]),
augment.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225]),
])
img, bboxes = process(img, bboxes)
return img, bboxes
def benchmark(config, args):
torch.backends.cudnn.benchmark = True
with open(config.dataset.eval_txt_file, 'r') as fr:
files = [
line.strip() for line in fr.readlines() if len(line.strip()) != 0
][:100]
model = tools.build_model(
config.model.cfg_path,
args.weight,
None,
device=args.device,
dataparallel=False,
qat=args.qat,
quantized=args.quant,
backend=args.backend,
)[0]
size = size_fix(args.size)
process = augment.Compose([
augment.Resize(size),
augment.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225]),
augment.ToTensor(args.device),
])
print('loading images')
images = _prepare_images(files, process)
total_timer = tools.TicToc('TOTAL')
forward_timer = tools.TicToc('FORWARD')
convert_timer = tools.TicToc('CONVERT')
nms_timer = tools.TicToc('NMS')
input_shape = torch.FloatTensor(size).to(args.device, non_blocking=False)
threshold = args.threshold
nms_iou = args.nms_iou
# warm up
print('warmimg up')
with torch.no_grad():
for _ in range(5):
model(torch.rand(1, 3, *size).to(args.device))
torch.cuda.synchronize()
for image, shape in tqdm(images):
image = image.unsqueeze_(0).to(args.device, non_blocking=False)
shape = shape.unsqueeze_(0).to(args.device, non_blocking=False)
total_timer.tic()
forward_timer.tic()
pred = model(image)
torch.cuda.synchronize()
forward_timer.toc()
convert_timer.tic()
bboxes = RECOVER_BBOXES_REGISTER[args.dataset](pred, input_shape,
shape)[0]
torch.cuda.synchronize()
convert_timer.toc()
nms_timer.tic()
tools.torch_nms(bboxes, threshold, nms_iou)
torch.cuda.synchronize()
nms_timer.toc()
total_timer.toc()
print('BENCHMARK: {} images in {} size'.format(len(images), size))
timers = [total_timer, forward_timer, convert_timer, nms_timer]
stats = [t.statistics() for t in timers]
for s in stats:
s['percent'] = s['mean'] / stats[0]['mean']
_print_statistics(s)
