def test_box_encoder_cpu():
pipe = Pipeline(batch_size=batch_size, num_threads=4, device_id=None)
test_box_shape = [20, 4]
def get_boxes():
out = [
(np.random.randint(0, 255, size=test_box_shape, dtype=np.uint8) /
255).astype(dtype=np.float32) for _ in range(batch_size)
]
return out
test_lables_shape = [20, 1]
def get_lables():
out = [
np.random.randint(0, 255, size=test_lables_shape, dtype=np.int32)
for _ in range(batch_size)
]
return out
boxes = fn.external_source(source=get_boxes)
lables = fn.external_source(source=get_lables)
processed, _ = fn.box_encoder(boxes, lables, anchors=coco_anchors())
pipe.set_outputs(processed)
pipe.build()
for _ in range(3):
pipe.run()
def create_coco_pipeline(default_boxes, args):
try:
shard_id = torch.distributed.get_rank()
num_shards = torch.distributed.get_world_size()
except RuntimeError:
shard_id = 0
num_shards = 1
images, bboxes, labels = fn.readers.coco(
file_root=args.train_coco_root,
annotations_file=args.train_annotate,
skip_empty=True,
shard_id=shard_id,
num_shards=num_shards,
ratio=True,
ltrb=True,
random_shuffle=False,
shuffle_after_epoch=True,
name="Reader")
crop_begin, crop_size, bboxes, labels = fn.random_bbox_crop(
bboxes,
labels,
device="cpu",
aspect_ratio=[0.5, 2.0],
thresholds=[0, 0.1, 0.3, 0.5, 0.7, 0.9],
scaling=[0.3, 1.0],
bbox_layout="xyXY",
allow_no_crop=True,
num_attempts=50)
images = fn.image_decoder_slice(images,
crop_begin,
crop_size,
device="mixed",
output_type=types.RGB)
flip_coin = fn.random.coin_flip(probability=0.5)
images = fn.resize(images,
resize_x=300,
resize_y=300,
min_filter=types.DALIInterpType.INTERP_TRIANGULAR)
saturation = fn.uniform(range=[0.5, 1.5])
contrast = fn.uniform(range=[0.5, 1.5])
brightness = fn.uniform(range=[0.875, 1.125])
hue = fn.uniform(range=[-0.5, 0.5])
images = fn.hsv(images, dtype=types.FLOAT, hue=hue,
saturation=saturation) # use float to avoid clipping and
# quantizing the intermediate result
images = fn.brightness_contrast(
images,
contrast_center=128, # input is in float, but in 0..255 range
dtype=types.UINT8,
brightness=brightness,
contrast=contrast)
dtype = types.FLOAT16 if args.fp16 else types.FLOAT
bboxes = fn.bb_flip(bboxes, ltrb=True, horizontal=flip_coin)
images = fn.crop_mirror_normalize(
images,
crop=(300, 300),
mean=[0.485 * 255, 0.456 * 255, 0.406 * 255],
std=[0.229 * 255, 0.224 * 255, 0.225 * 255],
mirror=flip_coin,
dtype=dtype,
output_layout="CHW",
pad_output=False)
bboxes, labels = fn.box_encoder(bboxes,
labels,
criteria=0.5,
anchors=default_boxes.as_ltrb_list())
labels = labels.gpu()
bboxes = bboxes.gpu()
return images, bboxes, labels
def test_box_encoder_cpu():
def coco_anchors():
anchors = []
fig_size = 300
feat_sizes = [38, 19, 10, 5, 3, 1]
feat_count = len(feat_sizes)
steps = [8., 16., 32., 64., 100., 300.]
scales = [21., 45., 99., 153., 207., 261., 315.]
aspect_ratios = [[2], [2, 3], [2, 3], [2, 3], [2], [2]]
fks = []
for step in steps:
fks.append(fig_size / step)
anchor_idx = 0
for idx in range(feat_count):
sk1 = scales[idx] / fig_size
sk2 = scales[idx + 1] / fig_size
sk3 = sqrt(sk1 * sk2)
all_sizes = [[sk1, sk1], [sk3, sk3]]
for alpha in aspect_ratios[idx]:
w = sk1 * sqrt(alpha)
h = sk1 / sqrt(alpha)
all_sizes.append([w, h])
all_sizes.append([h, w])
for sizes in all_sizes:
w, h = sizes[0], sizes[1]
for i in range(feat_sizes[idx]):
for j in range(feat_sizes[idx]):
cx = (j + 0.5) / fks[idx]
cy = (i + 0.5) / fks[idx]
cx = max(min(cx, 1.), 0.)
cy = max(min(cy, 1.), 0.)
w = max(min(w, 1.), 0.)
h = max(min(h, 1.), 0.)
anchors.append(cx - 0.5 * w)
anchors.append(cy - 0.5 * h)
anchors.append(cx + 0.5 * w)
anchors.append(cy + 0.5 * h)
anchor_idx = anchor_idx + 1
return anchors
pipe = Pipeline(batch_size=batch_size, num_threads=4, device_id=None)
test_box_shape = [20, 4]
def get_boxes():
out = [
(np.random.randint(0, 255, size=test_box_shape, dtype=np.uint8) /
255).astype(dtype=np.float32) for _ in range(batch_size)
]
return out
test_lables_shape = [20, 1]
def get_lables():
out = [
np.random.randint(0, 255, size=test_lables_shape, dtype=np.int32)
for _ in range(batch_size)
]
return out
boxes = fn.external_source(source=get_boxes)
lables = fn.external_source(source=get_lables)
processed, _ = fn.box_encoder(boxes, lables, anchors=coco_anchors())
pipe.set_outputs(processed)
pipe.build()
for _ in range(3):
pipe.run()
def box_encoder_pipeline(get_boxes, get_labels):
boxes = fn.external_source(source=get_boxes)
labels = fn.external_source(source=get_labels)
out = fn.box_encoder(boxes, labels, anchors=coco_anchors())
return tuple(out)
