def transpose(a, perm=None, conjugate=False, name='transpose'):
a_rank = len(a.pureShape)
if perm is None:
perm = [1, 0]
assert a_rank == 2
assert conjugate is False, 'not implement if conjugate is True'
for dim in perm:
assert dim < a_rank
return bF.transpose(a, perm, debugContext=name)
def nms(input_scores,
input_boxes,
threshold=0.7,
numDetections=300,
score_threshold=None,
debugContext=''):
load_lib()
input_scores = input_scores.cast('FLOAT')
input_boxes = input_boxes.cast('FLOAT')
valid_area_mask = bF.transpose(get_valid_area_mask(input_boxes),
[1, 0]) # 1,n
input_scores = input_scores + 1e-6 # if score==0, proposals will be ignored
local_input_scores = bF.identity(input_scores * valid_area_mask,
debugContext=debugContext).detach()
local_input_boxes = bF.identity(input_boxes,
debugContext=debugContext).detach()
if local_input_scores.shape.ndims == 1:
local_input_scores = local_input_scores.unsqueeze(0)
if local_input_boxes.shape.ndims == 2:
local_input_boxes = local_input_boxes.unsqueeze(0)
assert local_input_boxes.pureShape[0] == 1, 'only implemented batch=1'
if score_threshold is not None:
assert isinstance(score_threshold, float)
local_mask = bF.greater(
local_input_scores,
bF.to_tensor(score_threshold, dtype=local_input_scores.dtype))
local_mask = bF.cast(local_mask, target_type=local_input_scores.dtype)
local_input_scores = local_input_scores * local_mask
with bF.name_scope("nms"):
out = bF.get_builder().customOp(opName="nms",
opVersion=1,
domain="ai.graphcore",
inputs=[
local_input_scores.getIpuIndex(),
local_input_boxes.getIpuIndex()
],
attributes={
"threshold": threshold,
"numDetections": numDetections
},
numOutputs=3,
name="nmsCustomOp")
#
_, output_boxes, output_keep = out[0], bF.TTensor(out[1]), bF.TTensor(
out[2])
targetType = input_scores.dtype
roiKeeps_flag = bF.cast(bF.greater(
output_keep, bF.constant(np.asarray(-1, dtype=np.int32))),
target_type='INT32')
num_valids = bF.reduceSum(roiKeeps_flag, axes=[1])
roiKeeps_flag = bF.cast(roiKeeps_flag, target_type=targetType)
roiKeeps_flag = bF.unsqueeze(roiKeeps_flag, [-1])
output_boxes = bF.mul([output_boxes, roiKeeps_flag])
return output_boxes, output_keep, num_valids
def get_valid_area_mask(boxes):
# input boxes: 1,n,4
# output: mask: n,1
ws = boxes[:, :, 2] - boxes[:, :, 0]
hs = boxes[:, :, 3] - boxes[:, :, 1]
areas = ws * hs
valid_flags = bF.greater(
areas, bF.constant(np.asarray(0.0,
dtype=bF.mappin_gc2npy[areas.dtype])))
valid_mask = bF.cast(valid_flags, target_type=boxes.dtype)
return bF.transpose(valid_mask, [1, 0])