def temporary_init_weights(data,
name,
train=True,
fp16_on=False,
load_global_first=True):
local_func = bF.addInitializedInputTensor if train else bF.constant
global_initializer = bF.get_global_initializer()
local_name = bF.get_builder().getNameScope(name)
if global_initializer.get(local_name,
None) is not None and load_global_first:
# overwrite data
if local_name not in bF.get_exclude_weights():
new_data = bF.get_global_initializer()[local_name]
assert np.all(
np.asarray(new_data.shape) == np.asarray(
data.shape)), '{}: {} vs {}'.format(
name, new_data.shape, data.shape)
data = new_data
else:
assert not bF.load_strict(
), 'The global load_strict has been set, but the missing weight is detected: {}'.format(
name)
data = data.astype(np.float16 if fp16_on else np.float32)
weights = local_func(data, name)
if train:
GLOBAL_V['all_trainable_weights'].append(weights)
GLOBAL_V['all_weights'].append(weights)
return weights
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 roi_align(bottom_data,
bottom_rois,
spatial_scale=1 / 16.0,
num_rois=300,
aligned_height=7,
aligned_width=7,
fp16_on=None):
"""roi_align implements."""
load_lib()
assert isinstance(aligned_height, int) and isinstance(
aligned_width,
int), 'they should be int or IndexError: map::at will raised'
cast_flag, bottom_data, fp16_on = bF.deduce_half(bottom_data, fp16_on)
if fp16_on:
bottom_rois = bottom_rois.cast('FLOAT16')
else:
bottom_rois = bottom_rois.cast('FLOAT')
if fp16_on:
raise NotImplementedError('maybe not implemented')
# same as detectron2 roi_align version2(aligned=True and sampling_ratio=1)
batch_size, channels, height, width = bottom_data.pureShape
with bF.name_scope("roiAlign"):
out = bF.get_builder().customOp(
opName="roiAlign",
opVersion=1,
domain="ai.graphcore",
inputs=[bottom_data.getIpuIndex(),
bottom_rois.getIpuIndex()],
attributes={
"spatial_scale": spatial_scale,
"batch_size": batch_size,
"num_rois": num_rois,
"height": height,
"width": width,
"channels": channels,
"aligned_height": aligned_height,
"aligned_width": aligned_width
},
numOutputs=1)
result = bF.TTensor(out[0])
if cast_flag:
result = result.cast(cast_flag)
return result
def __init__(self, pattern):
self.builder = bF.get_builder()
self.pattern = pattern
self.stack = ExitStack()
def init_proto(self, ):
self.proto = bF.get_builder().getModelProto()