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 random_shuffle(x, seed=None, debugPrefix=""):
if seed is not None:
raise RuntimeError(
'random seed is globally set by session.setRandomSeed')
with bF.name_scope(debugPrefix):
x = bF.cast(x, 'FLOAT')
seeds = bF.randomuniformlike(x, high=6.0, low=-6.0)
flatten_seeds = bF.flatten(seeds)
flatten_seeds_shape = flatten_seeds.pureShape
_K = bF.constant(np.asarray([flatten_seeds_shape[0]]).astype(np.int64))
_, shuffle_indices = bF.topk(flatten_seeds, _K, dim=0)
flatten_x = bF.flatten(x)
shuffle_indices = bF.cast(shuffle_indices, 'INT32')
shuffled_flatten_x = bF.gather(
flatten_x,
shuffle_indices,
dim=0,
)
x_shape = x.pureShape
target_shape = bF.constant(np.asarray(x_shape).astype(np.int64))
shuffled_x = bF.reshape(shuffled_flatten_x, target_shape)
return shuffled_x
def batch_norm(x,
train=False,
fp16_on=None,
weights={
'mean': None,
'var': None,
'scale': None,
'bias': None
},
momentum=0.9,
epsilon=1e-5,
debugPrefix="bn"):
cast_flag, x, fp16_on = bF.deduce_half(x, fp16_on)
batch, c_in, height, width = x.pureShape
dst_type = bF.mappin_gc2npy[x.dtype]
mean = np.zeros(c_in).astype(
dst_type) if weights['mean'] is None else weights['mean']
var = np.ones(c_in).astype(
dst_type) if weights['var'] is None else weights['var']
scale = np.ones(c_in).astype(
dst_type) if weights['scale'] is None else weights['scale']
bias = np.zeros(c_in).astype(
dst_type) if weights['bias'] is None else weights['bias']
with bF.name_scope(debugPrefix):
mean = temporary_init_weights(mean,
"running_mean",
train,
fp16_on=fp16_on)
var = temporary_init_weights(var,
"running_var",
train,
fp16_on=fp16_on)
scale = temporary_init_weights(scale, "weight", train, fp16_on=fp16_on)
bias = temporary_init_weights(bias, "bias", train, fp16_on=fp16_on)
if train:
result = bF._batchNorm(x,
scale,
bias,
mean,
var,
5 if train else 1,
momentum=momentum,
epsilon=epsilon,
debugContext='')
else:
mean = mean.unsqueeze(-1).unsqueeze(-1).unsqueeze(0)
var = var.unsqueeze(-1).unsqueeze(-1).unsqueeze(0)
scale = scale.unsqueeze(-1).unsqueeze(-1).unsqueeze(0)
bias = bias.unsqueeze(-1).unsqueeze(-1).unsqueeze(0)
eps = np.asarray(1e-6).astype(
np.float16 if fp16_on else np.float32)
result = (x - mean) / bF.sqrt(var + eps) * scale + bias
results = [result, mean, var, mean, var]
if cast_flag:
results = [result.cast(cast_flag) for result in results]
return results
def name_scope(scope_name):
return bF.name_scope(scope_name)