def decoder(params, qrec, offsets, anchors, scores, anchors_type='centers'):
if anchors_type == 'centers':
anchors_cnts = anchors
else:
anchors_cnts = convert_cors2cnts(anchors)
out_boxes_q = qrec.out_qs[0]
scores_q = qrec.in_qs[1]
score_threshold = scores_q.quantize(params.nms_score_threshold)
# keep only the offsets with score > threshold
bboxes_indices = np.arange(offsets.shape[0])
valid_indices = bboxes_indices[np.any(scores > score_threshold, axis=1)]
valid_scores = scores[valid_indices]
valid_offsets = offsets[valid_indices]
valid_anchors = anchors_cnts[valid_indices]
qrec.set_scales(params)
# xcnt, ycnt --> Q14
# xcnt = (So*O * Sa*Aw)/params.x_scale + Sa*Ax = So*Sa/params.x_scale (O*Aw + x_scale/So * Ax) =
# (scale_x * (O*Aw + (scale_x_anc*Ax)>>scale_x_ancNorm))>>scale_xNorm =
# at_norm(scale_x*(O*Aw + at_norm(scale_x_anc*Ax, scale_x_ancNorm)), scale_xNorm)
xcenter = qrec.scale_x_q.apply_scales(
np.multiply(valid_offsets[:, CNTX_IDX], valid_anchors[:, W_IDX], dtype=np.int32) + \
qrec.scale_x_anc_q.apply_scales(valid_anchors[:, CNTX_IDX])
)
ycenter = qrec.scale_y_q.apply_scales(
np.multiply(valid_offsets[:, CNTY_IDX], valid_anchors[:, H_IDX], dtype=np.int32) + \
qrec.scale_y_anc_q.apply_scales(valid_anchors[:, CNTY_IDX])
)
# half_h, half_w --> Q14
# half_h = exp(So*Off / params.h_scale) * Sa*A = Sa/So * exp(So/params.h_scale *O) * A =
# (scale_ao * (A* exp17.15(scale_h*O<<15-scale_hNorm))>>scale_aoNorm) =
# at_norm(scale_ao*(A*exp17.15(scale_h*O<<15-scale_hNorm)), scale_aoNorm)
norm_h = 15 - qrec.scale_h_q.qnorms
norm_w = 15 - qrec.scale_w_q.qnorms
exp_h = exp_fp_17_15(np.multiply(valid_offsets[:, H_IDX], int(qrec.scale_h_q.qbiases), dtype=np.int32) << norm_h)
exp_w = exp_fp_17_15(np.multiply(valid_offsets[:, W_IDX], int(qrec.scale_w_q.qbiases), dtype=np.int32) << norm_w)
half_h = qrec.scale_ao_q.apply_scales(np.multiply(exp_h, valid_anchors[:, H_IDX], dtype=np.int32)) >> 1
half_w = qrec.scale_ao_q.apply_scales(np.multiply(exp_w, valid_anchors[:, W_IDX], dtype=np.int32)) >> 1
# min-max or corners format: required for nms
decoded_anchors = np.zeros_like(valid_anchors, dtype=out_boxes_q.dtype)
decoded_anchors[:, YMIN_IDX] = ycenter - half_h
decoded_anchors[:, YMAX_IDX] = ycenter + half_h
decoded_anchors[:, XMIN_IDX] = xcenter - half_w
decoded_anchors[:, XMAX_IDX] = xcenter + half_w
return decoded_anchors, valid_scores
def pow_17_15(x, y):
if isinstance(y, int):
y = np.full_like(x, y)
elif y.size == 1 and x.size > 1:
y = np.full_like(x, y[0])
assert np.all(y >= 0), "only postive exponents currently supported"
assert np.all(
y >> 15 == 0), "only fractional exponents currently supported"
return exp_fp_17_15(gap_roundnorm(y * logn_17_15(x), 15))
def execute(cls, params, in_tensors, qrec: QRec, **kwargs):
in_tensor = in_tensors[0].flatten()
max_val = np.max(in_tensor)
norm = 15 + np.ceil(np.log2(qrec.in_qs[0].scale)).astype(np.int32)
exp = exp_fp_17_15((in_tensor.astype(np.int32) - max_val) << (norm))
sum_exp = np.sum(exp)
inv_sum = (np.array([(1 << 15) - 1], dtype=np.uint32) << 15) // sum_exp
res = np.abs((exp * inv_sum + (1 << 14)) >> 15)
iinfo = np.iinfo(np.int16)
res = np.clip(res, iinfo.min, iinfo.max).astype(np.int16).reshape(
params.out_dims[0].shape)
return qrec.get_outputs(params, [res], ktype="symmetric")
def pow_17_15(x, y):
x = np.atleast_1d(x)
y = np.atleast_1d(y)
if isinstance(y, int):
y = np.full_like(x, y)
elif y.size == 1 and x.size > 1:
y = np.full_like(x, y[0])
assert np.all(y >= 0), "only postive exponents currently supported"
assert np.all(
y >> 15 == 0), "only fractional exponents currently supported"
return np.where(x == 0, np.where(y == 0, 1 << 15, 0),
exp_fp_17_15(gap_roundnorm(y * logn_17_15(x), 15)))
def pow_17_15(x, y):
x = np.atleast_1d(x)
y = np.atleast_1d(y)
clip_bits = gap_clb(y)
limit_high = (1 << clip_bits) - 1
limit_low = -(1 << clip_bits)
if isinstance(y, int):
y = np.full_like(x, y)
elif y.size == 1 and x.size > 1:
y = np.full_like(x, y[0])
assert np.all(y >= 0), "only postive exponents currently supported"
assert np.all(y >> 15 == 0), "only fractional exponents currently supported"
return np.where(x == 0, np.where(y == 0, np.int32(1<<15), np.int32(0)), exp_fp_17_15(gap_roundnorm(y * np.clip(logn_17_15(x), limit_low, limit_high), 15))).astype(np.int32)
def softmax_sq8(params,
in_tensors,
qrec: QuantizationRecordBase,
details=None):
del details
in_tensor = in_tensors[0].flatten()
max_val = np.max(in_tensor)
norm = 15 + np.ceil(np.log2(qrec.in_qs[0].scale)).astype(np.int32)
exp = exp_fp_17_15((in_tensor.astype(np.int32) - max_val) << (norm))
sum_exp = np.sum(exp)
inv_sum = (np.array([(1 << 15) - 1], dtype=np.uint32) << 15) // sum_exp
res = np.abs((exp * inv_sum + (1 << 14)) >> 15)
iinfo = np.iinfo(np.int16)
res = np.clip(res, iinfo.min,
iinfo.max).astype(np.int16).reshape(params.out_dims[0].shape)
return qrec.get_outputs(params, [res], ktype="symmetric")
def _impl(self, *args, **kwargs):
return exp_fp_17_15(np.array(args[0]))
def execute(cls, params, in_tensors, qrec: QRec, **kwargs):
in_tensors = qrec.prepare_inputs(params, in_tensors, ktype="symmetric")
offsets = in_tensors[0]
scores = in_tensors[1]
anchors = in_tensors[2]
# decoded_bboxes: Q14
# valid_scores: Q7
anchors_type = "centers"
if anchors_type == 'centers':
anchors_cnts = anchors
else:
anchors_cnts = convert_cors2cnts(anchors)
set_ssd_scales(qrec, params)
scores_q = qrec.in_qs[1]
score_threshold = scores_q.quantize(params.nms_score_threshold)
decoded_bboxes = []
for i in range(scores.shape[0]):
for j in range(scores.shape[1]):
if len(decoded_bboxes) > params.max_bb_before_nms:
break
if scores[i, j] <= score_threshold:
continue
offset = offsets[i]
anchor = anchors[i]
# xcnt, ycnt --> Q14
# xcnt = (So*O * Sa*Aw)/params.x_scale + Sa*Ax = So*Sa/params.x_scale (O*Aw + x_scale/So * Ax) =
# (scale_x * (O*Aw + (scale_x_anc*Ax)>>scale_x_ancNorm))>>scale_xNorm =
# at_norm(scale_x*(O*Aw + at_norm(scale_x_anc*Ax, scale_x_ancNorm)), scale_xNorm)
xcenter = qrec.cache['scale_x_q'].apply_scales(
np.multiply(
offset[CNTX_IDX], anchor[W_IDX], dtype=np.int32) +
qrec.cache['scale_x_anc_q'].apply_scales(anchor[CNTX_IDX]))
ycenter = qrec.cache['scale_y_q'].apply_scales(
np.multiply(
offset[CNTY_IDX], anchor[H_IDX], dtype=np.int32) +
qrec.cache['scale_y_anc_q'].apply_scales(anchor[CNTY_IDX]))
# half_h, half_w --> Q14
# half_h = exp(So*Off / params.h_scale) * Sa*A = Sa/So * exp(So/params.h_scale *O) * A =
# (scale_ao * (A* exp17.15(scale_h*O<<15-scale_hNorm))>>scale_aoNorm) =
# at_norm(scale_ao*(A*exp17.15(scale_h*O<<15-scale_hNorm)), scale_aoNorm)
norm_h = 15 - qrec.cache['scale_h_q'].qnorms
norm_w = 15 - qrec.cache['scale_w_q'].qnorms
exp_h = exp_fp_17_15(
np.multiply(offset[H_IDX],
int(qrec.cache['scale_h_q'].qbiases),
dtype=np.int32) << norm_h)
exp_w = exp_fp_17_15(
np.multiply(offset[W_IDX],
int(qrec.cache['scale_w_q'].qbiases),
dtype=np.int32) << norm_w)
half_h = qrec.cache['scale_ao_q'].apply_scales(
np.multiply(exp_h, anchor[H_IDX], dtype=np.int32)) >> 1
half_w = qrec.cache['scale_ao_q'].apply_scales(
np.multiply(exp_w, anchor[W_IDX], dtype=np.int32)) >> 1
decoded_bboxes.append({
"bbox": [
ycenter - half_h, xcenter - half_w, ycenter + half_h,
xcenter + half_w
],
"score":
scores[i, j],
"class":
j,
"alive":
True
})
# Bubble sort to sort the scores
changed = True
while changed:
changed = False
for i in range(len(decoded_bboxes) - 1):
if decoded_bboxes[i]['score'] < decoded_bboxes[i + 1]['score']:
temp = decoded_bboxes[i]
decoded_bboxes[i] = decoded_bboxes[i + 1]
decoded_bboxes[i + 1] = temp
changed = True
# NMS
for idx in range(len(decoded_bboxes)):
for idx_int in range(idx + 1, len(decoded_bboxes)):
if (not decoded_bboxes[idx_int]['alive']) or (
decoded_bboxes[idx]['class'] !=
decoded_bboxes[idx_int]['class']):
continue
intersection = rect_intersect_area(
decoded_bboxes[idx]['bbox'],
decoded_bboxes[idx_int]['bbox'])
union = rect_union_area(decoded_bboxes[idx]['bbox'],
decoded_bboxes[idx_int]['bbox'])
if intersection >= at_norm(
scores_q.quantize(params.nms_iou_threshold) * union,
7):
decoded_bboxes[idx_int]['alive'] = False
out_boxes = np.zeros((params.max_detections, 4),
dtype=qrec.out_qs[0].dtype)
out_classes = np.zeros(params.max_detections,
dtype=qrec.out_qs[1].dtype)
out_scores = np.zeros(params.max_detections,
dtype=qrec.out_qs[2].dtype)
out_idx = 0
for i in range(len(decoded_bboxes)):
if out_idx >= params.max_detections:
break
bbox = decoded_bboxes[i]
if bbox['alive']:
out_boxes[out_idx] = bbox['bbox']
out_classes[out_idx] = bbox['class']
out_scores[out_idx] = bbox['score']
out_idx += 1
# decoded_bboxes, valid_scores = cls.decoder(
# params, qrec, offsets, anchors, scores, anchors_type='centers')
# out_boxes, out_scores, out_classes = cls.nms(params, qrec, decoded_bboxes, valid_scores)
# out_count = np.array([sum(out_classes != 0)])
return qrec.get_outputs(params, [out_boxes, out_classes, out_scores],
ktype="symmetric")
