def roi_align(g, input, rois, spatial_scale, pooled_height, pooled_width,
sampling_ratio, aligned):
batch_indices = _cast_Long(
g,
squeeze(
g,
select(
g, rois, 1,
g.op('Constant',
value_t=torch.tensor([0], dtype=torch.long))), 1),
False)
rois = select(
g, rois, 1,
g.op('Constant',
value_t=torch.tensor([1, 2, 3, 4], dtype=torch.long)))
if aligned:
warnings.warn(
"ONNX export of ROIAlign with aligned=True does not match PyTorch when using malformed boxes,"
" ONNX forces ROIs to be 1x1 or larger.")
scale = torch.tensor(0.5 / spatial_scale).to(dtype=torch.float)
rois = g.op("Sub", rois, scale)
# ONNX doesn't support negative sampling_ratio
if sampling_ratio < 0:
warnings.warn("ONNX doesn't support negative sampling ratio,"
"therefore is is set to 0 in order to be exported.")
sampling_ratio = 0
return g.op('RoiAlign',
input,
rois,
batch_indices,
spatial_scale_f=spatial_scale,
output_height_i=pooled_height,
output_width_i=pooled_width,
sampling_ratio_i=sampling_ratio)
def roi_align(g, input, rois, spatial_scale, pooled_height, pooled_width,
sampling_ratio, aligned):
batch_indices = _cast_Long(
g,
squeeze(
g,
select(
g, rois, 1,
g.op("Constant",
value_t=torch.tensor([0], dtype=torch.long))), 1),
False)
rois = select(
g, rois, 1,
g.op("Constant",
value_t=torch.tensor([1, 2, 3, 4], dtype=torch.long)))
# TODO: Remove this warning after ONNX opset 16 is supported.
if aligned:
warnings.warn(
"ROIAlign with aligned=True is not supported in ONNX, but will be supported in opset 16. "
"The workaround is that the user need apply the patch "
"https://github.com/microsoft/onnxruntime/pull/8564 "
"and build ONNXRuntime from source.")
# ONNX doesn't support negative sampling_ratio
if sampling_ratio < 0:
warnings.warn(
"ONNX doesn't support negative sampling ratio, therefore is set to 0 in order to be exported."
)
sampling_ratio = 0
return g.op(
"RoiAlign",
input,
rois,
batch_indices,
spatial_scale_f=spatial_scale,
output_height_i=pooled_height,
output_width_i=pooled_width,
sampling_ratio_i=sampling_ratio,
)
def symbolic_multi_label_nms(g, boxes, scores, iou_threshold):
boxes = unsqueeze(g, boxes, 0)
scores = unsqueeze(g, unsqueeze(g, scores, 0), 0)
max_output_per_class = g.op("Constant",
value_t=torch.tensor([sys.maxsize],
dtype=torch.long))
iou_threshold = g.op("Constant",
value_t=torch.tensor([iou_threshold],
dtype=torch.float))
nms_out = g.op("NonMaxSuppression", boxes, scores,
max_output_per_class, iou_threshold)
return squeeze(
g,
select(
g, nms_out, 1,
g.op("Constant", value_t=torch.tensor([2], dtype=torch.long))),
1)