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) 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): if (aligned): raise RuntimeError( 'Unsupported: ONNX export of roi_align with 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))) 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 min_opset9(g, self, dim_or_y=None, keepdim=None): # torch.min(input) if dim_or_y is None and keepdim is None: return _cast_Long( g, g.op("ReduceMin", _cast_Int(g, self, False), keepdims_i=0), False) # torch.min(input, other) if keepdim is None: return g.op("Min", self, dim_or_y) # torch.min(input, dim, keepdim) else: dim = sym_help._get_const(dim_or_y, 'i', 'dim') keepdim = sym_help._get_const(keepdim, 'i', 'keepdim') min = g.op("ReduceMin", self, axes_i=[dim], keepdims_i=keepdim) indices = g.op('ArgMin', self, axis_i=dim, keepdims_i=keepdim) return min, indices
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 roi_align(g, input, rois, spatial_scale, pooled_height, pooled_width, sampling_ratio): 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))) 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)