def backward(ctx, grad_output):
rois, = ctx.saved_tensors
output_size = ctx.output_size
spatial_scale = ctx.spatial_scale
sampling_ratio = ctx.sampling_ratio
if not ctx.is_nhwc:
bs, ch, h, w = ctx.input_shape
else:
bs, h, w, ch = ctx.input_shape
## TODO: NHWC kernel + transposes is faster than NCHW backward kernel
## Might change to transposes + NHWC kernel if we want to speed up NCHW case
## Cast to fp32 for the kernel because FP16 atomics is slower than FP32 in Volta
grad_input = _C.roi_align_backward(grad_output.float(), rois,
spatial_scale, output_size[0],
output_size[1], bs, ch, h, w,
sampling_ratio, ctx.is_nhwc).half()
return grad_input, None, None, None, None, None
def backward(ctx, grad_output):
rois, = ctx.saved_tensors
output_size = ctx.output_size
spatial_scale = ctx.spatial_scale
sampling_ratio = ctx.sampling_ratio
bs, ch, h, w = ctx.input_shape
grad_input = _C.roi_align_backward(
grad_output,
rois,
spatial_scale,
output_size[0],
output_size[1],
bs,
ch,
h,
w,
sampling_ratio,
)
return grad_input, None, None, None, None
def backward(ctx, grad_output):
rois, = ctx.saved_tensors
output_size = ctx.output_size
spatial_scale = ctx.spatial_scale
sampling_ratio = ctx.sampling_ratio
bs, ch, h, w = ctx.input_shape
grad_input = _C.roi_align_backward(
grad_output,
rois,
spatial_scale,
output_size[0],
output_size[1],
bs,
ch,
h,
w,
sampling_ratio,
)
return grad_input, None, None, None, None
