|
请教一下各位大神:
我这边现在在将pysot中的siamrpn++模型转换到RK3588的平台,在转换完成rpn_head.onnx模型后对比rpn_head.rknn和rpn_head.onnx的结果,发现差距比较大。通过调试后发现是rpn_head中的互相关操作结果对不上了,具体函数是
def xcorr_depthwise(x, kernel):
"""depthwise cross correlation
"""
batch = kernel.size(0)
channel = kernel.size(1)
x = x.view(1, batch*channel, x.size(2), x.size(3))
kernel = kernel.view(batch*channel, 1, kernel.size(2), kernel.size(3))
out = F.conv2d(x, kernel, groups=batch*channel)
out = out.view(batch, channel, out.size(2), out.size(3))
return out
结构图为
具体计算方式为该conv层接收上层的[256,1,5,5]维的数据初始化conv节点中的参数,然后对【1,256,29,29】维的数据进行卷积操作。
请问一下想要实现该计算方式应该如何操作?
|
|