[Relay] Fix index order in conv2d computation for Arm CPU.

When dilation is larger than value 1 in conv2d with NHWC
layout, the ordering of indexes when accessing data array
in computation of convolution appears to be incorrect.

'data_vec' is defined as

lambda n, oho, owo, kh, kw, ic, ohi, owi:

But accessed as

data_vec[n, oho, owo, kh, kw, ohi, owi, ic]

This patch fixes the order of indexes.

python/tvm/topi/arm_cpu/conv2d_spatial_pack.py

@@ -344,7 +344,7 @@ def conv2d_spatial_pack_nhwc(cfg, data, kernel, strides, padding, dilation, out_
         conv = te.compute(
             ovshape,
             lambda n, oho, owo, oco, ohi, owi, oci: te.sum(
-                data_vec[n, oho, owo, kh, kw, ohi, owi, ic].astype(out_dtype)
+                data_vec[n, oho, owo, kh, kw, ic, ohi, owi].astype(out_dtype)
                 * kernel_vec[oco, kh, kw, ic, oci].astype(out_dtype),
                 axis=[ic, kh, kw],
             ),