Fix upsample bicubic2d batching handling on CPU. (pytorch#52389) (pytorch#52445)

Summary:
Pull Request resolved: pytorch#52389

Fixes: pytorch#49159

Test Plan: Imported from OSS

Reviewed By: albanD

Differential Revision: D26496319

Pulled By: gchanan

fbshipit-source-id: d385cd683ef09e0596a9875ce84d03e6e77acc93

Author: gchanan

aten/src/ATen/native/UpSampleBicubic2d.cpp

@@ -26,7 +26,7 @@ static void upsample_bicubic2d_out_frame(
         const scalar_t* in = &idata[output_y * input_width + output_x];
         scalar_t* out = &odata[output_y * output_width + output_x];
 
-        for (int64_t c = 0; c < channels; ++c) {
+        for (int64_t c = 0; c < channels * nbatch; ++c) {
           out[0] = in[0];
           in += input_width * input_height;
           out += output_width * output_height;

test/test_nn.py

@@ -8674,7 +8674,7 @@ def test_upsamplingBicubic2d(self):
             kwargs = dict(mode='bicubic', align_corners=align_corners)
             # test float scale factor up & downsampling
             for device in device_list:
-                for scale_factor in [0.5, 1.5, 2]:
+                for scale_factor in [0.5, 1, 1.5, 2]:
                     in_t = torch.ones(2, 2, 2, 2).to(device)
                     out_t = F.interpolate(in_t, scale_factor=scale_factor, **kwargs)
                     out_size = int(math.floor(in_t.shape[-1] * scale_factor))