comment out cutmix in hlb_cifar (tinygrad#3201)

it's no-op with multi gpu and less STEPS. also the patch was selected from the whole dataset, not from the same batch

examples/hlb_cifar10.py

@@ -189,7 +189,6 @@ def cutmix(X:Tensor, Y:Tensor, mask_size=3):
     mask = make_square_mask(X.shape, mask_size)
     order = list(range(0, X.shape[0]))
     random.shuffle(order)
-    # NOTE: Memory access fault if use getitem directly
     X_patch = Tensor(X.numpy()[order,...])
     Y_patch = Tensor(Y.numpy()[order])
     X_cutmix = Tensor.where(mask, X_patch, X)
@@ -208,7 +207,8 @@ def fetch_batches(X_in:Tensor, Y_in:Tensor, BS:int, is_train:bool):
       if is_train:
         X = random_crop(X, crop_size=32)
         X = Tensor.where(Tensor.rand(X.shape[0],1,1,1) < 0.5, X[..., ::-1], X) # flip LR
-        if step >= hyp['net']['cutmix_steps']: X, Y = cutmix(X, Y, mask_size=hyp['net']['cutmix_size'])
+        # NOTE: to bring cutmix back, make sure it's performing on mini-batch and not the whole set
+        # if step >= hyp['net']['cutmix_steps']: X, Y = cutmix(X, Y, mask_size=hyp['net']['cutmix_size'])
       X, Y = X.numpy(), Y.numpy()
       et = time.monotonic()
       print(f"shuffling {'training' if is_train else 'test'} dataset in {(et-st)*1e3:.2f} ms ({cnt})")