Update README.md (apache#7248)

example/image-classification/README.md

@@ -39,7 +39,7 @@ commonly used options are listed as following:
 
 | Argument                      | Comments                                 |
 | ----------------------------- | ---------------------------------------- |
-| `network`                     | The network to train, which is defined in [symbol/](https://github.com/dmlc/mxnet/tree/master/example/image-classification/symbol). Some networks may accept additional arguments, such as `--num-layers` is used to specify the number of layers in ResNet. |
+| `network`                     | The network to train, which is defined in [symbol/](https://github.com/dmlc/mxnet/tree/master/example/image-classification/symbols). Some networks may accept additional arguments, such as `--num-layers` is used to specify the number of layers in ResNet. |
 | `data-train`, `data-val`      | The data for training and validation. It can be either a filename or a directory. For the latter, all files in the directory will be used. But if `--benchmark 1` is used, then there two arguments will be ignored. |
 | `gpus`                        | The list of GPUs to use, such as `0` or `0,3,4,7`. If an empty string `''` is given, then we will use CPU. |
 | `batch-size`                  | The batch size for SGD training. It specifies the number of examples used for each SGD iteration. If we use *k* GPUs, then each GPU will compute *batch_size/k* examples in each time. |