Fix a link error (#353)

* Fix a link error

* Fix some bugs in "Resume Training"

* Amend a detail about "Resume training"

docs/en/tutorials/getting_started_en.md

@@ -62,7 +62,7 @@ If the training process is terminated for some reasons, you can also load the ch
 ```
 python tools/train.py \
     -c configs/quick_start/MobileNetV3_large_x1_0_finetune.yaml \
-    -o checkpoints="./output/MobileNetV3_large_x1_0_gpupaddle/0/ppcls" \
+    -o checkpoints="./output/MobileNetV3_large_x1_0/5/ppcls" \
     -o last_epoch=5 \
     -o use_gpu=True
 ```
@@ -72,7 +72,7 @@ The configuration file does not need to be modified. You only need to add the `c
 **Note**:
 * The parameter `-o last_epoch=5` means to record the number of the last training epoch as `5`, that is, the number of this training epoch starts from `6`, , and the parameter defaults to `-1`, which means the number of this training epoch starts from `0`.
 
-* The `-o checkpoints` parameter does not need to include the suffix of the checkpoints. The above training command will generate the checkpoints as shown below during the training process. If you want to continue training from the epoch `0`, Just set the `checkpoints` to `./output/MobileNetV3_large_x1_0_gpupaddle/0/ppcls`, PaddleClas will automatically fill in the `pdopt` and `pdparams` suffixes.
+* The `-o checkpoints` parameter does not need to include the suffix of the checkpoints. The above training command will generate the checkpoints as shown below during the training process. If you want to continue training from the epoch `5`, Just set the `checkpoints` to `./output/MobileNetV3_large_x1_0_gpupaddle/5/ppcls`, PaddleClas will automatically fill in the `pdopt` and `pdparams` suffixes.
 
     ```shell
     output/

docs/zh_CN/tutorials/getting_started.md

@@ -1,6 +1,6 @@
 # 开始使用
 ---
-请参考[安装指南](./install.md)配置运行环境，并根据[快速开始](./quick_start)文档准备flower102数据集，本章节下面所有的实验均以flower102数据集为例。
+请参考[安装指南](./install.md)配置运行环境，并根据[快速开始](./quick_start.md)文档准备flower102数据集，本章节下面所有的实验均以flower102数据集为例。
 
 PaddleClas目前支持的训练/评估环境如下：
 ```shell
@@ -71,7 +71,7 @@ python tools/train.py \
 ```
 python tools/train.py \
     -c configs/quick_start/MobileNetV3_large_x1_0_finetune.yaml \
-    -o checkpoints="./output/MobileNetV3_large_x1_0_gpupaddle/0/ppcls" \
+    -o checkpoints="./output/MobileNetV3_large_x1_0/5/ppcls" \
     -o last_epoch=5 \
     -o use_gpu=True
 ```
@@ -81,7 +81,7 @@ python tools/train.py \
 **注意**：
 * 参数`-o last_epoch=5`表示将上一次训练轮次数记为`5`，即本次训练轮次数从`6`开始计算，该值默认为-1，表示本次训练轮次数从`0`开始计算。
 
-* `-o checkpoints`参数无需包含断点权重文件的后缀名，上述训练命令会在训练过程中生成如下所示的断点权重文件，若想从断点`0`继续训练，则`checkpoints`参数只需设置为`"./output/MobileNetV3_large_x1_0_gpupaddle/0/ppcls"`，PaddleClas会自动补充后缀名。
+* `-o checkpoints`参数无需包含断点权重文件的后缀名，上述训练命令会在训练过程中生成如下所示的断点权重文件，若想从断点`5`继续训练，则`checkpoints`参数只需设置为`"./output/MobileNetV3_large_x1_0_gpupaddle/5/ppcls"`，PaddleClas会自动补充后缀名。
     ```shell
     output/
     └── MobileNetV3_large_x1_0