fix doc related to CPU (#3048)

PaddleCV/PaddleDetection/docs/GETTING_STARTED.md

@@ -28,7 +28,7 @@ python tools/train.py -c configs/faster_rcnn_r50_1x.yml
 ```bash
 export CPU_NUM=8
 export PYTHONPATH=$PYTHONPATH:.
-python tools/train.py -c configs/faster_rcnn_r50_1x.yml
+python tools/train.py -c configs/faster_rcnn_r50_1x.yml -o use_gpu=false
 ```
 
 ##### Optional arguments
@@ -80,10 +80,9 @@ python -u tools/train.py -c configs/faster_rcnn_r50_1x.yml \
 
 
 ```bash
-export CUDA_VISIBLE_DEVICES=0
+# run on GPU with:
 export PYTHONPATH=$PYTHONPATH:.
-# or run on CPU with:
-# export CPU_NUM=1
+export CUDA_VISIBLE_DEVICES=0
 python tools/eval.py -c configs/faster_rcnn_r50_1x.yml
 ```
 
@@ -98,10 +97,9 @@ python tools/eval.py -c configs/faster_rcnn_r50_1x.yml
 
 - configuration options && assign Dataset path
 ```bash
-export CUDA_VISIBLE_DEVICES=0
+# run on GPU with:
 export PYTHONPATH=$PYTHONPATH:.
-# or run on CPU with:
-# export CPU_NUM=1
+export CUDA_VISIBLE_DEVICES=0
 python -u tools/eval.py -c configs/faster_rcnn_r50_1x.yml \
                         -o weights=output/faster_rcnn_r50_1x/model_final \
                         -d dataset/coco
@@ -109,13 +107,12 @@ python -u tools/eval.py -c configs/faster_rcnn_r50_1x.yml \
 
 - Evaluation with json
 ```bash
-export CUDA_VISIBLE_DEVICES=0
+# run on GPU with:
 export PYTHONPATH=$PYTHONPATH:.
-# or run on CPU with:
-# export CPU_NUM=1
+export CUDA_VISIBLE_DEVICES=0
 python tools/eval.py -c configs/faster_rcnn_r50_1x.yml \
-		     --json_eval \
-		     -f evaluation/
+             --json_eval \
+             -f evaluation/
 ```
 
 The json file must be named bbox.json or mask.json, placed in the `evaluation/` directory. Or without the `-f` parameter, default is the current directory.
@@ -133,20 +130,18 @@ moment, but it is a planned feature
 - Run inference on a single image:
 
 ```bash
-export CUDA_VISIBLE_DEVICES=0
+# run on GPU with:
 export PYTHONPATH=$PYTHONPATH:.
-# or run on CPU with:
-# export CPU_NUM=1
+export CUDA_VISIBLE_DEVICES=0
 python tools/infer.py -c configs/faster_rcnn_r50_1x.yml --infer_img=demo/000000570688.jpg
 ```
 
 - Multi-image inference:
 
 ```bash
-export CUDA_VISIBLE_DEVICES=0
+# run on GPU with:
 export PYTHONPATH=$PYTHONPATH:.
-# or run on CPU with:
-# export CPU_NUM=1
+export CUDA_VISIBLE_DEVICES=0
 python tools/infer.py -c configs/faster_rcnn_r50_1x.yml --infer_dir=demo
 ```
 
@@ -160,26 +155,24 @@ python tools/infer.py -c configs/faster_rcnn_r50_1x.yml --infer_dir=demo
 
 - Output specified directory && Set up threshold
 ```bash
-export CUDA_VISIBLE_DEVICES=0
+# run on GPU with:
 export PYTHONPATH=$PYTHONPATH:.
-# or run on CPU with:
-# export CPU_NUM=1
+export CUDA_VISIBLE_DEVICES=0
 python tools/infer.py -c configs/faster_rcnn_r50_1x.yml \
                       --infer_img=demo/000000570688.jpg \
                       --output_dir=infer_output/ \
                       --draw_threshold=0.5
 ```
 The visualization files are saved in `output` by default, to specify a different
-path, simply add a `--output_dir=` flag.         
+path, simply add a `--output_dir=` flag.  
 `--draw_threshold` is an optional argument. Default is 0.5. Different thresholds will produce different results depending on the calculation of [NMS](https://ieeexplore.ieee.org/document/1699659)
 
 - Save inference model
 
 ```bash
+# run on GPU with:
 export CUDA_VISIBLE_DEVICES=0
 export PYTHONPATH=$PYTHONPATH:.
-# or run on CPU with:
-# export CPU_NUM=1
 python tools/infer.py -c configs/faster_rcnn_r50_1x.yml \
                       --infer_img=demo/000000570688.jpg \
                       --save_inference_model
@@ -192,12 +185,12 @@ Save inference model by set `--save_inference_model`, which can be loaded by Pad
 
 **Q:**  Why do I get `NaN` loss values during single GPU training? </br>
 **A:**  The default learning rate is tuned to multi-GPU training (8x GPUs), it must
-be adapted for single GPU training accordingly (e.g., divide by 8).       
-The calculation rules are as follows，they are equivalent: </br>     
+be adapted for single GPU training accordingly (e.g., divide by 8).  
+The calculation rules are as follows，they are equivalent: </br>  
 
 
-| GPU number  | Learning rate  | Max_iters | Milestones       |       
-| :---------: | :------------: | :-------: | :--------------: |     
+| GPU number  | Learning rate  | Max_iters | Milestones       |  
+| :---------: | :------------: | :-------: | :--------------: |  
 | 2           | 0.0025         | 720000    | [480000, 640000] |
 | 4           | 0.005          | 360000    | [240000, 320000] |
 | 8           | 0.01           | 180000    | [120000, 160000] |

PaddleCV/PaddleDetection/docs/GETTING_STARTED_cn.md

@@ -29,7 +29,7 @@ python tools/train.py -c configs/faster_rcnn_r50_1x.yml
 ```bash
 export CPU_NUM=8
 export PYTHONPATH=$PYTHONPATH:.
-python tools/train.py -c configs/faster_rcnn_r50_1x.yml
+python tools/train.py -c configs/faster_rcnn_r50_1x.yml -o use_gpu=false
 ```
 
 ##### 可选参数
@@ -51,7 +51,7 @@ python -u tools/train.py -c configs/faster_rcnn_r50_1x.yml --eval
 可通过设置`--eval`在训练epoch中交替执行评估, 评估在每个snapshot_iter时开始。可在配置文件的`snapshot_iter`处修改。
 如果验证集很大，测试将会比较耗时，影响训练速度，建议减少评估次数，或训练完再进行评估。
 
-- 设置配置文件参数 && 指定数据集路径 
+- 设置配置文件参数 && 指定数据集路径
 ```bash
 export CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7
 export PYTHONPATH=$PYTHONPATH:.
@@ -75,10 +75,9 @@ python -u tools/train.py -c configs/faster_rcnn_r50_1x.yml \
 
 
 ```bash
+# GPU评估
 export CUDA_VISIBLE_DEVICES=0
 export PYTHONPATH=$PYTHONPATH:.
-# 若使用CPU，则执行
-# export CPU_NUM=1
 python tools/eval.py -c configs/faster_rcnn_r50_1x.yml
 ```
 
@@ -91,12 +90,11 @@ python tools/eval.py -c configs/faster_rcnn_r50_1x.yml
 
 #### 例子
 
-- 设置配置文件参数 && 指定数据集路径 
+- 设置配置文件参数 && 指定数据集路径
 ```bash
+# GPU评估
 export CUDA_VISIBLE_DEVICES=0
 export PYTHONPATH=$PYTHONPATH:.
-# or run on CPU with:
-# export CPU_NUM=1
 python -u tools/eval.py -c configs/faster_rcnn_r50_1x.yml \
                         -o weights=output/faster_rcnn_r50_1x/model_final \
                         -d dataset/coco
@@ -104,13 +102,12 @@ python -u tools/eval.py -c configs/faster_rcnn_r50_1x.yml \
 
 - 通过json文件评估
 ```bash
+# GPU评估
 export CUDA_VISIBLE_DEVICES=0
 export PYTHONPATH=$PYTHONPATH:.
-# or run on CPU with:
-# export CPU_NUM=1
 python tools/eval.py -c configs/faster_rcnn_r50_1x.yml \
-		     --json_eval \
-		     -f evaluation/
+             --json_eval \
+             -f evaluation/
 ```
 
 json文件必须命名为bbox.json或者mask.json，放在`evaluation/`目录下，或者不加`-f`参数，默认为当前目录。
@@ -127,20 +124,18 @@ json文件必须命名为bbox.json或者mask.json，放在`evaluation/`目录下
 - 单图片推断
 
 ```bash
+# GPU推断
 export CUDA_VISIBLE_DEVICES=0
 export PYTHONPATH=$PYTHONPATH:.
-# 若使用CPU，则执行
-# export CPU_NUM=1
 python tools/infer.py -c configs/faster_rcnn_r50_1x.yml --infer_img=demo/000000570688.jpg
 ```
 
 - 多图片推断
 
 ```bash
+# GPU推断
 export CUDA_VISIBLE_DEVICES=0
 export PYTHONPATH=$PYTHONPATH:.
-# 若使用CPU，则执行
-# export CPU_NUM=1
 python tools/infer.py -c configs/faster_rcnn_r50_1x.yml --infer_dir=demo
 ```
 
@@ -154,10 +149,9 @@ python tools/infer.py -c configs/faster_rcnn_r50_1x.yml --infer_dir=demo
 
 - 设置输出路径 && 设置推断阈值
 ```bash
+# GPU推断
 export CUDA_VISIBLE_DEVICES=0
 export PYTHONPATH=$PYTHONPATH:.
-# or run on CPU with:
-# export CPU_NUM=1
 python tools/infer.py -c configs/faster_rcnn_r50_1x.yml \
                       --infer_img=demo/000000570688.jpg \
                       --output_dir=infer_output/ \
@@ -165,16 +159,15 @@ python tools/infer.py -c configs/faster_rcnn_r50_1x.yml \
 ```
 
 
-可视化文件默认保存在`output`中，可通过`--output_dir=`指定不同的输出路径。       
+可视化文件默认保存在`output`中，可通过`--output_dir=`指定不同的输出路径。  
 `--draw_threshold` 是个可选参数. 根据 [NMS](https://ieeexplore.ieee.org/document/1699659) 的计算，不同阈值会产生不同的结果。
 
 - 保存推断模型
 
 ```bash
+# GPU推断
 export CUDA_VISIBLE_DEVICES=0
 export PYTHONPATH=$PYTHONPATH:.
-# or run on CPU with:
-# export CPU_NUM=1
 python tools/infer.py -c configs/faster_rcnn_r50_1x.yml --infer_img=demo/000000570688.jpg \
                       --save_inference_model
 ```
@@ -185,12 +178,12 @@ python tools/infer.py -c configs/faster_rcnn_r50_1x.yml --infer_img=demo/0000005
 ## FAQ
 
 **Q:**  为什么我使用单GPU训练loss会出`NaN`? </br>
-**A:**  默认学习率是适配多GPU训练(8x GPU)，若使用单GPU训练，须对应调整学习率（例如，除以8）。       
-计算规则表如下所示，它们是等价的: </br>          
+**A:**  默认学习率是适配多GPU训练(8x GPU)，若使用单GPU训练，须对应调整学习率（例如，除以8）。  
+计算规则表如下所示，它们是等价的: </br>  
 
 
-| GPU数  | 学习率  | 最大轮数 | 变化节点       |       
-| :---------: | :------------: | :-------: | :--------------: |     
+| GPU数  | 学习率  | 最大轮数 | 变化节点       |  
+| :---------: | :------------: | :-------: | :--------------: |  
 | 2           | 0.0025         | 720000    | [480000, 640000] |
 | 4           | 0.005          | 360000    | [240000, 320000] |
 | 8           | 0.01           | 180000    | [120000, 160000] |