Update README.md and add minor fixes

Author: daniilpastukhov

gen2/gen2-fatigue-detection/README.zh-CN.md

@@ -1,6 +1,6 @@
 [英文文档](README.md)
 
-# Gen2 疲劳检测
+# 疲劳检测
 
 该示例演示了Gen2 Pipeline Builder运行的 [面部检测网络](https://docs.openvinotoolkit.org/2019_R1/_face_detection_retail_0004_description_face_detection_retail_0004.html)和头部检测网络
 

gen2/gen2-license-plate-recognition/main.py

@@ -16,6 +16,7 @@
                     help="Path to video file to be used for inference (conflicts with -cam)")
 args = parser.parse_args()
 
+args.video = 'chinese_traffic.mp4'
 if not args.camera and not args.video:
     raise RuntimeError(
         "No source selected. Use either \"-cam\" to run on RGB camera as a source or \"-vid <path>\" to run on video"
@@ -159,6 +160,7 @@ def lic_thread(det_queue, rec_queue):
                 img.setData(to_planar(cropped_frame, (94, 24)))
                 img.setWidth(94)
                 img.setHeight(24)
+
                 rec_queue.send(img)
 
             fps.tick('lic')
@@ -319,6 +321,7 @@ def get_frame():
                 lic_frame.setType(dai.RawImgFrame.Type.BGR888p)
                 lic_frame.setWidth(300)
                 lic_frame.setHeight(300)
+
                 det_in.send(lic_frame)
                 veh_frame = dai.ImgFrame()
                 veh_frame.setData(to_planar(frame, (300, 300)))

sdk/sdk-class-saver-jpeg/README.md

@@ -43,7 +43,7 @@ timestamp,label,left,top,right,bottom,raw_frame,overlay_frame,cropped_frame
 
 ## Demo
 
-[![Gen2 Class Saver (JPEG)](https://user-images.githubusercontent.com/5244214/106964520-83b34b00-6742-11eb-8729-eff0a7584a46.gif)](https://youtu.be/gKawPaUcTi4 "Class Saver (JPEG) on DepthAI")
+[![Class Saver (JPEG)](https://user-images.githubusercontent.com/5244214/106964520-83b34b00-6742-11eb-8729-eff0a7584a46.gif)](https://youtu.be/gKawPaUcTi4 "Class Saver (JPEG) on DepthAI")
 
 ## Install requirements
 

sdk/sdk-class-saver-jpeg/README.zh-CN.md

@@ -1,6 +1,6 @@
 [英文文档](README.md)
 
-# SDK Class Saver (JPEG)
+# Class Saver (JPEG)
 
 本示例演示如何运行MobilenetSSD并收集按检测标签分组的检测对象的图像。运行此脚本后，DepthAI将启动MobilenetSSD，并且每当检测到对象时，它将添加一个数据集条目。
 
@@ -42,7 +42,7 @@ timestamp,label,left,top,right,bottom,raw_frame,overlay_frame,cropped_frame
 
 ## 演示
 
-[![Gen2 Class Saver (JPEG)](https://user-images.githubusercontent.com/5244214/106964520-83b34b00-6742-11eb-8729-eff0a7584a46.gif)](https://youtu.be/gKawPaUcTi4 "Class Saver (JPEG) on DepthAI")
+[![Class Saver (JPEG)](https://user-images.githubusercontent.com/5244214/106964520-83b34b00-6742-11eb-8729-eff0a7584a46.gif)](https://youtu.be/gKawPaUcTi4 "Class Saver (JPEG) on DepthAI")
 
 ## 先决条件
 

sdk/sdk-crowdcounting/README.md

@@ -1,17 +1,19 @@
-## [Gen2] Crowd Counting with density maps on DepthAI
+## Crowd Counting with density maps
 
-This example shows an implementation of Crowd Counting with density maps on DepthAI in the Gen2 API system.  We use [DM-Count](https://github.com/cvlab-stonybrook/DM-Count) ([LICENSE](https://github.com/cvlab-stonybrook/DM-Count/blob/master/LICENSE)) model, which has a VGG-19 backbone and is trained on Shanghai B data set.
+This example shows an implementation of Crowd Counting with density maps using DepthAI SDK. We
+use [DM-Count](https://github.com/cvlab-stonybrook/DM-Count) ([LICENSE](https://github.com/cvlab-stonybrook/DM-Count/blob/master/LICENSE))
+model, which has a VGG-19 backbone and is trained on Shanghai B data set.
 
 The model produces density map from which predicted count can be computed.
 
-Input video is resized to 426 x 240 (W x H). Due to a relatively heavy model, the inference speed is around 1 FPS.
+Input video is resized to 426x240 (WxH). Due to a relatively heavy model, the inference speed is around 1 FPS.
 
 ![Image example](imgs/example.gif)
 
 ![image](https://user-images.githubusercontent.com/32992551/171780142-5cd4f2a4-6c51-4dbc-9e3e-17062a9c6c6c.png)
 
-
-Example shows input video with overlay density map input. Example video taken from [VIRAT](https://viratdata.org/) dataset.
+Example shows input video with overlay density map input. Example video taken from [VIRAT](https://viratdata.org/)
+dataset.
 
 ## Pre-requisites
 

sdk/sdk-deeplabv3-person/README.zh-CN.md

@@ -1,8 +1,8 @@
 [英文文档](README.md)
 
-## [Gen2] DepthAI上的Deeplabv3
+## DepthAI上的DeepLabV3
 
-此示例显示了如何在Gen2 API系统中的DepthAI上运行Deeplabv3+。
+此示例显示了如何在 SDK 系统中的DepthAI上运行DeepLabV3+。
 
 [![Semantic Segmentation on DepthAI](https://user-images.githubusercontent.com/32992551/109359126-25a9ed00-7842-11eb-9071-cddc7439e3ca.png)](https://www.youtube.com/watch?v=zjcUChyyNgI "Deeplabv3+ Custom Training for DepthAI")
 

sdk/sdk-fast-depth/README.md

@@ -1,6 +1,8 @@
-## [Gen2] FastDepth on DepthAI
+## FastDepth
 
-This example shows an implementation of [FastDepth](https://github.com/dwofk/fast-depth) on DepthAI in the Gen2 API system.  Blob is created with ONNX from [PINTO's Model ZOO](https://github.com/PINTO0309/PINTO_model_zoo/tree/main/146_FastDepth), which is then converted to OpenVINO IR with required flags and converted to blob.
+This example shows an implementation of [FastDepth](https://github.com/dwofk/fast-depth) using DepthAI SDK. Blob is
+created with ONNX from [PINTO's Model ZOO](https://github.com/PINTO0309/PINTO_model_zoo/tree/main/146_FastDepth), which
+is then converted to OpenVINO IR with required flags and converted to blob.
 
 There are two available blob's for different input sizes:
 
@@ -12,6 +14,7 @@ There are two available blob's for different input sizes:
 ## Pre-requisites
 
 Install requirements:
+
 ```
 python3 -m pip install -r requirements.txt
 ```

sdk/sdk-fatigue-detection/README.zh-CN.md

@@ -1,8 +1,8 @@
 [英文文档](README.md)
 
-# Gen2 疲劳检测
+# 疲劳检测
 
-该示例演示了Gen2 Pipeline Builder运行的 [面部检测网络](https://docs.openvinotoolkit.org/2019_R1/_face_detection_retail_0004_description_face_detection_retail_0004.html)和头部检测网络
+该示例演示了 运行的 [面部检测网络](https://docs.openvinotoolkit.org/2019_R1/_face_detection_retail_0004_description_face_detection_retail_0004.html)和头部检测网络
 
 ## 演示:
 

sdk/sdk-flower-classification/README.zh-CN.md

@@ -1,6 +1,6 @@
 [英文文档](README.md)
 
-# Gen2 Tensorflow 图像分类示例
+# Tensorflow 图像分类示例
 
 该示例演示了如何运行使用 [TensorFlow Image Classification tutorial](https://colab.research.google.com/drive/1oNxfvx5jOfcmk1Nx0qavjLN8KtWcLRn6?usp=sharing)创建的神经网络 （即使将OpenVINO转换为.blob，我们的社区成员之一也将其整合到了一个Colab Notebook中）
 

sdk/sdk-human-pose/README.md

@@ -10,11 +10,11 @@ using DepthAI SDK.
 
 ### Camera
 
-[![Gen2 Age & Gender recognition](https://user-images.githubusercontent.com/5244214/107493701-35f97100-6b8e-11eb-8b13-02a7a8dbec21.gif)](https://www.youtube.com/watch?v=Py3-dHQymko "Human pose estimation on DepthAI")
+[![Age & Gender recognition](https://user-images.githubusercontent.com/5244214/107493701-35f97100-6b8e-11eb-8b13-02a7a8dbec21.gif)](https://www.youtube.com/watch?v=Py3-dHQymko "Human pose estimation on DepthAI")
 
 ### Video file
 
-[![Gen2 Age & Gender recognition](https://user-images.githubusercontent.com/5244214/110801736-d3bf8900-827d-11eb-934b-9755978f80d9.gif)](https://www.youtube.com/watch?v=1dp2wJ_OqxI "Human pose estimation on DepthAI")
+[![Age & Gender recognition](https://user-images.githubusercontent.com/5244214/110801736-d3bf8900-827d-11eb-934b-9755978f80d9.gif)](https://www.youtube.com/watch?v=1dp2wJ_OqxI "Human pose estimation on DepthAI")
 
 ## Pre-requisites