Merge pull request #14 from hailo-ai/update-documentation-12-04

Update documentation 12 04

docs/HAILO_MODELS.md

@@ -8,6 +8,11 @@ Each model is accompanied with its own README, retraining docker and retraining
     - [Object Detection](#object-detection)
     - [License Plate Recognition](#license-plate-recognition)
 
+> **Important**:  
+    Retraining is not available inside the docker version of Hailo Software Suite. In case you use it, clone the hailo_model_zoo outside of the docker, and perform the retraining there:  
+    ```git clone https://github.com/hailo-ai/hailo_model_zoo.git``` 
+
+
 <br>
 
 ## Object Detection

docs/RETRAIN_ON_CUSTOM_DATASET.md

@@ -2,10 +2,13 @@
 
 This page will help you ramping-up your training environment for various tasks and architectures.
 Each architecture has its own README which describes how to:
-   1. Setup the environment using a compatible   Dockerfile.
+   1. Setup the environment using a compatible Dockerfile.
    2. Start the training process.
    3. Export your model.
 
+> **Important**:  
+    Retraining is not available inside the docker version of Hailo Software Suite. In case you use it, clone the hailo_model_zoo outside of the docker, and perform the retraining there:  
+    ```git clone https://github.com/hailo-ai/hailo_model_zoo.git``` 
 <br>
 
 ## Object Detection

hailo_models/license_plate_detection/docs/TRAINING_GUIDE.md

@@ -58,7 +58,6 @@ Once the docker is started, you can train the license plate detector on your cus
 ## Compile the Model using Hailo Model Zoo<br>
 You can generate an HEF file for inference on Hailo-8 from your trained ONNX model. In order to do so you need a working model-zoo environment.
 Choose the model YAML from our networks configuration directory, i.e. `hailo_model_zoo/cfg/networks/tiny_yolov4_license_plates.yaml`, and run compilation using the model zoo:
-> **_NOTE:_** The following command should be run outside the docker
 ```
 python hailo_model_zoo/main.py compile --ckpt tiny_yolov4_license_plates.onnx --calib-path /path/to/calibration/imgs/dir/ --yaml tiny_yolov4_license_plates.yaml
 ```

hailo_models/license_plate_recognition/docs/TRAINING_GUIDE.md

@@ -59,7 +59,6 @@ Export the model to ONNX using the following command:
 ## Compile the Model using Hailo Model Zoo<br>
 You can generate an HEF file for inference on Hailo-8 from your trained ONNX model. In order to do so you need a working model-zoo environment.
 Choose the model YAML from our networks configuration directory, i.e. `hailo_model_zoo/cfg/networks/lprnet.yaml`, and run compilation using the model zoo:
-> **_NOTE:_** The following command should be run outside the docker
 ```
 python hailo_model_zoo/main.py compile --ckpt lprnet.onnx --calib-path /path/to/calibration/imgs/dir/ --yaml lprnet.yaml
 ```

hailo_models/vehicle_detection/docs/TRAINING_GUIDE.md

@@ -58,7 +58,6 @@ Export the model to ONNX using the following command:
 ## Compile the Model using Hailo Model Zoo<br>
 You can generate an HEF file for inference on Hailo-8 from your trained ONNX model. In order to do so you need a working model-zoo environment.
 Choose the model YAML from our networks configuration directory, i.e. `hailo_model_zoo/cfg/networks/yolov5m_vehicles.yaml`, and run compilation using the model zoo:
-> **_NOTE:_** The following command should be run outside the docker
 ```
 python hailo_model_zoo/main.py compile --ckpt yolov5m_vehicles.onnx --calib-path /path/to/calibration/imgs/dir/ --yaml yolov5m_vehicles.yaml
 ```

training/centerpose/README.md

@@ -5,7 +5,7 @@
 ## Prerequisites
   * docker ([installation instructions](https://docs.docker.com/engine/install/ubuntu/))
   * nvidia-docker2 ([installation instructions](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html))
-  > **_NOTE:_**  In case you use Hailo Software Suite docker, make sure you are doing all the following instructions outside this docker.
+  > **_NOTE:_**  In case you use Hailo Software Suite docker, make sure you are doing all the following instructions outside of this docker.
 ## Environment Preparations
 1. Build the docker image:
 

training/fcn/README.md

@@ -5,7 +5,7 @@
 ### Prerequisites
   * docker ([installation instructions](https://docs.docker.com/engine/install/ubuntu/))
   * nvidia-docker2 ([installation instructions](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html))
-  > **_NOTE:_**  In case you use Hailo Software Suite docker, make sure you are doing all the following instructions outside this docker.
+  > **_NOTE:_**  In case you use Hailo Software Suite docker, make sure you are doing all the following instructions outside of this docker.
 ### Environment Preparations
 1. Build the docker image:
 

training/nanodet/README.md

@@ -5,7 +5,7 @@
 ## Prerequisites
   * docker ([installation instructions](https://docs.docker.com/engine/install/ubuntu/))
   * nvidia-docker2 ([installation instructions](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html))
-  > **_NOTE:_**  In case you use Hailo Software Suite docker, make sure you are doing all the following instructions outside this docker.
+  > **_NOTE:_**  In case you use Hailo Software Suite docker, make sure you are doing all the following instructions outside of this docker.
 ## Environment Preparations
 1. Build the docker image:
 

training/ssd/README.md

@@ -5,7 +5,7 @@
 ## Prerequisites
   * docker ([installation instructions](https://docs.docker.com/engine/install/ubuntu/))
   * nvidia-docker2 ([installation instructions](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html))
-  > **_NOTE:_**  In case you use Hailo Software Suite docker, make sure you are doing all the following instructions outside this docker.
+  > **_NOTE:_**  In case you use Hailo Software Suite docker, make sure you are doing all the following instructions outside of this docker.
 ## Environment Preparations
 1. Build the docker image:
 
@@ -69,12 +69,7 @@
     Start training with the following command:
     
     <code stage="retrain">
-    python object_detection/model_main.py \
-    --pipeline_config_path=/home/tensorflow/models/research/pipeline.config \
-    --model_dir=ssd_mobilenet_v1_training \
-    --num_train_steps=<span val="iterations">200000</span> \
-    --sample_1_of_n_eval_examples=3 \
-    --alsologtostderr
+    python object_detection/model_main.py --pipeline_config_path=/home/tensorflow/models/research/pipeline.config --model_dir=ssd_mobilenet_v1_training --num_train_steps=<span val="iterations">200000</span> --sample_1_of_n_eval_examples=3 --alsologtostderr
     </code>
 
     * <code>--pipeline_config_path</code> - path to your training configuration file.
@@ -136,4 +131,4 @@ Choose the corresponding YAML from our networks configuration directory, i.e. <c
   The model zoo will take care of adding the input normalization to be part of the model.
 > *_NOTE_*: SSD postprocessing, including the box decoding and NMS, can be offloaded to the Hailo device. To do so, we use another JSON file which configures the Hailo Data Flow Compiler to add the neccessery layers. To edit this file check <code>models_files/ObjectDetection/Detection-COCO/ssd/ssd_mobilenet_v1/pretrained/mobilenet_ssd_nms_postprocess_config.json</code>, which is being downloaded automatically when testing ssd_mobilenet_v1.
 
-The compiled model can be used in the [**Hailo TAPPAS**](https://hailo.ai/developer-zone/tappas-apps-toolkit/) to generate a full application.
+The compiled model can be used in the [**Hailo TAPPAS**](https://hailo.ai/developer-zone/tappas-apps-toolkit/) to generate a full application.

training/yolact/README.md

@@ -4,7 +4,7 @@
 ## Prerequisites
   * docker ([installation instructions](https://docs.docker.com/engine/install/ubuntu/))
   * nvidia-docker2 ([installation instructions](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html))
-  > **_NOTE:_**  In case you use Hailo Software Suite docker, make sure you are doing all the following instructions outside this docker.
+  > **_NOTE:_**  In case you use Hailo Software Suite docker, make sure you are doing all the following instructions outside of this docker.
 ## Environment Preparations
 1. Build the docker image:
 

training/yolov3/README.md

@@ -5,7 +5,7 @@
 ## Prerequisites
   * docker ([installation instructions](https://docs.docker.com/engine/install/ubuntu/))
   * nvidia-docker2 ([installation instructions](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html))
-  > **_NOTE:_**  In case you use Hailo Software Suite docker, make sure you are doing all the following instructions outside this docker.
+  > **_NOTE:_**  In case you use Hailo Software Suite docker, make sure you are doing all the following instructions outside of this docker.
 ## Environment Preparations
   1. Build the docker image:
 

training/yolov4/README.md

@@ -5,7 +5,7 @@
 ### Prerequisites
   * docker ([installation instructions](https://docs.docker.com/engine/install/ubuntu/))
   * nvidia-docker2 ([installation instructions](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html))
-  > **_NOTE:_**  In case you use Hailo Software Suite docker, make sure you are doing all the following instructions outside this docker.
+  > **_NOTE:_**  In case you use Hailo Software Suite docker, make sure you are doing all the following instructions outside of this docker.
 ### Environment Preparations
   1. Build the docker image:
 

training/yolov5/README.md

@@ -5,7 +5,7 @@
 ## Prerequisites
   * docker ([installation instructions](https://docs.docker.com/engine/install/ubuntu/))
   * nvidia-docker2 ([installation instructions](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html))
-  > **_NOTE:_**  In case you use Hailo Software Suite docker, make sure you are doing all the following instructions outside this docker.
+  > **_NOTE:_**  In case you use Hailo Software Suite docker, make sure you are doing all the following instructions outside of this docker.
 ## Environment Preparations
   1. Build the docker image:
 

training/yolox/README.md

@@ -6,7 +6,7 @@
 ## Prerequisites
   * docker ([installation instructions](https://docs.docker.com/engine/install/ubuntu/))
   * nvidia-docker2 ([installation instructions](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html))
-  > **_NOTE:_**  In case you use Hailo Software Suite docker, make sure you are doing all the following instructions outside this docker.
+  > **_NOTE:_**  In case you use Hailo Software Suite docker, make sure you are doing all the following instructions outside of this docker.
 ## Environment Preparations
   1. Build the docker image: