# DeepLab-v3 using the Qualcomm Neural Processing SDK for AI on Ubuntu

Source: [https://docs.qualcomm.com/doc/80-63442-4/topic/deeplab-v3-on-ubuntu.html](https://docs.qualcomm.com/doc/80-63442-4/topic/deeplab-v3-on-ubuntu.html)

Procedure for training, converting and running a DeepLab model for image
        segmentation

Semantic segmentation involves applying a label, such as “tree,” “flower,” “grass” or
            “house,” to every pixel in an image. It is useful in applications like changing the
            background of an image. [DeepLab-v3](https://ai.googleblog.com/2018/03/semantic-image-segmentation-with.html) is a model implemented by Google
            for semantic segmentation that classifies objects in an image, pixel by pixel, and
            assigns a label to them.

DeepLab-v3 is used in multiple mobile devices for implementing portrait mode in the
            camera. This article describes how to train a DeepLab-v3 model with the help of
            Qualcomm® Neural Processing SDK for AI.

(For a comprehensive look at image segmentation and DeepLab-v3, visit [Semantic Segmentation: Introduction to the Deep
                Learning Technique Behind Google Pixel’s Camera](https://www.analyticsvidhya.com/blog/2019/02/tutorial-semantic-segmentation-google-deeplab/).)

## Training the model

Collecting and pre-processing data are the most time-consuming tasks in machine
                learning. To save time, many researchers use pre-processed datasets for object
                detection, segmentation and captions.

## Converting a model into a DLC

To run with the Qualcomm Neural Processing SDK, the pre-trained DeepLab model must be
                converted to deep learning container (DLC) format using the Qualcomm Neural
                Processing SDK for AI. To use a custom-trained DeepLab model, follow the
                instructions provided in the “Training the model” section above.

If the Qualcomm Neural Processing SDK is not yet installed, refer to the instructions
                on the [Getting Started page](https://docs.qualcomm.com/bundle/publicresource/topics/80-63442-2/setup.html).

## **1. Downloading and extracting the model**

Execute the following command to download and extract the pre-trained DeepLab
                model:

    $wget
    http://download.tensorflow.org/models/deeplabv3_mnv2_pascal_train_aug_2018_01_29.tar.gz
    $tar -xzvf deeplabv3_mnv2_pascal_train_aug_2018_01_29.tar.gzCopy to clipboard

## **2. Converting the model**

The model is pre-trained using the TensorFlow framework and exported to a graph file
                with the .pb extension. The SDK includes an [snpe-tensorflow-to-dlc](https://docs.qualcomm.com/bundle/publicresource/topics/80-63442-2/tools.html#snpe-tensorflow-to-dlc) conversion tool.
                Run it from the directory containing the .pb file. Use the following input arguments
                suited to DeepLab-v3:

- Input Layer name: sub\_7
- Input Shape: 1, 513, 513, 3 (if using the Xception network architecture)
- Output Layer name: ArgMax

That is:

    $ snpe-tensorflow-to-dlc –graph deeplabv3_mnv2_pascal_train_aug/frozen_inference_graph.pb -i sub_7 1,513,513,3 --out_node ArgMax --dlc deeplabv3.dlc --allow_unconsumed_nodesCopy to clipboard

The resulting deeplabv3.dlc file is in the deep learning container format (DLC)
                required by the SDK.

## Running inference on Ubuntu using the SDK

For running inference, the Qualcomm® Neural Processing Engine runtime does not
                support images as a direct input to the model. To run the application in the SDK,
                the following operations are necessary for pre-processing the images, as with OpenCV
                in the example below.

- Resize the image with the shape of 513×513×3.
- Pad the smaller dimensions to the mean value of 128. The padding is used to
                    produce an image of 513×513×3.
- Convert the image to type float32.
- Multiply the image element-wise by 0.00784313771874 and subtract 1.0
                    respectively. (Note: This step converges the pixel values bound to the range
                    [-1,1]. The subtraction is optional, so not included in the code below.)
- Make a NumPy array of required shape
- Store the resulting pre-processed NumPy array as a raw file.

## **1. Pre-processing**

The following script represents those pre-processing steps for the input image:

    import numpy as np
    import cv2
    frame = cv2.imread('image.jpg')
    # Resize frame with Required image size
    frame_resized = cv2.resize(frame,(513,513))
    # Pad smaller dimensions to Mean value & Multiply with 0.007843
    blob = cv2.dnn.blobFromImage(frame_resized, 0.007843, (513, 513), (127.5, 127.5, 127.5), swapRB=True)
    # Making numpy array of required shape
    blob = np.reshape(blob, (1,513,513,3))
    # Storing to a raw file
    np.ndarray.tofile(blob, open('blob.raw','w') )Copy to clipboard

Output of the script is the blob.raw file.

## **2. Changing the background using DeepLab**

Image pre-processing generates the file /output/Result\_0/ArgMax:0.raw.

Here is how to change the background for a pre-processed image

1. The output of the DeepLab-v3 model is a 513×513×1 NumPy array.
2. Read the output file as float32.
3. Each element in the array contains the predicted class number of the
                    corresponding pixels for the given input image.
4. Replace the background in the image, by changing the pixel RGB values based on
                    the predicted class numbers in the array.
5. Resize the image to its original size.

The following script will change the background of a pre-processed image to
                grayscale:

    import cv2
    import numpy as np
    arr = np.fromfile(open('ArgMax:0.raw', 'r'), dtype="float32")
    arr = np.reshape(arr, (513,513,1))
    segment = arr[342:, 342:]
    arr[arr == 15] = 255
    original_img = cv2.imread('image.jpg')
    arr2=cv2.resize(segment,(original_img.shape[1], original_img.shape[0]))
    print(arr.shape)
    for i in range(arr2.shape[0]):
    for j in range(arr2.shape[1]):
    if (arr2[i][j] != 255):
    original_img[i][j] = original_img[i][j][0] = original_img[i][j][1] = original_img[i][j][2]
    cv2.imshow('output1', original_img)
    cv2.imwrite('changed_bg_img.jpg', original_img)
    cv2.imshow('output', arr)
    cv2.imwrite('actual_out.jpg', arr)
    cv2.imwrite('single_segment.jpg', segment)
    cv2.waitKey(0)Copy to clipboard

Below are sample before- and after-images showing the changed background:  
![](data:image/png;base64,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)

**Parent Topic:** [Image Segmentation using DeepLab-v3 and Qualcomm Neural Processing SDK for AI](https://docs.qualcomm.com/doc/80-63442-4/topic/image-segmentation-deeplabv3.html)

Last Published: Jun 24, 2024

[Previous Topic
Classification, Object Detection and Image Segmentation](https://docs.qualcomm.com/bundle/publicresource/80-63442-4/topics/classification-object-detection-and-image-segmentation.md) [Next Topic
DeepLab-v3 using Qualcomm Neural Processing SDK for AI on Android](https://docs.qualcomm.com/bundle/publicresource/80-63442-4/topics/deeplab-v3-on-android.md)