Problem statement:

Using a machine learning toolkit of your choice, create a tool which identifies objects in the image, then returns positions in pixels corresponding to bounding boxes of a user-selected class of object in the image. For example, given an image with both cats and dogs, return bounding boxes for only cats.

Solution:

Approach

Tiny Yolo architecture was used which is as shown below:

Weights: yolo-tiny.h5

Results:

Input Image:

Output Image:

Running the code:

The ipynb file of the code provided was implemented in google colab environment. If you already have the required libraries, run from cell 2. Since it was colab, cv2_imshow was used.
For running on local system, use the py file and make sure that the python file, weights, and input image are in the same working directory.