Object Detection using PyTorch for images using Faster RCNN | PyTorch object detection in colab

In this video, we are going to implement Object Detection in PyTorch for images. For PyTorch Object Detection, we will be using the Faster RCNN algorithm and the code will be available on Github.

PyTorch framework has excelled in tasks like object detection in Computer Vision and carrying on its legacy, we have one of the most famous Object Detection algorithms Faster RCNN. The video basically focuses on detecting objects in an image and this can easily be scaled to multiple images and even videos. We use the pretrained version of Faster RCNN meaning that there is no fine tuning involved. We also use OpenCV for making bounding boxes for the detections. The whole project is implemented in Google Colab without any GPU.

Image:

coco_names = ["person" , "bicycle" , "car" , "motorcycle" , "airplane" , "bus" , "train" , "truck" , "boat" , "traffic light" , "fire hydrant" , "street sign" , "stop sign" , "parking meter" , "bench" , "bird" , "cat" , "dog" , "horse" , "sheep" , "cow" , "elephant" , "bear" , "zebra" , "giraffe" , "hat" , "backpack" , "umbrella" , "shoe" , "eye glasses" , "handbag" , "tie" , "suitcase" ,
"frisbee" , "skis" , "snowboard" , "sports ball" , "kite" , "baseball bat" ,
"baseball glove" , "skateboard" , "surfboard" , "tennis racket" , "bottle" ,
"plate" , "wine glass" , "cup" , "fork" , "knife" , "spoon" , "bowl" ,
"banana" , "apple" , "sandwich" , "orange" , "broccoli" , "carrot" , "hot dog" ,
"pizza" , "donut" , "cake" , "chair" , "couch" , "potted plant" , "bed" ,
"mirror" , "dining table" , "window" , "desk" , "toilet" , "door" , "tv" ,
"laptop" , "mouse" , "remote" , "keyboard" , "cell phone" , "microwave" ,
"oven" , "toaster" , "sink" , "refrigerator" , "blender" , "book" ,
"clock" , "vase" , "scissors" , "teddy bear" , "hair drier" , "toothbrush" , "hair brush"]

[abhishekkumarpandey]

It really very useful. Please tell me how to implement this on our custom dataset.

[mahenoormerchant]

Amazing ..Helped me alot for my assignment. thanks

[lscharan]

Where can I find the code? Btw your explanation is too good.

[lintheshwarsakthivel]

How to use this without the help of pre trained models?

[SYtechseries]

Is this trained on these classes only?

[shinkevin]

TYSM for your video!!! It worked perfectly

[shinkevin]

Can you also make a video on exporting this model into onnx format and run it on the onnx runtime please? My company asked me to implement it ASAP lol

[owaisbutt]

but sir when i train the model with own dataset then how can we do expect things?

[Dimoven]

AttributeError: module 'torch' has no attribute 'argwhere'