[FR]Ask an example to create the object detection video on my own model?

[twmht]

Instructions

Thank you for submitting an issue. Please refer to our
issue policy
for information on what types of issues we address.

Please fill in this template to ensure a timely and thorough response.

• Place an "x" between the brackets next to an option if it applies. Example:
  • Selected option
• Please delete this section (all content above this line) before submitting
  the issue

Proposal Summary

(In a few sentences, provide a clear, high-level description of the feature
request)

Motivation

I found out it was not easy to read frames from the video when using fiftyone.

I followed the tutorial (https://github.com/voxel51/fiftyone-examples/blob/master/examples/pytorchvideo_tutorial.ipynb), which reads a few video shots and using classification model to classifiy the activities.

But what i want is to use object detection to every frame of the given video, althought the tutorial mentioned the object detection, but is too simple to figure it out.

subset.apply_model(model, "detections")

Can you give me a simple example to grad each frame from a video sample, and i can use my own model to predict and add labels to the sample?

like,

sample = fo.Sample(filepath="/path/to/my.mp4")
dataset = fo.Dataset() : type | Unknown
dataset.add_sample(sample)
for frame_number, frame in sample.frames():
    model(frame)
    ....

how can i use fiftyone to do that?

Details

(Use this section to include any additional information about the feature. If
you have a proposal for how to implement this feature, please include it here.)

Willingness to contribute

The FiftyOne Community encourages new feature contributions. Would you or
another member of your organization be willing to contribute an implementation
of this feature?

• [] Yes. I can contribute this feature independently.
• [] Yes. I would be willing to contribute this feature with guidance from
  the FiftyOne community.
• No. I cannot contribute this feature at this time.