Instead of the final classification layer (which would say "dog" or "running"), you extract the output from the (often called the "bottleneck" or "pooling layer").
Depending on what you want the "feature" to represent, choose a model: Download: video5179512026745012956.mp4 (5.75 MB)
If you have the file locally, you can use PyTorch and OpenCV to get the feature: Instead of the final classification layer (which would