search

wizyoung / YOLOv3_TensorFlow

Complete YOLO v3 TensorFlow implementation. Support training on your own dataset.
MIT License
1.55k stars 579 forks source link

Features extraction #121

Open tommyz94 opened 5 years ago

tommyz94 commented 5 years ago

Hi wizyoung, There's a way to extract features from the last convolutional layer for each bounding box?

Thanks

Cli98 commented 5 years ago

@tommyz94 what's the meaning of extract feature? Get weights of layer?

tommyz94 commented 5 years ago

I mean the features extracted by the last convolutional layer. For example in VGG16 after all convolutional phase I can obtain a vector of dimension 4096 that describes the image at an high-level.

Cli98 commented 5 years ago

@tommyz94 Yes it is possible, you can hook out weights of layer and save it, from you checkpoint

bujianyiwang commented 4 years ago

I want to use yolov3 to predict the number of real-time person from the rtsp stream with suited interval,anyone has the right python file?

SouradipBh commented 4 years ago

I mean the features extracted by the last convolutional layer. For example in VGG16 after all convolutional phase I can obtain a vector of dimension 4096 that describes the image at an high-level.

Do u have it?