work with network after training

rdevon / DIM

Deep InfoMax (DIM), or "Learning Deep Representations by Mutual Information Estimation and Maximization"

BSD 3-Clause "New" or "Revised" License

806 stars 102 forks source link

work with network after training #16

Closed masoudpz closed 5 years ago

masoudpz commented 5 years ago

Hi again. How can I send an Image into network and get out-put vector (Mutual Information) and loss value for my Input? I want to use my trained network, Is it possible?

rdevon commented 5 years ago

In principle you can just access your network through the .t7 checkpoint file, in which you can find all relevant parameters. You can just load the parameters onto the network the normal way in pytorch.

rdevon commented 5 years ago

Closing this.