Biscuits of Deep Learning

Manipulate Gradient The section includes some technologies related to gradient descent optimization method. Gradient Clipping A good explanation: What is Gradient Clipping? Related paper: Why Gradient Clipping Accelerates Training: A…

Continue Reading Biscuits of Deep Learning

Neural Style Transfer via Meta Networks

Outline Introduction Style transfer Content-perceptual loss Style-perceptual loss Example Proposed Method (simple but inspirational) Arbitrary style transfer Meta networks for arbitrary style transfer Experiments Conclusion Slides

Continue Reading Neural Style Transfer via Meta Networks

Experiment Control

Prepare the environment of the experiment control Tutorial from https://shenxiaohai.me/2019/01/17/sacred-tool/ Installation To install Sacred at client (t.g. conda environment) pip install sacred pip install numpy pymongo Server: database # 1.…

Continue Reading Experiment Control