search

plemeri / RandWire_tensorflow

tensorflow implementation of Exploring Randomly Wired Neural Networks for Image Recognition
MIT License
31 stars 9 forks source link

dataset_generator.py #1

Open henbucuoshanghai opened 5 years ago

henbucuoshanghai commented 5 years ago

是做什么的？

henbucuoshanghai commented 5 years ago

graph_generator.py是做什么的？

plemeri commented 5 years ago

Hi, graph_generator.py generates random graph. You can choose from watts strogatz, erdos renyi, or barabasi albert model. While running train.py, it generates random graphs when there are no graph data, or loads graph data if graph data exists. Once you trained your network and want to retrain the network from checkpoint, just rerun and it will load previous graph data.

henbucuoshanghai commented 5 years ago

watts strogatz, erdos renyi, or barabasi albert model？？what are they？

plemeri commented 5 years ago

Those are algorithms for ramdom graph generation. You can refer to the paper "Exploring Randomly Wired Neural Networks for Image Recognition"

plemeri commented 5 years ago

I'm sorry but I'm little bit confused. Is your question about "dataset_generator.py"? or "graph_generator.py" .