Shypd.aiThe largest open index of AI toolsMorph-Net is an Open Source & Models tool that enables fast and simple resource-constrained learning of deep network structures. It helps optimize neural networks by adjusting output channels in convolution layers.
Trending
About
Morph-Net is an open-source method for learning deep network structure during training, focusing on continuous relaxation of the network-structure learning problem. It induces activation sparsity by adding regularizers that target resource consumption like FLOPs or model size. The tool allows users to shrink existing models to satisfy constraints such as memory or latency by adjusting the number of output channels in each convolution layer. Morph-Net supports various regularizer types, including LogisticSigmoid for probabilistic channel regularization, GroupLasso for models without BatchNorm, and Gamma for models with BatchNorm. It provides functionality to export learned model structures in JSON format and offers examples for adding FLOPs regularizers.
Capabilities
Pricing & Plans
Open Source
Free
FAQs
Trending
