chop.passes.transform.utils
conv_bn_fusion_transform_pass
logicnets_fusion_transform_pass
onnx_annotate_transform_pass
- chop.passes.graph.transforms.utils.onnx_annotate_transform_pass(graph, pass_args)[source]
Convert MaseGraph to ONNX and annotate the relevant layers with sparsity information. The code here is derived from Zhewen’s SparseCNN codebase: https://github.com/Yu-Zhewen/sparseCNN/blob/main/onnx_sparsity_attribute.py