neural_compressor.adaptor.tf_utils.graph_rewriter.int8
Tensorflow INT8 Graph Rewriters.
Submodules
neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_fake_quant
neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_value
neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_value_without_calib
neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_conv_redundant_dequantize
neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_conv_requantize
neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_matmul_redundant_dequantize
neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_matmul_requantize
neural_compressor.adaptor.tf_utils.graph_rewriter.int8.meta_op_optimizer
neural_compressor.adaptor.tf_utils.graph_rewriter.int8.post_hostconst_converter
neural_compressor.adaptor.tf_utils.graph_rewriter.int8.post_quantized_op_cse
neural_compressor.adaptor.tf_utils.graph_rewriter.int8.rnn_convert
neural_compressor.adaptor.tf_utils.graph_rewriter.int8.scale_propagation