- Sort Score
- Result 10 results
- Languages All
Results 1 - 3 of 3 for quantizable_input_indices (0.53 sec)
-
tensorflow/compiler/mlir/lite/quantization/lite/quantize_weights.h
// Stores information about how to quantize a user-specified custom operation. // CustomOpInfo contains info of its corresponding CustomOp registered in the // CustomOpMap. 'quantizable_input_indices' is used to determine which indices // of the CustomOp are quantizable. 'is_weight_only' is used specify whether the // custom op is quantized only for storage and dequantized at runtime.
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed Jun 12 23:15:24 UTC 2024 - 4.2K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/quantization/lite/quantize_weights.cc
quant_specs.legacy_float_scale = legacy_float_scale; quant_specs.ops_blocklist = denylisted_mlir_op_names; for (const auto& entry : custom_op_map) { quant_specs.custom_map[entry.first].quantizable_input_indices = entry.second.quantizable_input_indices; quant_specs.custom_map[entry.first].is_weight_only = entry.second.is_weight_only; quant_specs.custom_map[entry.first].no_side_effect = entry.second.no_side_effect;
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed Jun 12 23:15:24 UTC 2024 - 9.5K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/common/quantization_lib/quantization_config.cc
const std::vector<std::string> indices = absl::StrSplit(node_specification, '-'); for (const std::string& cur_index : indices) { custom_op_map[node_name].quantizable_input_indices.push_back( std::stoi(cur_index)); } break; } case CustomOpUpdateOptions::kWeightOnly: custom_op_map[node_name].is_weight_only =
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue Mar 05 07:39:40 UTC 2024 - 5.9K bytes - Viewed (0)