- Sort Score
- Result 10 results
- Languages All
Results 1 - 1 of 1 for enable_legacy_weight_only (0.46 sec)
-
tensorflow/compiler/mlir/quantization/tensorflow/quantization_options.proto
// Produces legacy weight-only graph where the qconst op(containing quantized // values) is followed by a dequantization op. This flag will be deprecated. bool enable_legacy_weight_only = 13; // If set to true, it forces calibration in graph model instead of eager mode // when the context is in eager mode. This will be forcibly set to true when // using DebuggerOptions.
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue Mar 19 06:31:19 UTC 2024 - 9.2K bytes - Viewed (0)