- Sort Score
- Result 10 results
- Languages All
Results 1 - 1 of 1 for freeze_all_variables (0.13 sec)
-
tensorflow/compiler/mlir/quantization/tensorflow/quantization_options.proto
// Setting this to `false` is an experimental feature and quantization may // fail. To quantize models larger than 2 GiB, this should be set to `false`. // If not set, it defaults to `true`. optional bool freeze_all_variables = 9; // Enables channel-wise quantization. By default, channel-wise quantization is // not applied regardless of the op support. Currently, it is supported for
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue Mar 19 06:31:19 UTC 2024 - 9.2K bytes - Viewed (0)