- Sort Score
- Result 10 results
- Languages All
Results 1 - 1 of 1 for QuantizeValue (0.1 sec)
-
tensorflow/compiler/mlir/lite/transforms/default_quant_params.cc
} return false; } // Uses `quant_params` to quantize `value` and inserting a pair of // tfl.quantize and tfl.dequantize ops for this `value`. void QuantizeValue(OpBuilder builder, Value value, quant::QuantParams quant_params); // If the value hasn't been quantized, the functions adds it to `values`.
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Apr 25 16:01:03 UTC 2024 - 9.4K bytes - Viewed (0)