- Sort Score
- Result 10 results
- Languages All
Results 21 - 23 of 23 for quantize_i8 (0.11 sec)
-
tensorflow/compiler/mlir/quantization/tensorflow/passes/quantized_function_library_tf_drq.mlir
} : (tensor<*xi32>, tensor<*xf32>, tensor<*xf32>) -> tensor<*xf32> func.return %out : tensor<*xf32> } // For weight-only func.func @dequantize_i8(%input : tensor<*xi8>, %scale : tensor<*xf32>, %zp : tensor<*xi32>) -> tensor<*xf32> { // Use identity op to avoid the weight being constant-folded. %identity = "tf.Identity"(%input) : (tensor<*xi8>) -> tensor<*xi8>
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Fri Mar 03 15:43:38 UTC 2023 - 12.2K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/common/quantization_lib/quantization_utils.h
// For not quantizable ops, search for dequantize attached to the // quantized op of the output. if (Operation* quantize_op = dyn_cast_or_null<QuantizeOpT>( *quantized_op->getResult(i).getUsers().begin())) { result = quantize_op->getResult(0); } else { quantized_op->emitError() << "Output[" << i
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed Apr 24 20:30:06 UTC 2024 - 41.7K bytes - Viewed (0) -
RELEASE.md
support generators and Sequences. * `tf.lite` * Legalization for `NMS` ops in TFLite. * add `narrow_range` and `axis` to `quantize_v2` and `dequantize` ops. * Added support for `FusedBatchNormV3` in converter. * Add an `errno`-like field to `NNAPI` delegate for detecting `NNAPI` errors for fallback behaviour.
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue Jun 11 23:24:08 UTC 2024 - 730.3K bytes - Viewed (0)