- Sort Score
- Result 10 results
- Languages All
Results 1 - 6 of 6 for fake_quant_with_min_max_args (0.63 sec)
-
tensorflow/compiler/mlir/quantization/tensorflow/python/integration_test/quantize_model_test_base.py
) # Insert fake quant to simulate a QAT model. weight = array_ops.fake_quant_with_min_max_args( weight, min=-0.1, max=0.2, num_bits=8, narrow_range=False ) # shape: (2, 2) output_tensor = math_ops.matmul(matmul_input, weight) # Insert fake quant to simulate a QAT model. output_tensor = array_ops.fake_quant_with_min_max_args( output_tensor, min=-0.2, max=0.2, num_bits=8, narrow_range=False
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Mar 21 08:51:46 UTC 2024 - 51.2K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/common/ir/QuantOps.td
}]; let description = [{ Given a const min, max, num_bits and narrow_range attribute, applies the same uniform quantization simulation as is done by the TensorFlow fake_quant_with_min_max_args op. See the fakeQuantAttrsToType() utility method and the quant-convert-simulated-quantization pass for further details. }]; let arguments = (ins F32Tensor:$inputs, F32Attr:$min,
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue Jan 09 03:10:59 UTC 2024 - 10.2K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/tensorflow/python/integration_test/quantize_model_test.py
def _matmul(self, x, y): x = array_ops.fake_quant_with_min_max_vars( x, min=ops.convert_to_tensor(self._min[0]), max=ops.convert_to_tensor(self._max[0]), num_bits=8, narrow_range=False, ) y = array_ops.fake_quant_with_min_max_vars( y, min=ops.convert_to_tensor(self._min[1]),
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Fri May 17 03:36:50 UTC 2024 - 235.6K bytes - Viewed (0) -
tensorflow/compiler/mlir/tensorflow/tests/lower_tf.mlir
// CHECK: return [[VAL8]] : tensor<1x8x2xf32> func.return %2 : tensor<1x8x2xf32> } func.func @fake_quant_with_min_max_args(%arg0 : tensor<?x?xf32>) -> tensor<?x?xf32> { // CHECK-DAG: [[VAL0:%.+]] = "tf.Const"() <{value = dense<1.275000e+02> : tensor<f32>}> // CHECK-DAG: [[VAL1:%.+]] = "tf.Const"() <{value = dense<1.00392163> : tensor<f32>}>
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Fri Jan 05 18:35:42 UTC 2024 - 92K bytes - Viewed (0) -
RELEASE.md
`tf.math.zeta`. * New endpoints in `tf.quantization` namespace: `tf.quantization.dequantize`, `tf.quantization.fake_quant_with_min_max_args`, `tf.quantization.fake_quant_with_min_max_args_gradient`, `tf.quantization.fake_quant_with_min_max_vars`, `tf.quantization.fake_quant_with_min_max_vars_gradient`, `tf.quantization.fake_quant_with_min_max_vars_per_channel`,
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue Jun 11 23:24:08 UTC 2024 - 730.3K bytes - Viewed (0) -
tensorflow/compiler/mlir/tensorflow/ir/tf_generated_ops.td
`min_adj = scale * round(min / scale)` and `max_adj = max + min_adj - min`. Examples ```python inp = tf.constant ([10.03, -10.23, 3]) out = tf.quantization.fake_quant_with_min_max_args(inp, min=-5, max=5, num_bits=16) print(out) # Output: # tf.Tensor([ 4.9999237 -5.0000763 3.0000763], shape=(3,), dtype=float32) ```
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue Jun 11 23:24:08 UTC 2024 - 793K bytes - Viewed (0)