- Sort Score
- Result 10 results
- Languages All
Results 1 - 4 of 4 for uniform_quantize (0.26 sec)
-
tensorflow/compiler/mlir/lite/stablehlo/tests/uniform-quantized-stablehlo-to-tfl.mlir
%0 = stablehlo.uniform_quantize %arg : (tensor<2x2x!quant.uniform<i8:f32, 2.000000e+0:16>>) -> tensor<2x2x!quant.uniform<i8:f32, 3.000000e+0:127>> return %0 : tensor<2x2x!quant.uniform<i8:f32, 3.000000e+0:127>> } // CHECK-LABEL: uniform_quantize_op_quantized_input // CHECK: stablehlo.uniform_quantize // CHECK-NOT: tfl.quantize // -----
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue May 14 17:10:32 UTC 2024 - 106.2K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/stablehlo/transforms/uniform_quantized_stablehlo_to_tfl_pass.cc
} // Returns kernel input feature dimension of TFLite convolutions. int64_t GetConvolutionKernelInputFeatureDimension(bool is_depthwise) { return is_depthwise ? 0 : 3; } // stablehlo.uniform_quantize -> tfl.quantize // TODO: b/322428814 - Add StableHLO quantizer integration tests for ODML. class RewriteUniformQuantizeOp : public OpRewritePattern<stablehlo::UniformQuantizeOp> {
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Mon Apr 22 09:00:19 UTC 2024 - 99.8K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/tensorflow/python/integration_test/quantize_model_test.py
'target_opset': quant_opts_pb2.UNIFORM_QUANTIZED, 'input_shape_dynamic': False, 'enable_per_channel_quantization': False, }, { 'testcase_name': 'dilation_with_bias_and_bn_and_relu6_to_uq', 'activation_fn': nn_ops.relu6, 'has_bias': True, 'has_batch_norm': True, 'target_opset': quant_opts_pb2.UNIFORM_QUANTIZED,
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/tf-ops.mlir
// ----- func.func @testUniformQuantize(%arg0: tensor<*xf32>, %scales: tensor<2xf32>, %zps: tensor<i32>) -> tensor<*x!tf_type.qint8> { // expected-error @below {{'tf.UniformQuantize' op quantization_axis is -1, scales must have 0 rank.}} %0 = "tf.UniformQuantize"(%arg0, %scales, %zps) { quantization_axis = -1 : i64, quantization_min_val = -128 : i64, quantization_max_val = 127 : i64
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Mon Oct 23 14:40:35 UTC 2023 - 236.4K bytes - Viewed (0)