- Sort Score
- Result 10 results
- Languages All
Results 21 - 30 of 226 for weights (0.39 sec)
-
tensorflow/compiler/mlir/lite/tests/debuginfo/v1_1.0_224_frozen.wrong_attr.stack.part.pbtxt.debug
value { file_line_cols { file_index: 49 line: 492 } } } traces { key: "MobilenetV1/Conv2d_0/weights@" value { file_line_cols { file_index: 54 line: 649 } } } traces { key: "MobilenetV1/Conv2d_0/weights/read@" value { file_line_cols { file_index: 49 line: 421 } } } traces {
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed Dec 11 15:36:55 UTC 2019 - 3.9K bytes - Viewed (0) -
src/runtime/metrics/histogram.go
// Copyright 2020 The Go Authors. All rights reserved. // Use of this source code is governed by a BSD-style // license that can be found in the LICENSE file. package metrics // Float64Histogram represents a distribution of float64 values. type Float64Histogram struct { // Counts contains the weights for each histogram bucket. // // Given N buckets, Count[n] is the weight of the range // [bucket[n], bucket[n+1]), for 0 <= n < N. Counts []uint64
Registered: Wed Jun 12 16:32:35 UTC 2024 - Last Modified: Fri Jan 08 03:43:44 UTC 2021 - 1.3K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/tests/debuginfo/v1_1.0_224_frozen.wrong_attr.line.part.pbtxt.debug
value { file_line_cols { file_index: 49 line: 492 } } } traces { key: "MobilenetV1/Conv2d_0/weights@" value { file_line_cols { file_index: 54 line: 649 } } } traces { key: "MobilenetV1/Conv2d_0/weights/read@" value { file_line_cols { file_index: 49 line: 421 } } } traces {
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed Dec 11 15:36:55 UTC 2019 - 3.7K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/common/uniform_quantized_types.h
// storage type. The available values use the full range of the storage value, // i.e. [-128, 127]. Assumes asymmetric quantization, meaning the zero point // value can be a non-zero value. // If `narrow_range` is set true (ex: for weights), a restricted range of // integers will be used for symmetric mapping, i.e. [-127, 127]. UniformQuantizedType CreateI8F32UniformQuantizedType(Location loc, MLIRContext& context,
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Apr 25 16:01:03 UTC 2024 - 5.7K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/tensorflow/tests/lift_quantizable_spots_as_functions_drq_min_elements.mlir
// RUN: tf-quant-opt %s -split-input-file -quant-lift-quantizable-spots-as-functions-drq="min-num-elements-for-weights=2500000" | FileCheck %s // CHECK-LABEL: lift_float_matmul func.func @lift_float_matmul(%arg0: tensor<1x12x12x512xf32>) -> (tensor<*xf32>, tensor<*xf32>) { %cst = "tf.Const"() {value = dense<0.000000e+00> : tensor<512x512xf32>} : () -> tensor<512x512xf32> %out_1 = "tf.MatMul"(%arg0, %cst) { device = "", transpose_a = false, transpose_b = false
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Mon Oct 30 06:52:55 UTC 2023 - 2.1K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/transforms/quantize_patterns.td
// point constant. def : Pat<(TFL_DequantizeOp (TFL_QuantizeOp (Arith_ConstantOp F32ElementsAttr:$cst), $qt)), (TFL_ConstOp $cst)>; // Transpose conv supports hybrid computation with quantized weights. def FoldQuantWeightsIntoTposeConv : Pat< (TFL_TransposeConvOp $output_shape, (TFL_DequantizeOp $quant_weights), $quant_input, $bias, $padding, $stride_h, $stride_w, $faf),
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue May 28 23:10:13 UTC 2024 - 2.3K bytes - Viewed (0) -
pilot/pkg/xds/endpoints/ep_filters.go
return scaleFactor } weight := uint32(math.MaxUint32) if ep.GetLoadBalancingWeight().Value < math.MaxUint32/scaleFactor { weight = ep.GetLoadBalancingWeight().Value * scaleFactor } return weight } // Apply the weight for this endpoint to the network gateways.
Registered: Fri Jun 14 15:00:06 UTC 2024 - Last Modified: Wed May 29 01:17:58 UTC 2024 - 9.1K bytes - Viewed (0) -
src/cmd/internal/pgo/pprof.go
} return postProcessNamedEdgeMap(weight, totalWeight) } func sortByWeight(edges []NamedCallEdge, weight map[NamedCallEdge]int64) { sort.Slice(edges, func(i, j int) bool { ei, ej := edges[i], edges[j] if wi, wj := weight[ei], weight[ej]; wi != wj { return wi > wj // want larger weight first } // same weight, order by name/line number if ei.CallerName != ej.CallerName {
Registered: Wed Jun 12 16:32:35 UTC 2024 - Last Modified: Wed Mar 27 20:20:01 UTC 2024 - 4K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/tensorflow/quantization_options.proto
// determined. The activation and weight are quantized to INT8 while bias is // quantized to INT32. METHOD_STATIC_RANGE_INT8 = 2; // Dynamic range quantization. Quantized tensor values' ranges are // determined in the graph executions. The weights are quantized during // conversion. METHOD_DYNAMIC_RANGE_INT8 = 3; // Weight-only quantization. Only weights are quantized during conversion.
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue Mar 19 06:31:19 UTC 2024 - 9.2K bytes - Viewed (0) -
tensorflow/compiler/mlir/tfrt/ir/mlrt/tf_mlrt_tpu_ops.td
$constant_operand_indices are the indices of the inputs that are constant to the TPU program (e.g. weights in inference), the rest of the inputs are input tensors. constant_operand_indices is sorted in ascending order. $operands_with_static_shape are indices of operands that are tagged with a maximum static shape.
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed Oct 04 21:25:31 UTC 2023 - 3.1K bytes - Viewed (0)