- Sort Score
- Result 10 results
- Languages All
Results 71 - 80 of 568 for weights (0.11 sec)
-
tensorflow/compiler/mlir/quantization/tensorflow/passes/passes.h
// resource ops are considered duplicated if they have the same `shared_name`. std::unique_ptr<OperationPass<func::FuncOp>> CreateMergeDuplicateResourceOpsPass(); // Apply quantization to weights based on the provided schemes. std::unique_ptr<OperationPass<ModuleOp>> CreateQuantizeWeightsPass( const tensorflow::quantization::QuantizationOptions& quant_options); // Propagate quantized type through allowed ops.
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Fri May 10 04:07:09 UTC 2024 - 12.3K bytes - Viewed (0) -
docs/zh/docs/tutorial/body-nested-models.md
``` !!! tip 请记住 JSON 仅支持将 `str` 作为键。 但是 Pydantic 具有自动转换数据的功能。 这意味着,即使你的 API 客户端只能将字符串作为键发送,只要这些字符串内容仅包含整数,Pydantic 就会对其进行转换并校验。 然后你接收的名为 `weights` 的 `dict` 实际上将具有 `int` 类型的键和 `float` 类型的值。 ## 总结 使用 **FastAPI** 你可以拥有 Pydantic 模型提供的极高灵活性,同时保持代码的简单、简短和优雅。 而且还具有下列好处: * 编辑器支持(处处皆可自动补全!) * 数据转换(也被称为解析/序列化) * 数据校验 * 模式文档
Registered: Mon Jun 17 08:32:26 UTC 2024 - Last Modified: Fri Mar 22 01:42:11 UTC 2024 - 9.3K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/stablehlo/quantization_config.proto
// value {dimension_specs {dimension: 3}}} // }} // } // ``` // // This preset: // * Applies per-channel quantization for weights (input index 1) of // convolution quantizable unit family. The quantization dimension is 3, the // channel dimension, which assumes the weight tensor is in NHWC format. // * Applies static-range PTQ for all other ops. // // Next ID: 4 message StaticRangePtqPreset {
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Fri May 17 03:36:50 UTC 2024 - 14.3K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/python/tf_tfl_flatbuffer_helpers.cc
constexpr mlir::StringRef kUnidirectionalSequenceRnnOp = "name: 'UnidirectionalSequenceRnn' input_arg: {name: 'Input' type: " "DT_FLOAT} input_arg: { name: 'Weights' type: DT_FLOAT } " "input_arg: { name: 'RecurrentWeights' type: DT_FLOAT } input_arg: { " "name: 'Bias' type: DT_FLOAT} " "input_arg: { name: 'HiddenState' type: DT_FLOAT} " "output_arg: { name: "
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Sun May 12 12:39:37 UTC 2024 - 17.3K bytes - Viewed (0) -
pkg/config/validation/validation.go
} return } func validateRouteDestinations(weights []*networking.RouteDestination, gatewaySemantics bool) (errs error) { var totalWeight int32 for _, weight := range weights { if weight == nil { errs = multierror.Append(errs, errors.New("weight may not be nil")) continue } if weight.Destination == nil {
Registered: Fri Jun 14 15:00:06 UTC 2024 - Last Modified: Wed Jun 12 04:03:33 UTC 2024 - 107.2K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/tensorflow/passes/prepare_quantize.cc
// prepare_quantize_ptq_per_channel.mlir. Option<bool> enable_per_channel_quantization_{ *this, "enable-per-channel-quantization", llvm::cl::init(false), llvm::cl::desc("Whether enable per-channel quantized weights.")}; }; bool PrepareQuantizePass::SetInputNodesQuantizationParams(func::FuncOp func) { StringRef func_name = func.getName(); auto has_quantize_op = [&](const Value arg) { return (arg.hasOneUse() &&
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Apr 25 16:01:03 UTC 2024 - 17.2K bytes - Viewed (0) -
pkg/scheduler/framework/runtime/framework_test.go
return buildScoreConfigWithWeights(defaultWeights, ps...) } func buildScoreConfigWithWeights(weights map[string]int32, ps ...string) *config.Plugins { var plugins []config.Plugin for _, p := range ps { plugins = append(plugins, config.Plugin{Name: p, Weight: weights[p]}) } return &config.Plugins{Score: config.PluginSet{Enabled: plugins}} } type injectedResult struct {
Registered: Sat Jun 15 01:39:40 UTC 2024 - Last Modified: Fri May 17 09:07:27 UTC 2024 - 103K bytes - Viewed (0) -
src/cmd/vendor/github.com/google/pprof/internal/graph/graph.go
ret += edge.Weight } return ret } type edgeList []*Edge func (el edgeList) Len() int { return len(el) } func (el edgeList) Less(i, j int) bool { if el[i].Weight != el[j].Weight { return abs64(el[i].Weight) > abs64(el[j].Weight) } from1 := el[i].Src.Info.PrintableName() from2 := el[j].Src.Info.PrintableName() if from1 != from2 {
Registered: Wed Jun 12 16:32:35 UTC 2024 - Last Modified: Fri May 31 19:48:28 UTC 2024 - 31K bytes - Viewed (0) -
pilot/pkg/xds/endpoints/ep_filters_test.go
{Address: "20.0.0.1", Weight: 6}, {Address: "20.0.0.2", Weight: 6}, {Address: "20.0.0.3", Weight: 6}, // 2 endpoint on network1 with weight aggregated at the gateway {Address: "1.1.1.1", Weight: 12}, // 1 endpoint on network4 with no gateway (i.e. directly accessible) {Address: "40.0.0.1", Weight: 6}, }, Weight: 36, }, }, wantWorkloadMetadata: []string{
Registered: Fri Jun 14 15:00:06 UTC 2024 - Last Modified: Wed May 29 01:17:58 UTC 2024 - 26.8K bytes - Viewed (0) -
docs/ja/docs/tutorial/body-nested-models.md
``` !!! tip "豆知識" JSONはキーとして`str`しかサポートしていないことに注意してください。 しかしPydanticには自動データ変換機能があります。 これは、APIクライアントがキーとして文字列しか送信できなくても、それらの文字列に純粋な整数が含まれている限り、Pydanticが変換して検証することを意味します。 そして、`weights`として受け取る`dict`は、実際には`int`のキーと`float`の値を持つことになります。 ## まとめ **FastAPI** を使用すると、Pydanticモデルが提供する最大限の柔軟性を持ちながら、コードをシンプルに短く、エレガントに保つことができます。 以下のような利点があります: * エディタのサポート(どこでも補完!) * データ変換(別名:構文解析・シリアライズ)
Registered: Mon Jun 17 08:32:26 UTC 2024 - Last Modified: Fri Mar 22 01:42:11 UTC 2024 - 8.7K bytes - Viewed (0)