TensorFlow.js 是一个开源硬件加速 JavaScript 库,用于训练和部署机器学习模型。 TensorFlow.js 0.11.1 已发布,包含大量更新: Core (0.8.3 ==> 0.11.0)FeaturesAdd tf.unstack (#1018). Add tf.losses.logLoss (#1021). Add tf.losses.hingeLoss (#1008). Gradient for tf.gather (#981). Add resizeBilinear gradient implementation. (#996). Add tf.losses.cosineDistance (#1005). Add tf.losses.meanSquaredError (#991). Add tf.disposeVariables which disposes all registered variables. (#988). Add tensor.round() (chaining was missing for round) (#994). Add support for loading quantized weights (#965). Add tf.linalg.gramSchmidt and tf.eye (#1024). Add tf.io.browserHTTPRequest (#1030). Add tf.io.browserDownloads() and tf.io.browserFiles() (#1012). Add IOHandler subtype BrowserLocalStorage. (#1003). Add tf.cumsum (#1032). Add tf.io.browserIndexedDB (#1017). Add support for StridedSlice (#1026). Add model store managers (#1038).
Breaking changesBug fixesFix bug: transpose(scalar|1d) should return a clone. (#1033). Remove explicit dispose in tf.grad to fix second-order gradient (#1013). Clean up tensor leak in tf.toPixels() (#1031). Fix the import/export of gpgpu_util. (#1009). Fix a bug with backendCPU.conv2dDerInput (#1014). Fix tensor2d/3d/4d to require shape to have the correct length (#1004). Checks if window location is not undefined (#1002). Default
behavior changed with newest NVidia Drivers in Mac OS >=10.13.4 so
we have to check for NaN explicitly. [Fix nan propagation in tf.relu]
([#1001] Improve the WebGL random number generator (#993). Fix build issue where module-import code gets dropped from the bundle (#987). (tensorflow/tfjs-core#1001)). Align tf.resizeNearestNeighbor with TF. (#1000). Return 0 for tf.sign(NaN) to align with TF (#998).
PerformanceDevelopmentadds template to pull request message [adds pull request template] (#1036). Travis: run tests on Node.js 10 as well (#1039). Travis: use yarn cache (#1040). Travis: clone only last 5 commits (#1041).
DocumentationFix typo in tf.tile documentation. (#1043). Remove erroneous endpoint parameter from linspace JSDoc (#1020). Removed duplicate typo in tf.buffer docs (#1023). Fixe bug in oneHot doc example (#1015). Fix code snippet in docs where indices should be int32 (#989). Fix typo in comments of io module. (#1006). Update a comment in environment.ts reference deeplearn.js. (#1007). Add logic operation code snippets in jsdocs (#900). Update docstring for tf.setBackend() re disposing the old backend. (#1029).
MiscExport GPGPUContext and add getCanvas() to the WebGLBackend. (#982). Add IS_BROWSER to ENV; add scheme-based URL router to tf.io.* modules (#1034). Add tf.pad test for 4d tensor and test memory (#1025). Exports operation decorator for use in tfjs-layers (#1027). Add serialization infrastructure to core (#997). Add tests for tf.conv1d gradients (#992). Add basic types and helper methods for model exporting (#990).
Layers (0.5.2 ==> 0.6.1)FeaturesAdd version string (e.g., 'tfjs-layers 0.10.3') to the keras_version field of JSONs from model serialization.(#157). added tf.layers.cropping2D (#155).
Breaking changes"tfl" => "tf" for es5 bundle users. (#191). Remove the exporting of the backend symbols (#193). Model.fit(): Change default epochs to 1 (#156).
Bug fixesFix axis in Softmax activation layer (#177). Fix slowness in Orthgonal initializer for some RNN layers. (#172). The padding mode is called 'causal' not 'casual' (#152).
Developmentchore: use yarn cache (#187). chore: add Node.js 10 (#189). adds default pull request template to help remind contributors to use PR commit message tags. (#180). Add integration_test/tfjs2keras. (#173).
DocumentationAdd code snippet for tf.layers.reshape . (#198). Clarify that the default value of useBias is true for (#162). Clarify that filters is a required field for non-depthwise (#162). Fixes #165: Document model.fit callbacks (#149).
Misc下载地址: |