排序 相关度 时间
共 2,993 条 · 0.351 秒
82搜索为您找到约 2,993 条结果
keras.io 网页 综合
GptOssCausalLMPreprocessor layer
…load a pre-trained model. The preset can be passed as one of: For any Preprocessor subclass, you can run cls.presets.keys() to list all built-in presets available on the class. As there are …
2026-11-14 自动蜘蛛 相关度 3.1
keras.io 网页 综合
Transfer learning & fine-tuning
…g training (either when training with fit() or when training with any custom loop that relies on trainable_weights to apply gradient updates). Example: setting trainable to False When a trai…
2026-11-15 自动蜘蛛 相关度 3.0
keras.io 网页 综合
Writing a training loop from scratch in JAX
…bles (e.g. weight tensors) must be passed as function inputs, and any variable that has been updated during the forward pass must be returned as function output. The function have no side ef…
2026-11-14 自动蜘蛛 相关度 3.0
keras.io 网页 综合
The Functional API
…s (that were learned during training) - model training config, if any (as passed to compile()) - optimizer and its state, if any (to restart training where you left off) For details, read th…
2026-11-14 自动蜘蛛 相关度 3.0
keras.io 网页 综合
How to use Keras with NNX backend
…shows: The KerasVariable is successfully traced by NNX, just like any native nnx.Variable. The nnx.variables() function correctly identifies and lists our custom_variable as part of the mode…
2026-11-15 自动蜘蛛 相关度 2.9
keras.io 网页 综合
The Sequential model
…hat the Sequential constructor accepts a name argument, just like any layer or model in Keras. This is useful to annotate TensorBoard graphs with semantically meaningful names. Generally, al…
2026-11-14 自动蜘蛛 相关度 2.8
keras.io 网页 综合
Distributed training with Keras 3
… single device) while automatically managing distribution across many devices. The API leverages the underlying framework (e.g. JAX) to distribute the program and tensors according to the sh…
2026-11-15 自动蜘蛛 相关度 2.7
keras.io 网页 综合
GptOssCausalLM model
…load a pre-trained model. The preset can be passed as one of: For any Task subclass, you can run cls.presets.keys() to list all built-in presets available on the class. This constructor can …
2026-11-15 自动蜘蛛 相关度 2.6
keras.io 网页 综合
Writing a training loop from scratch in TensorFlow
…knowledge of what comes next. You can compile into a static graph any function that takes tensors as input. Just add a @tf.function decorator on it, like this: Let's do the same with the eva…
2026-11-14 自动蜘蛛 相关度 2.5
keras.io 网页 综合
GptOssCausalLM model
…load a pre-trained model. The preset can be passed as one of: For any Task subclass, you can run cls.presets.keys() to list all built-in presets available on the class. This constructor can …
2026-11-14 自动蜘蛛 相关度 2.5
第 153 / 300 页