榜单
IT文库
服务器优惠
-
Regularizing an LSTM
Regularizing an LSTM Dropout Activation Regularization and Temporal Activation Regularization Training a Weight-Tied Regularized LSTM Regularizing an LSTM Recurrent neural n... -
Approximate k-NN search
Approximate k-NN search Recommendations for engines and cluster node sizing Get started with approximate k-NN Building a k-NN index from a model Using approximate k-NN with filte... -
RNNTrainer
callbacks.rnn Training tweaks for an RNN class RNNTrainer [source] [test] Callback methods on_epoch_begin [source] [test] on_loss_begin [source] [test] on_backward_begin ... -
End-to-end Kubeflow on IBM Cloud
End-to-end Kubeflow on IBM Cloud Introduction Overview of IKS The model and the data The overall workflow Run the MNIST Tutorial on IKS End-to-end Kubeflow on IBM Cloud Ru... -
Reference Overview
Reference Overview TFJob PyTorchJob Metadata Reference Overview Reference documentation for Kubeflow APIs and services. TFJob TFJob is a Kubernetes custom resourc... -
Fairing
Fairing Overview of Kubeflow Fairing Install Kubeflow Fairing Configure Kubeflow Fairing Fairing on Azure Fairing on GCP Tutorials Reference Fairing Documentation for Ku... -
dropout2d
dropout2d 参数 返回 代码示例 dropout2d paddle.nn.functional. dropout2d ( x, p=0.5, training=True, name=None ) [源代码] 该算子根据丢弃概率 p ，在训练过程中随机将某些通道特征图置0(对一个形状为 NCHW 的4维张量，通道特征图指的是其中的形状... -
dropout2d
dropout2d 参数 返回 代码示例 dropout2d paddle.nn.functional.dropout2d ( x, p=0.5, training=True, name=None ) [源代码] 该算子根据丢弃概率 p ，在训练过程中随机将某些通道特征图置0(对一个形状为 NCHW 的4维张量，通道特征图指的是其中的形状... -
3.1. Cross-validation: evaluating estimator performance
3.1. Cross-validation: evaluating estimator performance 3.1.1. Computing cross-validated metrics 3.1.1.1. The cross_validate function and multiple metric evaluation 3.1.1.2. Obtai... -
Improving Our Model
Improving Our Model The Learning Rate Finder Unfreezing and Transfer Learning Discriminative Learning Rates Selecting the Number of Epochs Deeper Architectures Improving O...