Vector DB tool Step 1: Register and deploy a sparse encoding model Step 2: Ingest data into an index Step 3: Register a flow agent that will run the VectorDBTool Step 4: Run the...

Installing plugins Managing plugins List Usage Example Path and HTTP method Example response Install Install a plugin by name: Usage Example Install a plugin from a zip f...

Vector DB tool Step 1: Register and deploy a sparse encoding model Step 2: Ingest data into an index Step 3: Register a flow agent that will run the VectorDBTool Step 4: Run the...

6.4 Influential Instances 6.4.1 Deletion Diagnostics 6.4.2 Influence Functions 6.4.3 Advantages of Identifying Influential Instances 6.4.4 Disadvantages of Identifying Influenti...

PixelShuffle 参数 形状 返回 代码示例 PixelShuffle paddle.nn.PixelShuffle ( upscale_factor, data_format=’NCHW’, name=None ) [源代码] 该算子将一个形为[N, C, H, W]或是[N, H, W, C]的Tensor重新排列成形为 [...

linear_lr_warmup linear_lr_warmup paddle.fluid.layers. linear_lr_warmup ( learning_rate, warmup_steps, start_lr, end_lr ) [源代码] 该OP使用学习率优化策略-线性学习率热身(warm up)对学习率进行初步调整。在正常调整学...

lrn lrn paddle.fluid.layers. lrn (input, n=5, k=1.0, alpha=0.0001, beta=0.75, name=None)[源代码] 该OP实现了局部响应正则化层（Local Response Normalization Layer），用于对局部输入区域正则化，执行一种侧向抑制（late...

bpr_loss bpr_loss paddle.fluid.layers. bpr_loss (input, label, name=None)[源代码] 贝叶斯个性化排序损失函数（Bayesian Personalized Ranking Loss Operator ） 该OP属于pairwise类型的损失函数。损失值由下式计算而得:...

Search for an agent Path and HTTP methods Example request: Searching for all agents Example request: Searching for agents of a certain type Example: Searching for an agent by des...