zhxiucui

Results 8 issues of zhxiucui

(1)paddle.nn.functional.**max_pool2d**()函数用来构建 max_pool2d 类的一个可调用对象,其将构建一个二维平均池化层,根据输入参数 kernel_size, stride, padding 等参数对输入做最大池化操作。 ![image](https://user-images.githubusercontent.com/115776894/204475740-123a6ad0-230f-4f46-b51e-03b11109894e.png) 更多函数说明见https://www.paddlepaddle.org.cn/documentation/docs/zh/api/paddle/nn/functional/max_pool2d_cn.html (2)paddle.nn.functional.**avg_pool2d**()函数是一个二维平均池化函数,其将构建一个二维平均池化层,根据输入参数 kernel_size, stride, padding 等参数对输入做平均池化操作。 ![image](https://user-images.githubusercontent.com/115776894/204475645-6e568380-bf43-4e04-bbd3-8d5baf08533a.png) 更多函数说明见https://www.paddlepaddle.org.cn/documentation/docs/zh/api/paddle/nn/functional/avg_pool2d_cn.html (3)paddle.nn.functional.**conv2d_transpose**()函数是二维转置卷积层(Convlution2D transpose layer),该层根据输入(input)、卷积核(kernel)和空洞大小(dilations)、步长(stride)、填充(padding)来计算输出特征层大小或者通过 output_size 指定输出特征层大小。输入(Input)和输出(Output)为 NCHW 或 NHWC 格式,其中 N 为批尺寸,C 为通道数(channel),H 为特征层高度,W 为特征层宽度。卷积核是...

### New Issue Checklist - [ ] I have read the [Contribution Guidelines](https://github.com/tensorlayer/tensorlayer/blob/master/CONTRIBUTING.md) - [ ] I searched for [existing GitHub issues](https://github.com/tensorlayer/tensorlayer/issues) ### Issue Description [INSERT DESCRIPTION OF THE PROBLEM]...

paddle.nn.InstanceNorm2D(num_features, epsilon=1e-05, momentum=0.9, weight_attr=None, bias_attr=None, data_format="NCHW", name=None) ![image](https://user-images.githubusercontent.com/115776894/205000098-c591d462-7547-4475-9147-ff24b59dd283.png) 更多见接口文档https://www.paddlepaddle.org.cn/documentation/docs/zh/2.3/api/paddle/nn/InstanceNorm2D_cn.html#instancenorm2d ```python # ======================================================== # ###### THIS CODE IS AN EXAMPLE, REPLACE WITH YOUR OWN ###### # ======================================================== # import tensorlayerx as...

(1)paddle.nn.MaxUnPool2D(kernel_size, stride=None, padding=0, data_format='NCHW', output_size=None, name=None) 构建 MaxUnPool2D 类的一个可调用对象,根据输入的 input 和最大值位置计算出池化的逆结果。所有非最大值设置为零。 ![image](https://user-images.githubusercontent.com/115776894/204477386-a8ad193b-b117-430f-ac23-699af292cd4e.png) 更多函数说明见https://www.paddlepaddle.org.cn/documentation/docs/zh/api/paddle/nn/MaxUnPool2D_cn.html (2)class paddle.nn.Pad2D(padding, mode='constant', value=0.0, data_format='NCHW', name=None) 按照 padding、mode 和 value 属性对输入进行填充。更多函数说明见https://www.paddlepaddle.org.cn/documentation/docs/zh/api/paddle/nn/Pad2D_cn.html

paddle.nn.functional.interpolate接口说明如下 ![image](https://user-images.githubusercontent.com/115776894/204244223-270a2cf3-18da-4328-a55c-3ac59dd3e9f1.png)

### New Issue Checklist - [ ] I have read the [Contribution Guidelines](https://github.com/tensorlayer/tensorlayer/blob/master/CONTRIBUTING.md) - [ ] I searched for [existing GitHub issues](https://github.com/tensorlayer/tensorlayer/issues) ### Issue Description [INSERT DESCRIPTION OF THE PROBLEM]...

### New Issue Checklist - [ ] I have read the [Contribution Guidelines](https://github.com/tensorlayer/tensorlayer/blob/master/CONTRIBUTING.md) - [ ] I searched for [existing GitHub issues](https://github.com/tensorlayer/tensorlayer/issues) ### Issue Description [INSERT DESCRIPTION OF THE PROBLEM]...

paddle源码paddle.argmax(x, axis=None, keepdim=False, dtype='int64', name=None) 其中keepdim(bool,可选)- 是否在输出Tensor中保留减小的维度。如果 keepdim 为True,则输出Tensor和 x 具有相同的维度(减少的维度除外,减少的维度的大小为1),默认值为False。 tensorlayerx源码paddle.argmax(x, axis=None, dtype='int64')