TensorLayer官方中文文档1.7.4:API – 可视化
API - 可视化¶
TensorFlow 提供了可视化模型和激活输出等的工具 TensorBoard。
在这里,我们进一步提供一些可视化模型参数和数据的函数。
read_image (image[, path]) |
Read one image. |
read_images (img_list[, path, n_threads, ...]) |
Returns all images in list by given path and name of each image file. |
save_image (image[, image_path]) |
Save one image. |
save_images (images, size[, image_path]) |
Save mutiple images into one single image. |
draw_boxes_and_labels_to_image (image[, ...]) |
Draw bboxes and class labels on image. |
W ([W, second, saveable, shape, name, fig_idx]) |
Visualize every columns of the weight matrix to a group of Greyscale img. |
CNN2d ([CNN, second, saveable, name, fig_idx]) |
Display a group of RGB or Greyscale CNN masks. |
frame ([I, second, saveable, name, cmap, fig_idx]) |
Display a frame(image). |
images2d ([images, second, saveable, name, ...]) |
Display a group of RGB or Greyscale images. |
tsne_embedding (embeddings, reverse_dictionary) |
Visualize the embeddings by using t-SNE. |
读取与保存图片¶
读取单个图片¶
-
tensorlayer.visualize.
read_image
(image, path='')[源代码]¶ -
Read one image.
Parameters: images : string, file name.
path : string, path.
读取多个图片¶
-
tensorlayer.visualize.
read_images
(img_list, path='', n_threads=10, printable=True)[源代码]¶ -
Returns all images in list by given path and name of each image file.
Parameters: img_list : list of string, the image file names.
path : string, image folder path.
n_threads : int, number of thread to read image.
printable : bool, print infomation when reading images, default is True.
保存单个图片¶
-
tensorlayer.visualize.
save_image
(image, image_path='')[源代码]¶ -
Save one image.
Parameters: images : numpy array [w, h, c]
image_path : string.
保存多个图片¶
-
tensorlayer.visualize.
save_images
(images, size, image_path='')[源代码]¶ -
Save mutiple images into one single image.
Parameters: images : numpy array [batch, w, h, c]
size : list of two int, row and column number.
number of images should be equal or less than size[0] * size[1]
image_path : string.
Examples
>>> images = np.random.rand(64, 100, 100, 3)
>>> tl.visualize.save_images(images, [8, 8], 'temp.png')
保存目标检测图片¶
tensorlayer.visualize.
draw_boxes_and_labels_to_image
(image, classes=[], coords=[], scores=[], classes_list=[], is_center=True, is_rescale=True, save_name=None)[源代码]¶-
Draw bboxes and class labels on image. Return or save the image with bboxes, example in the docs of
tl.prepro
.Parameters: image : RGB image in numpy.array, [height, width, channel].
classes : a list of class ID (int).
coords : a list of list for coordinates.
- Should be [x, y, x2, y2] (up-left and botton-right format)
- If [x_center, y_center, w, h] (set is_center to True).
scores : a list of score (float). (Optional)
classes_list : list of string, for converting ID to string on image.
is_center : boolean, defalt is True.
If coords is [x_center, y_center, w, h], set it to True for converting [x_center, y_center, w, h] to [x, y, x2, y2] (up-left and botton-right).
If coords is [x1, x2, y1, y2], set it to False.is_rescale : boolean, defalt is True.
If True, the input coordinates are the portion of width and high, this API will scale the coordinates to pixel unit internally.
If False, feed the coordinates with pixel unit format.save_name : None or string
The name of image file (i.e. image.png), if None, not to save image.
References
- OpenCV rectangle and putText.
- scikit-image.
可视化模型参数¶
可视化Weight Matrix¶
-
tensorlayer.visualize.
W
(W=None, second=10, saveable=True, shape=[28, 28], name='mnist', fig_idx=2396512)[源代码]¶ -
Visualize every columns of the weight matrix to a group of Greyscale img.
Parameters: W : numpy.array
The weight matrix
second : int
The display second(s) for the image(s), if saveable is False.
saveable : boolean
Save or plot the figure.
shape : a list with 2 int
The shape of feature image, MNIST is [28, 80].
name : a string
A name to save the image, if saveable is True.
fig_idx : int
matplotlib figure index.
Examples
>>> tl.visualize.W(network.all_params[0].eval(), second=10, saveable=True, name='weight_of_1st_layer', fig_idx=2012)
可视化CNN 2d filter¶
tensorlayer.visualize.
CNN2d
(CNN=None, second=10, saveable=True, name='cnn', fig_idx=3119362)[源代码]¶-
Display a group of RGB or Greyscale CNN masks.
Parameters: CNN : numpy.array
The image. e.g: 64 5x5 RGB images can be (5, 5, 3, 64).
second : int
The display second(s) for the image(s), if saveable is False.
saveable : boolean
Save or plot the figure.
name : a string
A name to save the image, if saveable is True.
fig_idx : int
matplotlib figure index.
Examples
>>> tl.visualize.CNN2d(network.all_params[0].eval(), second=10, saveable=True, name='cnn1_mnist', fig_idx=2012)
可视化图像¶
matplotlib显示单图¶
tensorlayer.visualize.
frame
(I=None, second=5, saveable=True, name='frame', cmap=None, fig_idx=12836)[源代码]¶-
Display a frame(image). Make sure OpenAI Gym render() is disable before using it.
Parameters: I : numpy.array
The image
second : int
The display second(s) for the image(s), if saveable is False.
saveable : boolean
Save or plot the figure.
name : a string
A name to save the image, if saveable is True.
cmap : None or string
'gray' for greyscale, None for default, etc.
fig_idx : int
matplotlib figure index.
Examples
>>> env = gym.make("Pong-v0")
>>> observation = env.reset()
>>> tl.visualize.frame(observation)
matplotlib显示多图¶
tensorlayer.visualize.
images2d
(images=None, second=10, saveable=True, name='images', dtype=None, fig_idx=3119362)[源代码]¶-
Display a group of RGB or Greyscale images.
Parameters: images : numpy.array
The images.
second : int
The display second(s) for the image(s), if saveable is False.
saveable : boolean
Save or plot the figure.
name : a string
A name to save the image, if saveable is True.
dtype : None or numpy data type
The data type for displaying the images.
fig_idx : int
matplotlib figure index.
Examples
>>> X_train, y_train, X_test, y_test = tl.files.load_cifar10_dataset(shape=(-1, 32, 32, 3), plotable=False)
>>> tl.visualize.images2d(X_train[0:100,:,:,:], second=10, saveable=False, name='cifar10', dtype=np.uint8, fig_idx=20212)
可视化词嵌入矩阵¶
tensorlayer.visualize.
tsne_embedding
(embeddings, reverse_dictionary, plot_only=500, second=5, saveable=False, name='tsne', fig_idx=9862)[源代码]¶-
Visualize the embeddings by using t-SNE.
Parameters: embeddings : a matrix
The images.
reverse_dictionary : a dictionary
id_to_word, mapping id to unique word.
plot_only : int
The number of examples to plot, choice the most common words.
second : int
The display second(s) for the image(s), if saveable is False.
saveable : boolean
Save or plot the figure.
name : a string
A name to save the image, if saveable is True.
fig_idx : int
matplotlib figure index.
Examples
>>> see 'tutorial_word2vec_basic.py'
>>> final_embeddings = normalized_embeddings.eval()
>>> tl.visualize.tsne_embedding(final_embeddings, labels, reverse_dictionary,
... plot_only=500, second=5, saveable=False, name='tsne')
艾伯特(http://www.aibbt.com/)国内第一家人工智能门户
TensorLayer官方中文文档1.7.4:API – 可视化的更多相关文章
- TensorLayer官方中文文档1.7.4:API – 数据预处理
所属分类:TensorLayer API - 数据预处理¶ 我们提供大量的数据增强及处理方法,使用 Numpy, Scipy, Threading 和 Queue. 不过,我们建议你直接使用 Tens ...
- TensorLayer官方中文文档1.7.4:API – 强化学习
API - 强化学习¶ 强化学习(增强学习)相关函数. discount_episode_rewards([rewards, gamma, mode]) Take 1D float array of ...
- Keras官方中文文档:函数式模型API
\ 函数式模型接口 为什么叫"函数式模型",请查看"Keras新手指南"的相关部分 Keras的函数式模型为Model,即广义的拥有输入和输出的模型,我们使用M ...
- ReactNative官方中文文档0.21
整理了一份ReactNative0.21中文文档,提供给需要的reactnative爱好者.ReactNative0.21中文文档.chm 百度盘下载:ReactNative0.21中文文档 来源: ...
- PyTorch官方中文文档:torch.nn
torch.nn Parameters class torch.nn.Parameter() 艾伯特(http://www.aibbt.com/)国内第一家人工智能门户,微信公众号:aibbtcom ...
- 学习Python 新去处:Python 官方中文文档
Python 作为世界上最好用的语言,官方支持的文档一直没有中文.小伙伴们已经习惯了原汁原味的英文文档,但如果有官方中文文档,那么查阅或理解速度都会大大提升.本文将介绍隐藏在 Python 官网的中文 ...
- django2.0 官方中文文档地址
django2.0 官方开始发布中文文档了,之前还想着一直翻译完成所有有必要的内容,想着可以省事一些了,打开以后看了一下,发现官方的中文文档还没翻译完成, 现在(2018-7-10)最新章节是是 编 ...
- mysql 新手入门 官方文档+官方中文文档附地址
点评: 官方文档地址 官方中文文档地址 sql语句扩展
- PyTorch官方中文文档:torch.optim 优化器参数
内容预览: step(closure) 进行单次优化 (参数更新). 参数: closure (callable) –...~ 参数: params (iterable) – 待优化参数的iterab ...
随机推荐
- Godep的基本使用
[http://studygolang.com/articles/4385] 关于Godep 发现好多golang项目都使用到godep作为包管理的工具,像比较大型的项目,比如kubernetes这种 ...
- [JSOI2008]最大数maxnumber
[JSOI2008]最大数maxnumber 标签: 线段树 单独队列 题目链接 题解 线段树裸题. 如果一直RE可能是你用的cin/cout. Code #include<cstdio> ...
- Inspinia_admin-V2.3原版(英文)
Inspinia_admin-V2.3原版(英文) Inspinia_admin-V2.3 BootStrap原版(英文) 原版是老外开发的,结果 国内某人翻译成中文版进行二次开发 卖998 演示地址 ...
- 【应知应会】15个常用的JavaScript字符串操作方法
1 初始化 //常用初始化方法 var stringVal = "hello iFat3"; //构造函数创建方法 var stringObj = new String(" ...
- 用batch调用DB2 CLPPlus执行多个SQL文
不啰嗦直接上技能. 大概三部分组成: 1.bat文件.(run.bat) 2.辅助SQL文.(AllRun.sql) 3.要执行的SQL文.(S1.sql,S2.sql,S3.sql) +++++++ ...
- iOS中的定时器
据我所知,iOS中的定时器有两种.一个叫NSTimer,一个叫CADisplayLink.还有一种是使用GCD,不常用,这里就不介绍了. 下边说下两个定时器分别得用法: =============== ...
- 历届试题 剪格子 IDA*
思路:限制当前能剪下的最大格子数,保证能得到最少数目.IDA*的典型运用. AC代码 #include <cstdio> #include <cmath> #include & ...
- cache缓存的BUG
坑: 1.在使用这个模版代码开发的时候,当我们改变了数据库表的设置的时候,我们都要把本地的cache缓存文件删除一下. 如果不删除的话,当我们改变数据库设置的之后,程序读取数据是从本地的缓存文件里面读 ...
- IS-IS 路由协议 总结
第一章 is-is的协议概述 1. 发展史 Is-is最早是iso为osi模型中CLNP而设计的协议,后来根据发展需要,也支持了TCP/IP协议,因此,is-is叫做integrated is-is或 ...
- 在 React 中使用 JSX 的好处
优点: 1.允许使用熟悉的语法来定义 HTML 元素树: 2.提供更加语义化且移动的标签: 3.程序结构更容易被直观化: 4.抽象了 React Element 的创建过程: 5.可以随时掌控 HTM ...