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:

Parameters:	images : string, file name. path : string, path.

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:

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.

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:

Parameters:	images : numpy array [w, h, c] image_path : string.

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:

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.

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:

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.

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:

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.

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:

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.

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:

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.

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:

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.

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:

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.

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