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 a image.
save_images(images, size[, image_path])	Save multiple images into one single image.
draw_boxes_and_labels_to_image(image, ...[, ...])	Draw bboxes and class labels on image.
draw_mpii_pose_to_image(image, poses[, ...])	Draw people(s) into image using MPII dataset format as input, return or save the result 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.
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='')

Read one image.

参数

• image (str) -- The image file name.

• path (str) -- The image folder path.

返回

The image.

返回类型

numpy.array

读取多个图片

tensorlayer.visualize.read_images(img_list, path='', n_threads=10, printable=True)

Returns all images in list by given path and name of each image file.

参数

• img_list (list of str) -- The image file names.

• path (str) -- The image folder path.

• n_threads (int) -- The number of threads to read image.

• printable (boolean) -- Whether to print information when reading images.

返回

The images.

返回类型

list of numpy.array

保存单个图片

tensorlayer.visualize.save_image(image, image_path='_temp.png')

Save a image.

参数

• image (numpy array) -- [w, h, c]

• image_path (str) -- path

保存多个图片

tensorlayer.visualize.save_images(images, size, image_path='_temp.png')

Save multiple images into one single image.

参数

• images (numpy array) -- (batch, w, h, c)

• size (list of 2 ints) -- row and column number. number of images should be equal or less than size[0] * size[1]

• image_path (str) -- save path

实际案例

>>> import numpy as np
>>> import tensorlayer as tl
>>> 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)

Draw bboxes and class labels on image. Return or save the image with bboxes, example in the docs of tl.prepro.

参数

• image (numpy.array) -- The RGB image [height, width, channel].

• classes (list of int) -- A list of class ID (int).

• coords (list of int) --

  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 (list of float) -- A list of score (float). (Optional)

• classes_list (list of str) -- for converting ID to string on image.

• is_center (boolean) --

  Whether the coordinates is [x_center, y_center, w, h]

  • If coordinates are [x_center, y_center, w, h], set it to True for converting it to [x, y, x2, y2] (up-left and botton-right) internally.

  • If coordinates are [x1, x2, y1, y2], set it to False.

• is_rescale (boolean) --

  Whether to rescale the coordinates from pixel-unit format to ratio format.

  • 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 str) -- The name of image file (i.e. image.png), if None, not to save image.

返回

The saved image.

返回类型

numpy.array

引用

• OpenCV rectangle and putText.

• scikit-image.

保存姿态估计图片（MPII）

tensorlayer.visualize.draw_mpii_pose_to_image(image, poses, save_name='image.png')

Draw people(s) into image using MPII dataset format as input, return or save the result image.

This is an experimental API, can be changed in the future.

参数

• image (numpy.array) -- The RGB image [height, width, channel].

• poses (list of dict) -- The people(s) annotation in MPII format, see tl.files.load_mpii_pose_dataset.

• save_name (None or str) -- The name of image file (i.e. image.png), if None, not to save image.

返回

The saved image.

返回类型

numpy.array

实际案例

>>> import pprint
>>> import tensorlayer as tl
>>> img_train_list, ann_train_list, img_test_list, ann_test_list = tl.files.load_mpii_pose_dataset()
>>> image = tl.vis.read_image(img_train_list[0])
>>> tl.vis.draw_mpii_pose_to_image(image, ann_train_list[0], 'image.png')
>>> pprint.pprint(ann_train_list[0])

引用

• MPII Keyponts and ID

可视化模型参数

可视化Weight Matrix

tensorlayer.visualize.W(W=None, second=10, saveable=True, shape=None, name='mnist', fig_idx=2396512)

Visualize every columns of the weight matrix to a group of Greyscale img.

参数

• 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 or None) -- 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.

实际案例

>>> tl.visualize.draw_weights(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)

Display a group of RGB or Greyscale CNN masks.

参数

• 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 (str) -- A name to save the image, if saveable is True.

• fig_idx (int) -- The matplotlib figure index.

实际案例

>>> 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)

Display a frame. Make sure OpenAI Gym render() is disable before using it.

参数

• 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 (str) -- A name to save the image, if saveable is True.

• cmap (None or str) -- 'gray' for greyscale, None for default, etc.

• fig_idx (int) -- matplotlib figure index.

实际案例

>>> 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)

Display a group of RGB or Greyscale images.

参数

• 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 (str) -- 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.

实际案例

>>> 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)

Visualize the embeddings by using t-SNE.

参数

• embeddings (numpy.array) -- The embedding matrix.

• reverse_dictionary (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 (str) -- A name to save the image, if saveable is True.

• fig_idx (int) -- matplotlib figure index.

实际案例

>>> 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')