MortisHuang

fig.canvas.mpl_connect('motion_notify_event', hover)         

MortisHuang

def hover(event):
    # if the mouse is over the scatter points
    if line.contains(event)[0]:
        # find out the index within the array from the event
        ind, = line.contains(event)[1]["ind"]
        # get the figure size
        w,h = fig.get_size_inches()*fig.dpi
        ws = (event.x > w/2.)*-1 + (event.x <= w/2.) 
        hs = (event.y > h/2.)*-1 + (event.y <= h/2.)
        # if event occurs in the top or right quadrant of the figure,

MortisHuang

import matplotlib.pyplot as plt
from matplotlib.offsetbox import OffsetImage, AnnotationBbox
import numpy as np; np.random.seed(42)

# Generate data x, y for scatter and an array of images.
x = np.arange(20)
y = np.random.rand(len(x))
arr = np.empty((len(x),10,10))
for i in range(len(x)):
    f = np.random.rand(5,5)

MortisHuang

# create the annotations box
im = OffsetImage(arr[0,:,:], zoom=5)
xybox=(50., 50.)
ab = AnnotationBbox(im, (50,50), xybox=xybox, xycoords='data',
        boxcoords="offset points",  pad=0.3,  arrowprops=dict(arrowstyle="->"))

# add it to the axes and make it visible
ax.add_artist(ab)
ab.set_visible(True)

MortisHuang

# create figure and plot scatter
fig   = plt.figure()
ax    = fig.add_subplot(111)
line, = ax.plot(x,y, ls="", marker="o")

MortisHuang

import matplotlib.pyplot as plt
from matplotlib.offsetbox import OffsetImage, AnnotationBbox
import numpy as np; np.random.seed(42)

# Generate data x, y for scatter and an array of images.
x = np.arange(20)
y = np.random.rand(len(x))
arr = np.empty((len(x),10,10))
for i in range(len(x)):
    f = np.random.rand(5,5)

MortisHuang

import matplotlib.pyplot as plt
from matplotlib.offsetbox import OffsetImage, AnnotationBbox
import numpy as np; np.random.seed(42)

# Generate data x, y for scatter and an array of images.
x = np.arange(20)
y = np.random.rand(len(x))
arr = np.empty((len(x),10,10))
for i in range(len(x)):
    f = np.random.rand(5,5)

MortisHuang

# -*- coding: utf-8 -*-
"""

@author: Mortis
"""

#%% Read and prepare data

import os
import keras

MortisHuang

import keras.backend as K
import cv2
from keras.preprocessing.image import array_to_img
from scipy.misc import imsave
label_name = {0:'Cat',1:'Dog'}
index = 8
img = test_data[index]
img_show=array_to_img(img)
imsave('Image_{}.png'.format(index),img_show)
img=img.reshape(-1,128,128,3)

MortisHuang

#%% t-SNE
from keras.models import Model
from sklearn.manifold import TSNE

def plot_tSNE(model,layername,input_data,input_label,modelname='Model',label_name=['label one']):
    batch_size=64
    intermediate_layer_model = Model(inputs=model.input,
                                     outputs=model.get_layer(layername).output)
    intermediate_output = intermediate_layer_model.predict(
            input_data, batch_size=batch_size, verbose=1)