Firstly, I am newbie to these topics. My neural network classifies everything as person or background on both training and validation sets. Training set is VOC2011.
https://github.com/JihongJu/keras-fcn
#Defining model
from keras_fcn import FCN
fcn_vgg16 = FCN(input_shape=(500, 500, 3), classes=21)
fcn_vgg16.load_weights('fcn_vgg16_weights.h5')
#Preprocessing to image
from keras.preprocessing import image
from keras.applications.vgg16 import preprocess_input
import numpy as np
img_path = 'catdog2.jpg'
img1 = image.load_img(img_path, target_size=(500, 500))
x = image.img_to_array(img1)
x = np.expand_dims(x, axis=0)
#x = preprocess_input(x)
predicted = fcn_vgg16.predict(x)
predicted = np.squeeze(predicted, axis=0)
#I may have completely misunderstood the visualization part
color_list = {0:[176, 23, 31], 1:[220, 20, 60], 2:[139, 71, 93], 3:[0, 9, 236], 3:[255, 20, 147],
4:[139, 0, 139], 5:[0, 0, 255], 6:[202, 225, 255], 7:[30, 144, 255], 8:[240, 248, 255],
9:[0, 245, 255], 10:[0, 199, 140], 11:[0, 255, 127], 12:[139, 131, 134], 13:[255, 255, 0],
14:[255,165, 0], 15:[255, 153, 18], 16:[255, 69, 0], 17:[255, 0, 0], 18:[0, 0, 0],
19:[219,219, 219], 20:[0, 245, 255],255:[0, 0, 205]}
#*15:[255, 153, 18] => Orange*
"""
{0: 'background',
1: 'aeroplane',
2: 'bicycle',
3: 'bird',
4: 'boat',
5: 'bottle',
6: 'bus',
7: 'car',
8: 'cat',
9: 'chair',
10: 'cow',
11: 'diningtable',
12: 'dog',
13: 'horse',
14: 'motorbike',
15: 'person',
16: 'potted-plant',
17: 'sheep',
18: 'sofa',
19: 'train',
20: 'tv/monitor',
255: 'ambigious'}
"""
#http://warmspringwinds.github.io/tensorflow/tf-slim/2017/01/23/fully-convolutional-networks-(fcns)-for-image-segmentation/
import scipy.misc as smp
#Create a 500x500x3 array of 8 bit unsigned integers
data = np.zeros((500, 500, 3), dtype=np.uint8)
for i in range(500):
for j in range(500):
data[i][j] = color_list[np.argmax(predicted[i][j])]
img2 = smp.toimage(data)
import matplotlib.pyplot as plt
f, (ax1, ax2) = plt.subplots(1, 2, sharey=True)
ax1.imshow(np.squeeze(img1, axis=0))
ax2.imshow(img2)
plt.show()
Is that a kind of local minima (or saddle point?) that predicts everything as background (the most frequent label)?
What is the reason, what are your ideas? And also is there any proper way for visualization of semantic segmentation?
I guess there is something wrong about training. If there is overfitting, losses have always decreased, why is the result the same for traning data.
