在tensorflow下用讀取mnist資料集的方法讀emnist資料集總是顯示多了幾個標簽
uj5u.com熱心網友回復：
+1也是不知道這東西怎么加入神經網路uj5u.com熱心網友回復：
import numpy as np
import matplotlib.pyplot as plt
import gzip
"""
just look the "parse_emnist" API and "load_data" API
parse_emnist: parse the emnist file with extension -'.gz' to .npz
load_data: load the .npz (the data structure is same as the 'mnist' dataset of keras)
"""
def read_idx3(filename):
"""
Read the given file with its name
:param filename: extension name of the file is '.gz'
:return: images data, shape -> num, rows, cols
"""
with gzip.open(filename) as fo:
print('Reading images')
buf = fo.read()
offset = 0 # 指標
header = np.frombuffer(buf, '>i', 4, offset)
magic_number, num_images, num_rows, num_cols = header
print("magic number: {}, \nnumber of images: {},\nnumber of rows: {}, \nnumber of columns: {}" \
.format(magic_number, num_images, num_rows, num_cols))
offset += header.size * header.itemsize
data = np.frombuffer(buf, '>B', num_images * num_rows * num_cols, offset).reshape(
(num_images, num_rows, num_cols))
return data
def read_idx1(filename):
"""
Read the given file with its name
:param filename: extension name of the file is '.gz'
:return: labels
"""
with gzip.open(filename) as fo:
print('Reading labels')
buf = fo.read()
offset = 0
header = np.frombuffer(buf, '>i', 2, offset)
magic_number, num_labels = header
print("magic number: {}, \nnumber of labels: {}" \
.format(magic_number, num_labels))
offset += header.size * header.itemsize
data = np.frombuffer(buf, '>B', num_labels, offset)
return data
def show(images, labels, letter_mapping, window=(3, 4)):
fig, axes = plt.subplots(*window, figsize=(15, 15))
# fig.set_figheight(15)
# fig.set_figwidth(15)
for row in range(window[0]):
for column in range(window[1]):
ind = window[1] * row + column
x = images[ind]
y = labels[ind]
axes[row][column].imshow(x, cmap=plt.cm.gray)
axes[row][column].set_title(letter_mapping[y], fontsize=30)
axes[row][column].axis('off')
plt.tight_layout()
plt.show()
def parse_emnist(output_path, *arg):
"""
:param output_path:
:param arg: four path -> train_img, train_label, test_img, test_label
:return: None
"""
train_img_path, train_label_path, test_img_path, test_label_path = arg
train_img_data = read_idx3(train_img_path)
train_label_data = read_idx1(train_label_path)
test_img_data = read_idx3(test_img_path)
test_label_data = read_idx1(test_label_path)
if np.min(train_label_data) == 1:
train_label_data = train_label_data - 1
test_label_data = test_label_data - 1
np.savez(output_path,
x_train=train_img_data,
y_train=train_label_data,
x_test=test_img_data,
y_test=test_label_data)
print('Congratulations, your job has been done! Go to have a rest.')
def load_data(path):
"""Loads the EMNIST dataset.
# Arguments
path: path where to load the dataset
# Returns
Tuple of Numpy arrays: `(x_train, y_train), (x_test, y_test)`.
"""
f = np.load(path)
x_train, y_train = f['x_train'], f['y_train']
x_test, y_test = f['x_test'], f['y_test']
f.close()
return (x_train, y_train), (x_test, y_test)
uj5u.com熱心網友回復：
我是訓練資料總比標簽多。。轉載請註明出處，本文鏈接：https://www.uj5u.com/qita/273859.html
下一篇：python阻斷TCP連接