def create_generator(dataset_name,
split,
batch_size,
randomize,
attribute=None):
"""Creates a batch generator for the dataset.
Args:
dataset_name: `str`. The name of the dataset.
split: `str`. The split of data. It can be `train`, `val`, or `test`.
batch_size: An integer. The batch size.
randomize: `bool`. Whether to randomize the order of images before
batching.
attribute (optional): For cele
Returns:
image_batch: A Python generator for the images.
label_batch: A Python generator for the labels.
"""
flags = tf.app.flags.FLAGS
if dataset_name.lower() == 'mnist':
ds = Mnist()
elif dataset_name.lower() == 'f-mnist':
ds = FMnist()
elif dataset_name.lower() == 'cifar-10':
ds = Cifar10()
elif dataset_name.lower() == 'celeba':
ds = CelebA(attribute=attribute)
else:
raise ValueError("Dataset {} is not supported.".format(dataset_name))
ds.load(split=split, randomize=randomize)
def get_gen():
for i in range(0, len(ds) - batch_size, batch_size):
image_batch, label_batch = ds.images[
i:i + batch_size], \
ds.labels[i:i + batch_size]
yield image_batch, label_batch
return get_gen
import sys
sys.path.append('..')
sys.path.append('../..')
sys.path.append('../../cutedl')
'''
使用卷积神经网络实现的手写数字识别模型
'''
from datasets.mnist import Mnist
'''
加载手写数字数据集
'''
mnist = Mnist('../datasets/mnist')
ds_train, ds_test = mnist.load(64)
import pdb
import numpy as np
from cutedl.model import Model
from cutedl.session import Session
from cutedl import session, losses, optimizers, utils
from cutedl import nn_layers as nn
from cutedl import cnn_layers as cnn
import fit_tools
report_path = "./pics/mnist-recoginze-"
model_path = "./model/mnist-recoginze-"
'''
# coding=utf-8
import sys
sys.path.append('..')
sys.path.append('../..')
sys.path.append('../../cutedl')
'''
手写数字识别模型
'''
from datasets.mnist import Mnist
'''
加载手写数字数据集
'''
mnist = Mnist('../datasets/mnist')
ds_train, ds_test = mnist.load(64, flatting=True)
import pdb
import numpy as np
from cutedl.model import Model
from cutedl.session import Session
from cutedl import session, losses, optimizers, utils
from cutedl import nn_layers as nn
import matplotlib.pyplot as plt
'''
生成模型的拟合报告
'''
def test_classifier(self, input_split='test', save_result=False, model_name=None, labels_filename=None,
acc_filename=None, acc_filenames_i=None):
"""Predicts labels and compares them to ground truth labels from given split. Returns test accuracy.
Args:
input_split: What split to test on [train|val|test].
save_result: Optional, boolean. If True saves predicted labels and accuracy.
model_name: For neural network classifiers, model name to load and use to predict.
labels_filename: Optional, string. Path to save predicted labels in.
acc_filename: Optional, string. Path to save predicted accuracy in.
acc_filenames_i: Optional, array of strings. Path to save class-specific predicted labels in.
Returns:
predicted_labels: Predicted labels for the input split.
accuracy: Accuracy on the input split.
per_class_accuracies: Array of per-class accuracies on the input split.
Raises:
IOError: If an input error occurs when loading features, or an output error occurs when saving results.
ValueError: If the specified dataset [mnist|f-mnist|celeba] or classifier type
[svm|linear-svm|lmnn|logistic|knn|nn] is not supported.
"""
# If save_result is True, but no labels_filename was specified, use default filename.
if save_result and (labels_filename is None):
output_dir = self.get_output_dir()
labels_filename = self.get_labels_filename(input_split)
labels_filename = os.path.join(output_dir, labels_filename)
# If save_result is True, but no acc_filename was specified, use default filename.
if save_result and (acc_filename is None):
output_dir = self.get_output_dir()
acc_filename, acc_filenames_i = self.get_acc_filename(input_split)
acc_filename = os.path.join(output_dir, acc_filename)
for i in range(self.classifier_params['num_classes']):
acc_filenames_i[i] = os.path.join(output_dir, acc_filenames_i[i])
# Load feature vectors.
feature_dir = os.path.dirname(self.classifier_params['feature_file'])
feature_file = os.path.basename(self.classifier_params['feature_file'])
feature_file = feature_file.replace('train', input_split)
feature_file = os.path.join(feature_dir, feature_file)
try:
with open(feature_file, 'r') as f:
features = cPickle.load(f)
except IOError as err:
print('[!] I/O error({0}): {1}.'.format(err.errno, err.strerror))
if 'verbose' in self.classifier_params and self.classifier_params['verbose']:
print('[*] Loaded feature vectors from {}.'.format(feature_file))
# Initiate dataset object to load ground-truth labels.
if self.classifier_params['dataset'] == 'mnist':
ds = Mnist()
elif self.classifier_params['dataset'] == 'f-mnist':
ds = FMnist()
elif self.classifier_params['dataset'] == 'celeba':
ds = CelebA(resize_size=self.classifier_params['output_height'],
attribute=self.classifier_params['attribute'])
else:
raise ValueError('[!] Dataset {} is not supported.'.format(self.classifier_params['dataset']))
# Load ground-truth labels.
_, labels, _ = ds.load(input_split)
num_samples = min(np.shape(features)[0], len(labels))
labels = labels[:num_samples]
features = features[:num_samples, :]
if 'verbose' in self.classifier_params and self.classifier_params['verbose']:
print('[*] Loaded ground-truth labels from: {}.'.format(
self.classifier_params['dataset']))
# Predict labels.
if self.classifier_type in ('svm', 'logistic', 'knn', 'linear-svm', 'lmnn'):
predicted_labels = self.predict(features, save_result, labels_filename)
elif self.classifier_type == 'nn':
predicted_labels = self.predict(features, save_result, model_name, labels_filename)
else:
raise ValueError('[!] Classifier type {} is not supported.'.format(self.classifier_type))
# Compare predicted labels to ground-truth labels and calculate accuracy.
num_correct = np.sum(np.equal(predicted_labels, labels))
accuracy = num_correct / (1.0 * len(labels))
per_class_accuracies = []
for i in range(self.classifier_params['num_classes']):
idx = np.where(np.equal(labels, i))[0]
num_correct = np.sum(np.equal(predicted_labels[idx], labels[idx]))
accuracy_i = num_correct / (1.0 * len(labels[idx]))
per_class_accuracies.append(accuracy_i)
# Save results.
if save_result:
try:
with open(acc_filename, 'w') as fp:
fp.write("{}".format(accuracy))
except IOError as err:
print("[!] I/O error({0}): {1}.".format(err.errno,
err.strerror))
if self.classifier_params.has_key('verbose') and self.classifier_params['verbose']:
print('[*] Saved predicted labels {}.'.format(labels_filename))
print('[*] Saved predicted accuracy {}.'.format(acc_filename))
for i in range(self.classifier_params['num_classes']):
try:
with open(acc_filenames_i[i], 'w') as fp:
fp.write("{}".format(per_class_accuracies[i]))
except IOError as err:
print("[!] I/O error({0}): {1}.".format(err.errno,
err.strerror))
if self.classifier_params.has_key('verbose') and self.classifier_params['verbose']:
print('[*] Testing complete. Accuracy on {} split {}.'.format(
input_split, accuracy))
for i in range(self.classifier_params['num_classes']):
print('[*] Testing complete. Accuracy on {} split, class {}: {}.'.format(input_split, i,
per_class_accuracies[i]))
return predicted_labels, accuracy, per_class_accuracies
def validate(self):
"""Only needed for neural networks. Validates different checkpoints by testing them on the validation split and
retaining the one with the top accuracy.
Returns:
best_model: Name of chosen best model (empty string if no validation was performed). An empty string is
returned for non neural network classifiers.
Raises:
IOError: If an input error occurs when loading feature vectors, or an output error occurs when saving the
chosen model.
ValueError: If the specified dataset [mnist|f-mnist|celeba] or classifier type
[svm|linear-svm|lmnn|logistic|knn|nn] is not supported.
"""
if 'verbose' in self.classifier_params and self.classifier_params['verbose']:
print("[*] Validating.")
# Get feature file paths.
feature_dir = os.path.dirname(self.classifier_params['feature_file'])
feature_file = os.path.basename(self.classifier_params['feature_file'])
feature_file = feature_file.replace('train', 'val')
feature_file = os.path.join(feature_dir, feature_file)
# Load feature vectors.
try:
with open(feature_file, 'r') as f:
features = cPickle.load(f)
except IOError as err:
print("[!] I/O error({0}): {1}.".format(err.errno, err.strerror))
if 'verbose' in self.classifier_params and self.classifier_params['verbose']:
print('[*] Loaded feature vectors from {}.'.format(feature_file))
# Initialize the dataset object to load ground-truth labels.
if self.classifier_params['dataset'] == 'mnist':
ds = Mnist()
elif self.classifier_params['dataset'] == 'f-mnist':
ds = FMnist()
elif self.classifier_params['dataset'] == 'celeba':
ds = CelebA(resize_size=self.classifier_params['output_height'],
attribute=self.classifier_params['attribute'])
else:
raise ValueError('[!] Dataset {} is not supported.'.format(self.classifier_params['dataset']))
# Load ground-truth labels from the validation split.
_, labels, _ = ds.load('val')
num_samples = min(np.shape(features)[0], len(labels))
labels = labels[:num_samples]
features = features[:num_samples, :]
if 'verbose' in self.classifier_params and self.classifier_params['verbose']:
print('[*] Loaded ground-truth labels from {}.'.format(
self.classifier_params['dataset']))
# Non neural network classifiers do not require validation as no intermediate models exist.
if self.classifier_type in ('svm', 'logistic', 'knn', 'linear-svm', 'lmnn'):
print('[!] No validation needed.')
return ""
# Neural network classifiers.
elif self.classifier_type == 'nn':
# Call the neural network validate function on the features.
best_acc, best_model, _ = self.estimator.validate(features, labels, session=self.session)
# Save results.
try:
with open(os.path.join(self.get_output_dir(), self.tf_checkpoint_dir(), 'chosen_model.txt'), 'w') as fp:
fp.write("{} {}".format(os.path.basename(best_model), best_acc))
except IOError as err:
print("[!] I/O error({0}): {1}.".format(err.errno,
err.strerror))
if 'verbose' in self.classifier_params and self.classifier_params['verbose']:
print(
'[*] Chose model: {}, with validation accuracy {}.'.format(os.path.basename(best_model), best_acc))
return best_model
else:
raise ValueError('[!] Classifier type {} is not supported.'.format(self.classifier_type))
def train(self, features=None, labels=None, retrain=False, num_train=-1):
"""Trains classifier using training features and ground truth training labels.
Args:
features: Path to training feature vectors (use None to automatically load saved features from experiment
output directory).
labels: Path to ground truth train labels (use None to automatically load from dataset).
retrain: Boolean, whether or not to retrain if classifier is already saved.
num_train: Number of training samples to use (use -1 to include all training samples).
Raises:
ValueError: If the specified dataset [mnist|f-mnist|celeba] or classifier type
[svm|linear-svm|lmnn|logistic|knn|nn] is not supported.
"""
# If no feature vector is provided load from experiment output directory.
if features is None:
feature_file = self.classifier_params['feature_file']
try:
with open(feature_file, 'r') as f:
features = cPickle.load(f)
except IOError as err:
print("[!] I/O error({0}): {1}.".format(err.errno,
err.strerror))
if self.classifier_params.has_key('verbose') and self.classifier_params['verbose']:
print('[*] Loaded feature file from {}.'.format(feature_file))
# If no label vector is provided load from dataset.
if labels is None:
# Create dataset object based on dataset name.
if self.classifier_params['dataset'] == 'mnist':
ds = Mnist()
elif self.classifier_params['dataset'] == 'f-mnist':
ds = FMnist()
elif self.classifier_params['dataset'] == 'celeba':
ds = CelebA(resize_size=self.classifier_params['output_height'],
attribute=self.classifier_params['attribute'])
else:
raise ValueError('[!] Dataset {} is not supported.'.format(self.classifier_params['dataset']))
# Load labels from the train split.
_, labels, _ = ds.load('train')
num_samples = min(np.shape(features)[0], len(labels))
# Restrict to the first num_train samples if num_train is not -1.
if num_train > -1:
num_samples = min(num_train, num_samples)
labels = labels[:num_samples]
features = features[:num_samples, :]
if self.classifier_params.has_key('verbose') and self.classifier_params['verbose']:
print('[*] Loaded ground truth labels from {}.'.format(
self.classifier_params['dataset']))
# Train the classifier.
if self.classifier_type in ('svm', 'logistic', 'knn', 'linear-svm'):
self.estimator.fit(features, labels)
# Neural network classifiers.
elif self.classifier_type == 'nn':
self.estimator.fit(features, labels, retrain=retrain, session=self.session)
# For LMNN, first transform the feature vector then perform k-NN.
elif self.classifier_type == 'lmnn':
# Learn the metric.
self.helper_estimator.fit(features, labels)
# Transform feature space.
transformed_features = self.helper_estimator.transform(features)
# Create k-nn graph.
self.estimator.fit(transformed_features, labels)
else:
raise ValueError('[!] Classifier type {} is not supported.'.format(self.classifier_type))
if ('verbose' in self.classifier_params) and self.classifier_params['verbose']:
print('[*] Trained classifier.')