[Python] Google Deep Learning TensorFlow課程(二) -- 作業一 (下)

延續之前的作業，繼續往下寫XD~

• 分隔 dataset ，如果電腦不夠好的朋友請自行把最下面的dataset大小調小一點

	def make_arrays(nb_rows, img_size):
	if nb_rows:
	dataset = np.ndarray((nb_rows, img_size, img_size), dtype=np.float32)
	labels = np.ndarray(nb_rows, dtype=np.int32)
	else:
	dataset, labels = None, None
	return dataset, labels
	def merge_datasets(pickle_files, train_size, valid_size=0):
	num_classes = len(pickle_files)
	valid_dataset, valid_labels = make_arrays(valid_size, image_size)
	train_dataset, train_labels = make_arrays(train_size, image_size)
	vsize_per_class = valid_size // num_classes
	tsize_per_class = train_size // num_classes
	start_v, start_t = 0, 0
	end_v, end_t = vsize_per_class, tsize_per_class
	end_l = vsize_per_class+tsize_per_class
	for label, pickle_file in enumerate(pickle_files):
	try:
	with open(pickle_file, 'rb') as f:
	letter_set = pickle.load(f)
	if valid_dataset is not None:
	valid_letter = letter_set[:vsize_per_class, :, :]
	valid_dataset[start_v:end_v, :, :] = valid_letter
	valid_labels[start_v:end_v] = label
	start_v += vsize_per_class
	end_v += vsize_per_class
	train_letter = letter_set[vsize_per_class:end_l, :, :]
	train_dataset[start_t:end_t, :, :] = train_letter
	train_labels[start_t:end_t] = label
	start_t += tsize_per_class
	end_t += tsize_per_class
	except Exception as e:
	print('Unable to process data from', pickle_file, ':', e)
	raise
	return valid_dataset, valid_labels, train_dataset, train_labels
	train_size = 2000
	valid_size = 1000
	test_size = 1000
	valid_dataset, valid_labels, train_dataset, train_labels = merge_datasets(train_datasets, train_size, valid_size)
	__, __, test_dataset, test_labels = merge_datasets(test_datasets, test_size)
	print('Training:', train_dataset.shape, train_labels.shape)
	print('Validation:', valid_dataset.shape, valid_labels.shape)
	print('Testing:', test_dataset.shape, test_labels.shape)

view raw dataset.py hosted with ❤ by GitHub

• 接著把 dataset 的資料random

	np.random.seed(133)
	def randomize(dataset, labels):
	permutation = np.random.permutation(labels.shape[0])
	shuffled_dataset = dataset[permutation,:,:]
	shuffled_labels = labels[permutation]
	return shuffled_dataset, shuffled_labels
	train_dataset, train_labels = randomize(train_dataset, train_labels)
	test_dataset, test_labels = randomize(test_dataset, test_labels)

view raw radom.py hosted with ❤ by GitHub
• 接下來要用 logistic regression 分析這些圖片data

	model = LogisticRegression()
	model.fit(train_dataset.reshape(train_dataset.shape[0],-1), train_labels)
	test_pred = model.predict(test_dataset.reshape(test_dataset.shape[0],-1))
	sum(test_labels == test_pred)/float(len(test_labels)) //檢驗一下猜中的比例 (sample 2000)
	#0.709
	sum(test_labels == test_pred)/float(len(test_labels))//檢驗一下猜中的比例 (sample 20000)
	#0.869

view raw logistic.py hosted with ❤ by GitHub

把圖片讀成矩陣後，要再用reshape把矩陣攤平才能放入logistic regression model．預測的時候也一樣把train data資料reshape後丟到裡面，就會跑出來結果．檢驗的方式很簡單，單純去對預測值跟實際值一樣的比例． 當sample資料量增加十倍（2000 -> 20000），預測準確增加了22.6%．

下次就會開始使用Tensor Flow了．