python中range函数

函数语法

range(start, stop[, step])

参数说明：

• start: 计数从 start 开始。默认是从 0 开始。例如range（5）等价于range（0， 5）;
• stop: 计数到 stop 结束，但不包括 stop。例如：range（0， 5） 是[0, 1, 2, 3, 4]没有5
• step：步长，默认为1。例如：range（0， 5） 等价于 range(0, 5, 1)

实例

 
>>>range(10)        # 从 0 开始到 10
[0, 1, 2, 3, 4, 5, 6, 7, 8, 9]
>>> range(1, 11)     # 从 1 开始到 11
[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
>>> range(0, 30, 5)  # 步长为 5
[0, 5, 10, 15, 20, 25]
>>> range(0, 10, 3)  # 步长为 3
[0, 3, 6, 9]
>>> range(0, -10, -1) # 负数
[0, -1, -2, -3, -4, -5, -6, -7, -8, -9]
>>> range(0)
[]
>>> range(1, 0)
[]

以下是 range 在 for 中的使用，循环出runoob 的每个字母:

 
>>>x = 'runoob'
>>> for i in range(len(x)) :
...     print(x[i])
... 
r
u
n
o
o
b
>>>

 

在tensorflow python 3.6的环境下，range函数中实参必须为int型，否则报错

 

def load_dataset(data_dir, img_size):
	"""img_files = os.listdir(data_dir)
	test_size = int(len(img_files)*0.2)
	test_indices = random.sample(range(len(img_files)),test_size)
	for i in range(len(img_files)):
		#img = scipy.misc.imread(data_dir+img_files[i])
		if i in test_indices:
			test_set.append(data_dir+"/"+img_files[i])
		else:
			train_set.append(data_dir+"/"+img_files[i])
	return"""
	global train_set
	global test_set
	imgs = [] 
	img_files = os.listdir(data_dir)
	for img in img_files:
		try:
			tmp= scipy.misc.imread(data_dir+"/"+img)
			x,y,z = tmp.shape
			coords_x = x // img_size
			coords_y = y // img_size
           
#			coords_y = y / img_size
#                       coords_x = x / img_size
            
            #print (coords_x)
			coords = [ (q,r) for q in range(coords_x) for r in range(coords_y) ]
			for coord in coords:
				imgs.append((data_dir+"/"+img,coord))
		except:
			print ("oops")
	test_size = min(10,int( len(imgs)*0.2))
	random.shuffle(imgs)
	test_set = imgs[:test_size]
	train_set = imgs[test_size:][:200]
	return

def get_batch(batch_size,original_size,shrunk_size):
	global batch_index
	"""img_indices = random.sample(range(len(train_set)),batch_size)
	for i in range(len(img_indices)):
		index = img_indices[i]
		img = scipy.misc.imread(train_set[index])
		if img.shape:
			img = crop_center(img,original_size,original_size)
			x_img = scipy.misc.imresize(img,(shrunk_size,shrunk_size))
			x.append(x_img)
			y.append(img)"""
	max_counter = len(train_set)/batch_size   
	counter = batch_index % max_counter
#	counter = tf.to_int32(batch_index % max_counter)    
	window = [x for x in range(int(counter*batch_size),int((counter+1)*batch_size))]
 
#	window = [x for x in range(tf.to_int32(counter*batch_size),tf.to_int32((counter+1)*batch_size))]
#	window = [x for x in np.arange((counter*batch_size),((counter+1)*batch_size))]
#	a1=tf.cast(counter*batch_size,tf.int32)
#	a2=tf.cast((counter+1)*batch_size,tf.int32)
#	window = [x for x in range(a1,a2)]
#	window = [x for x in np.arange(a1,a2)]
#	win2 = tf.cast(window,tf.int32)
#	win2 = tf.to_int32(window)
#	win2 = tf.to_int64(window)
 
	imgs = [train_set[q] for q in window]
	x = [scipy.misc.imresize(get_image(q,original_size),(shrunk_size,shrunk_size)) for q in imgs]#scipy.misc.imread(q[0])[q[1][0]*original_size:(q[1][0]+1)*original_size,q[1][1]*original_size:(q[1][1]+1)*original_size].resize(shrunk_size,shrunk_size) for q in imgs]
	y = [get_image(q,original_size) for q in imgs]#scipy.misc.imread(q[0])[q[1][0]*original_size:(q[1][0]+1)*original_size,q[1][1]*original_size:(q[1][1]+1)*original_size] for q in imgs]
	batch_index = (batch_index+1)%max_counter
	return x,y