使用深度学习检测疟疾(3)

这些图片尺寸并不相同，因为血涂片和细胞图像是基于人、测试方法、图片方向不同而不同的。让我们总结我们的训练数据集的统计信息来决定最佳的图像尺寸（牢记，我们根本不会碰测试数据集）。

import cv2
from concurrent import futures
import threading
 
def get_img_shape_parallel(idx, img, total_imgs):
    if idx % 5000 == 0 or idx == (total_imgs - 1):
        print('{}: working on img num: {}'.format(threading.current_thread().name,
                                                  idx))
    return cv2.imread(img).shape
  
ex = futures.ThreadPoolExecutor(max_workers=None)
data_inp = [(idx, img, len(train_files)) for idx, img in enumerate(train_files)]
print('Starting Img shape computation:')
train_img_dims_map = ex.map(get_img_shape_parallel, 
                            [record[0] for record in data_inp],
                            [record[1] for record in data_inp],
                            [record[2] for record in data_inp])
train_img_dims = list(train_img_dims_map)
print('Min Dimensions:', np.min(train_img_dims, axis=0)) 
print('Avg Dimensions:', np.mean(train_img_dims, axis=0))
print('Median Dimensions:', np.median(train_img_dims, axis=0))
print('Max Dimensions:', np.max(train_img_dims, axis=0))
 
 
# Output
Starting Img shape computation:
ThreadPoolExecutor-0_0: working on img num: 0
ThreadPoolExecutor-0_17: working on img num: 5000
ThreadPoolExecutor-0_15: working on img num: 10000
ThreadPoolExecutor-0_1: working on img num: 15000
ThreadPoolExecutor-0_7: working on img num: 17360
Min Dimensions: [46 46  3]
Avg Dimensions: [132.77311215 132.45757733   3.]
Median Dimensions: [130. 130.   3.]
Max Dimensions: [385 394   3]

我们应用并行处理来加速图像读取，并且基于汇总统计结果，我们将每幅图片的尺寸重新调整到 125x125 像素。让我们载入我们所有的图像并重新调整它们为这些固定尺寸。

IMG_DIMS = (125, 125)
 
def get_img_data_parallel(idx, img, total_imgs):
    if idx % 5000 == 0 or idx == (total_imgs - 1):
        print('{}: working on img num: {}'.format(threading.current_thread().name,
                                                  idx))
    img = cv2.imread(img)
    img = cv2.resize(img, dsize=IMG_DIMS, 
                     interpolation=cv2.INTER_CUBIC)
    img = np.array(img, dtype=np.float32)
    return img
 
ex = futures.ThreadPoolExecutor(max_workers=None)
train_data_inp = [(idx, img, len(train_files)) for idx, img in enumerate(train_files)]
val_data_inp = [(idx, img, len(val_files)) for idx, img in enumerate(val_files)]
test_data_inp = [(idx, img, len(test_files)) for idx, img in enumerate(test_files)]
 
print('Loading Train Images:')
train_data_map = ex.map(get_img_data_parallel, 
                        [record[0] for record in train_data_inp],
                        [record[1] for record in train_data_inp],
                        [record[2] for record in train_data_inp])
train_data = np.array(list(train_data_map))
 
print('\nLoading Validation Images:')
val_data_map = ex.map(get_img_data_parallel, 
                        [record[0] for record in val_data_inp],
                        [record[1] for record in val_data_inp],
                        [record[2] for record in val_data_inp])
val_data = np.array(list(val_data_map))
 
print('\nLoading Test Images:')
test_data_map = ex.map(get_img_data_parallel, 
                        [record[0] for record in test_data_inp],
                        [record[1] for record in test_data_inp],
                        [record[2] for record in test_data_inp])
test_data = np.array(list(test_data_map))
 
train_data.shape, val_data.shape, test_data.shape  
 
 
# Output
Loading Train Images:
ThreadPoolExecutor-1_0: working on img num: 0
ThreadPoolExecutor-1_12: working on img num: 5000
ThreadPoolExecutor-1_6: working on img num: 10000
ThreadPoolExecutor-1_10: working on img num: 15000
ThreadPoolExecutor-1_3: working on img num: 17360
 
Loading Validation Images:
ThreadPoolExecutor-1_13: working on img num: 0
ThreadPoolExecutor-1_18: working on img num: 1928
 
Loading Test Images:
ThreadPoolExecutor-1_5: working on img num: 0
ThreadPoolExecutor-1_19: working on img num: 5000
ThreadPoolExecutor-1_8: working on img num: 8267
((17361, 125, 125, 3), (1929, 125, 125, 3), (8268, 125, 125, 3))

（编辑：ASP站长网）