Mask-RCNN程式碼Mask_RCNN/samples路徑下有一個demo.ipynb的檔案就是用來測試的，所以我們在這個基礎上更改一下，其實主要就是我們新建一個test.ipynb，然後把demo.ipynb程式碼複製過來，根據需要更改。

一、將demo程式碼更改

將demo中的程式碼

COCO_MODEL_PATH = os.path.join(ROOT_DIR, "mask_rcnn_coco.h5")

更改為：這裡面的h5檔案是我們訓練的結果，

COCO_MODEL_PATH = os.path.join(ROOT_DIR, "mask_rcnn_shapes_0005.h5")
 

demo中程式碼class InferenceConfig(coco.CocoConfig):也需要進行更改，要與自己的config匹配。

class InferenceConfig(shapeconfig.ShapesConfig):

ShapesConfig類中程式碼：

from mrcnn.config import Config
class ShapesConfig(Config):
    """Configuration for training on the toy shapes dataset.
    Derives from the base Config class and overrides values specific
    to the toy shapes dataset.
    """
    # Give the configuration a recognizable name
    NAME = "shapes"

    # Train on 1 GPU and 8 images per GPU. We can put multiple images on each
    # GPU because the images are small. Batch size is 8 (GPUs * images/GPU).
    GPU_COUNT = 1
    IMAGES_PER_GPU = 1

    # Number of classes (including background)
    NUM_CLASSES = 1 + 1 # background + 3 shapes

    # Use small images for faster training. Set the limits of the small side
    # the large side, and that determines the image shape.
    IMAGE_MIN_DIM = 448
    IMAGE_MAX_DIM = 640

    # Use smaller anchors because our image and objects are small
    #RPN_ANCHOR_SCALES = (8, 16, 32, 64, 128)  # anchor side in pixels
    RPN_ANCHOR_SCALES = (8 * 6, 16 * 6, 32 * 6, 64 * 6, 128 * 6)

    # Reduce training ROIs per image because the images are small and have
    # few objects. Aim to allow ROI sampling to pick 33% positive ROIs.
    TRAIN_ROIS_PER_IMAGE = 32

    # Use a small epoch since the data is simple
    STEPS_PER_EPOCH = 100

    # use small validation steps since the epoch is small
    VALIDATION_STEPS = 5
 

二、注意

IMAGE_MIN_DIM = 448

 IMAGE_MAX_DIM = 640

是圖片的尺寸。（按照自己圖片的大小更改）

值得注意的是，Mask_RCNN/mrcnn目錄下model.py檔案中第1815行到1819行程式碼

h, w = config.IMAGE_SHAPE[:2]
        if h / 2**6 != int(h / 2**6) or w / 2**6 != int(w / 2**6):
            raise Exception("Image size must be dividable by 2 at least 6 times "
                            "to avoid fractions when downscaling and upscaling."
                            "For example, use 256, 320, 384, 448, 512, ... etc. ")
 

需要注意圖片尺寸的設定最好符合標準，不然會報錯。

三、批量儲存

這樣我們初步可以測試了，但是隻能在ipython中一張圖片一張圖片的測試，且是從images路徑下隨機取值。

所以我們需要更改程式碼，獲取images資料夾下圖片的張數，作為索引，在test.ipynb檔案中更改為如下程式碼：

count = os.listdir(IMAGE_DIR)
for i in range(0,len(count)):
    path = os.path.join(IMAGE_DIR, count[i])
    if os.path.isfile(path):
        file_names = next(os.walk(IMAGE_DIR))[2]
        image = skimage.io.imread(os.path.join(IMAGE_DIR, count[i]))
        # Run detection
        results = model.detect([image], verbose=1)
        r = results[0]
        visualize.display_instances(count[i],image, r['rois'], r['masks'], r['class_ids'], 
                            class_names, r['scores'])

這時，需要到visualize.py檔案中更改，在Mask_RCNN/mrcnn路徑下找到該檔案開啟，更改display_instances類程式碼，在該類中新增一個引數count，並加上plt.savefig()儲存圖片到指定路徑下：

if auto_show:
        plt.savefig("./test_results/%3s.jpg"%(str(count[4:7])))
        plt.show()

圖片命名方式是取被測試圖片的第4-7位（我的4-7位是數字）命名。（根據需要可自己改）

四、儲存結果

在test_results資料夾中可以正常顯示。