mask-rcnn训练自己的数据集

Posted 2023-02-14 ZealCV

import os
import sys
import random
import math
import re
import time
import numpy as np
import cv2
import matplotlib
import matplotlib.pyplot as plt
import yaml
from config import Config
import utils
import model as modellib
import visualize
from model import log

from PIL import Image

#%matplotlib inline 

# Root directory of the project
ROOT_DIR = os.getcwd()

# Directory to save logs and trained model
MODEL_DIR = os.path.join(ROOT_DIR, "logs")

# Local path to trained weights file
COCO_MODEL_PATH = os.path.join(ROOT_DIR, "mask_rcnn_coco.h5")
# Download COCO trained weights from Releases if needed
if not os.path.exists(COCO_MODEL_PATH):
    utils.download_trained_weights(COCO_MODEL_PATH)


################################################       Configurations        ###############################################    
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 + 3  # background + 3 class

    # 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 = 1024
    IMAGE_MAX_DIM = 1024

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

    # 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 = 2000

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

config = ShapesConfig()
config.display()
def get_ax(rows=1, cols=1, size=8):
    """Return a Matplotlib Axes array to be used in
    all visualizations in the notebook. Provide a
    central point to control graph sizes.

    Change the default size attribute to control the size
    of rendered images
    """
    _, ax = plt.subplots(rows, cols, figsize=(size*cols, size*rows))
    return ax

#############################################       Dataset Made By Self         #############################################
class DrugDataset(utils.Dataset):

    def get_obj_index(self, image):
        n =np.max(image)
        return n

    def from_yaml_get_class(self,image_id):
        info=self.image_info[image_id]
        with open(info['yaml_path']) as f:
            temp=yaml.load(f.read())
            labels=temp['label_names']
            del labels[0]
        return labels

    def draw_mask(self, num_obj, mask, image):
        info = self.image_info[image_id]
        for index in range(num_obj):
            for i in range(info['width']):
                for j in range(info['height']):
                    at_pixel = image.getpixel((i, j))
                    if at_pixel == index + 1:
                        mask[j, i, index] = 1
        return mask

    def load_shapes(self, count, height, width, img_floder, mask_floder, imglist,dataset_root_path):
        """Generate the requested number of images.
        count: number of images to generate.
        height, width: the size of the generated images.
        """
        # Add classes
        self.add_class("shapes", 1, "intersection_three")
        self.add_class("shapes", 2, "intersection_four")
        self.add_class("shapes", 3, "roundabout")
        for i in range(count):
            filestr = imglist[i].split(".")[0]
            #filestr = filestr.split("_")[1]
            mask_path = mask_floder + "/" + filestr + ".png"
            yaml_path = dataset_root_path + "json/" + filestr + "_json/info.yaml"
            self.add_image("shapes", image_id=i, path=img_floder + "/" + imglist[i],
                           width=width, height=height, mask_path=mask_path,yaml_path=yaml_path)

    def load_mask(self, image_id):
        """Generate instance masks for shapes of the given image ID.
        """
        info = self.image_info[image_id]
        count = 1  # number of object
        img = Image.open(info['mask_path'])
        num_obj = self.get_obj_index(img)
        mask = np.zeros([info['height'], info['width'], num_obj], dtype=np.uint8)

        mask = self.draw_mask(num_obj, mask, img)

        occlusion = np.logical_not(mask[:, :, -1]).astype(np.uint8)
        for i in range(count - 2, -1, -1):
            mask[:, :, i] = mask[:, :, i] * occlusion
            occlusion = np.logical_and(occlusion, np.logical_not(mask[:, :, i]))

        labels = []
        labels = self.from_yaml_get_class(image_id)
        labels_form = []
        for i in range(len(labels)):
            if labels[i].find("intersection_three") != -1:
                labels_form.append("intersection_three")
            elif labels[i].find("intersection_four") != -1:
                labels_form.append("intersection_four")
            elif labels[i].find("roundabout") != -1:
                labels_form.append("roundabout")
        class_ids = np.array([self.class_names.index(s) for s in labels_form])

        return mask, class_ids.astype(np.int32)

#基础设置
dataset_root_path = "E:/Road Testdata/coco/"
img_floder = dataset_root_path + "JPGImages"
mask_floder = dataset_root_path + "mask"
imglist = os.listdir(img_floder)
count = len(imglist)
width = 1024
height = 1024

# Training dataset
dataset_train = DrugDataset()
dataset_train.load_shapes(count, 1024, 1024, img_floder, mask_floder, imglist,dataset_root_path)
dataset_train.prepare()

# Validation dataset
dataset_val = DrugDataset()
dataset_val.load_shapes(count, 1024, 1024, img_floder, mask_floder, imglist,dataset_root_path)
dataset_val.prepare()

# Load and display random samples

image_ids = np.random.choice(dataset_train.image_ids, 4)

for image_id in image_ids:
    image = dataset_train.load_image(image_id)
    mask, class_ids = dataset_train.load_mask(image_id)
    #visualize.display_top_masks(image, mask, class_ids, dataset_train.class_names)

##################################################       Ceate Model     ##################################################
# Create model in training mode
model = modellib.MaskRCNN(mode="training", config=config, model_dir=MODEL_DIR)

# Which weights to start with?
init_with = "coco"  # imagenet, coco, or last

if init_with == "imagenet":
    model.load_weights(model.get_imagenet_weights(), by_name=True)
elif init_with == "coco":
    # Load weights trained on MS COCO, but skip layers that
    # are different due to the different number of classes
    # See README for instructions to download the COCO weights
    model.load_weights(COCO_MODEL_PATH, by_name=True,
                       exclude=["mrcnn_class_logits", "mrcnn_bbox_fc", 
                                "mrcnn_bbox", "mrcnn_mask"])
elif init_with == "last":
    # Load the last model you trained and continue training
    model.load_weights(model.find_last()[1], by_name=True)


##################################################       Training        ##################################################
# Train the head branches
# Passing layers="heads" freezes all layers except the head
# layers. You can also pass a regular expression to select
# which layers to train by name pattern.
model.train(dataset_train, dataset_val, 
            learning_rate=config.LEARNING_RATE, 
            epochs=1, 
            layers='heads')

# Fine tune all layers
# Passing layers="all" trains all layers. You can also 
# pass a regular expression to select which layers to
# train by name pattern.
model.train(dataset_train, dataset_val, 
            learning_rate=config.LEARNING_RATE / 10,
            epochs=2, 
            layers="all")

# Save weights,Typically not needed because callbacks save after every epoch,Uncomment to save manually
# model_path = os.path.join(MODEL_DIR, "mask_rcnn_shapes.h5")
# model.keras_model.save_weights(model_path)

##################################################       Detection       ##################################################
class InferenceConfig(ShapesConfig):
    GPU_COUNT = 1
    IMAGES_PER_GPU = 1

inference_config = InferenceConfig()

# Recreate the model in inference mode
model = modellib.MaskRCNN(mode="inference", config=inference_config,model_dir=MODEL_DIR)

# Get path to saved weights
# Either set a specific path or find last trained weights
# model_path = os.path.join(ROOT_DIR, ".h5 file name here")
model_path = model.find_last()[1]

# Load trained weights (fill in path to trained weights here)
assert model_path != "", "Provide path to trained weights"
print("Loading weights from ", model_path)
model.load_weights(model_path, by_name=True)

# Test on a random image
image_id = random.choice(dataset_val.image_ids)
original_image, image_meta, gt_class_id, gt_bbox, gt_mask =\\
    modellib.load_image_gt(dataset_val, inference_config, image_id, use_mini_mask=False)

log("original_image", original_image)
log("image_meta", image_meta)
log("gt_class_id", gt_class_id)
log("gt_bbox", gt_bbox)
log("gt_mask", gt_mask)

visualize.display_instances( original_image, gt_bbox, gt_mask, gt_class_id, dataset_train.class_names, figsize=(8, 8) )

results = model.detect([original_image], verbose=1)

r = results[0]
visualize.display_instances(original_image, r['rois'], r['masks'], r['class_ids'], 
                            dataset_val.class_names, r['scores'], ax=get_ax())


##################################################       Evaluation      ##################################################                 
# Compute VOC-Style mAP @ IoU=0.5
# Running on 10 images. Increase for better accuracy.
image_ids = np.random.choice(dataset_val.image_ids, 50)
APs = []
for image_id in image_ids:
    # Load image and ground truth data
    image, image_meta, gt_class_id, gt_bbox, gt_mask =\\
        modellib.load_image_gt(dataset_val, inference_config,image_id, use_mini_mask=False)
    molded_images = np.expand_dims(modellib.mold_image(image, inference_config), 0)
    # Run object detection
    results = model.detect([image], verbose=0)
    r = results[0]
    # Compute AP
    AP, precisions, recalls, overlaps =\\
        utils.compute_ap(gt_bbox, gt_class_id, gt_mask,r["rois"], r["class_ids"], r["scores"], r['masks'])
    APs.append(AP)

print("mAP: ", np.mean(APs))