数据集目录结构(在train_data目录下)：
pic目录下的部分图片：
cv2_mask目录下部分图片：
json目录下部分文件：
labelme_json目录下部分文件：
代码块一
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
from config import Config
import utils
import model as modellib
import visualize
import yaml
from model import log
from PIL import Image
iter_num=0
# 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)
代码块2
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
# 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 = 80
IMAGE_MAX_DIM = 512
# 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
—————————————-
#输出：
Configurations: BACKBONE resnet101 BACKBONE_STRIDES [4, 8, 16, 32, 64] BATCH_SIZE 1 BBOX_STD_DEV [0.1 0.1 0.2 0.2] COMPUTE_BACKBONE_SHAPE None DETECTION_MAX_INSTANCES 100 DETECTION_MIN_CONFIDENCE 0.7 DETECTION_NMS_THRESHOLD 0.3 FPN_CLASSIF_FC_LAYERS_SIZE 1024 GPU_COUNT 1 GRADIENT_CLIP_NORM 5.0 IMAGES_PER_GPU 1 IMAGE_MAX_DIM 512 IMAGE_META_SIZE 14 IMAGE_MIN_DIM 80 IMAGE_MIN_SCALE 0 IMAGE_RESIZE_MODE square IMAGE_SHAPE [512 512 3] LEARNING_MOMENTUM 0.9 LEARNING_RATE 0.001 LOSS_WEIGHTS {‘rpn_class_loss’: 1.0, ‘rpn_bbox_loss’: 1.0, ‘mrcnn_class_loss’: 1.0, ‘mrcnn_bbox_loss’: 1.0, ‘mrcnn_mask_loss’: 1.0} MASK_POOL_SIZE 14 MASK_SHAPE [28, 28] MAX_GT_INSTANCES 100 MEAN_PIXEL [123.7 116.8 103.9] MINI_MASK_SHAPE (56, 56) NAME shapes NUM_CLASSES 2 POOL_SIZE 7 POST_NMS_ROIS_INFERENCE 1000 POST_NMS_ROIS_TRAINING 2000 ROI_POSITIVE_RATIO 0.33 RPN_ANCHOR_RATIOS [0.5, 1, 2] RPN_ANCHOR_SCALES (48, 96, 192, 384, 768) RPN_ANCHOR_STRIDE 1 RPN_BBOX_STD_DEV [0.1 0.1 0.2 0.2] RPN_NMS_THRESHOLD 0.7 RPN_TRAIN_ANCHORS_PER_IMAGE 256 STEPS_PER_EPOCH 100 TOP_DOWN_PYRAMID_SIZE 256 TRAIN_BN False TRAIN_ROIS_PER_IMAGE 32 USE_MINI_MASK True USE_RPN_ROIS True VALIDATION_STEPS 5 WEIGHT_DECAY 0.0001
讯享网
——————————————-
代码块三#
class DrugDataset(utils.Dataset):
# 得到该图中有多少个实例（物体）
def get_obj_index(self, image):
n = np.max(image)
return n
# 解析labelme中得到的yaml文件，从而得到mask每一层对应的实例标签
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
# 重新写draw_mask
def draw_mask(self, num_obj, mask, image,image_id):
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
# 重新写load_shapes，里面包含自己的自己的类别
def load_shapes(self, count, img_floder, mask_floder, imglist, dataset_root_path):
”““Generate the requested number of synthetic images.
count: number of images to generate.
height, width: the size of the generated images.
”“”
# Add classes
self.addclass(“shapes”, 1, “box”) # box
for i in range(count):
# 获取图片宽和高
filestr = imglist[i].split(“.”)[0]
# filestr = filestr.split(””)[1]
mask_path = mask_floder + “/” + filestr + “.png”
yaml_path = dataset_root_path + “labelme_json/” + filestr + “-box_json/info.yaml”
print(dataset_root_path + “labelme_json/” + filestr + “-box_json/img.png”)
cv_img = cv2.imread(dataset_root_path + “labelme_json/” + filestr + “-box_json/img.png”)
self.add_image(“shapes”, image_id=i, path=img_floder + “/” + imglist[i],width=cv_img.shape[1], height=cv_img.shape[0], mask_path=mask_path, yaml_path=yaml_path)
# 重写load_mask
def load_mask(self, image_id):
”““Generate instance masks for shapes of the given image ID.”“”
global iter_num
print(“image_id”,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,image_id)
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(“box”) != -1:
# print “box”
labels_form.append(“box”)
class_ids = np.array([self.class_names.index(s) for s in labels_form])
return mask, class_ids.astype(np.int32)
#代码块四
def getax(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
代码块五
#基础设置
dataset_root_path=“train_data/”
img_floder = dataset_root_path + “pic”
mask_floder = dataset_root_path + “cv2_mask”
#yaml_floder = dataset_root_path
imglist = os.listdir(img_floder)
count = len(imglist)
#train与val数据集准备
dataset_train = DrugDataset()
dataset_train.load_shapes(count, img_floder, mask_floder, imglist,dataset_root_path)
dataset_train.prepare()
#print(“dataset_train–>”,dataset_train._image_ids)
dataset_val = DrugDataset()
dataset_val.load_shapes(10, img_floder, mask_floder, imglist,dataset_root_path)
dataset_val.prepare()
—————————————–
输出：
讯享网train_data/labelme_json/0-box_json/img.png train_data/labelme_json/1-box_json/img.png train_data/labelme_json/10-box_json/img.png train_data/labelme_json/100-box_json/img.png train_data/labelme_json/101-box_json/img.png train_data/labelme_json/102-box_json/img.png train_data/labelme_json/103-box_json/img.png train_data/labelme_json/104-box_json/img.png train_data/labelme_json/105-box_json/img.png train_data/labelme_json/106-box_json/img.png train_data/labelme_json/107-box_json/img.png train_data/labelme_json/108-box_json/img.png train_data/labelme_json/109-box_json/img.png train_data/labelme_json/11-box_json/img.png train_data/labelme_json/110-box_json/img.png train_data/labelme_json/111-box_json/img.png train_data/labelme_json/112-box_json/img.png train_data/labelme_json/113-box_json/img.png train_data/labelme_json/114-box_json/img.png train_data/labelme_json/115-box_json/img.png train_data/labelme_json/116-box_json/img.png train_data/labelme_json/117-box_json/img.png train_data/labelme_json/118-box_json/img.png train_data/labelme_json/119-box_json/img.png train_data/labelme_json/12-box_json/img.png train_data/labelme_json/120-box_json/img.png train_data/labelme_json/121-box_json/img.png train_data/labelme_json/122-box_json/img.png train_data/labelme_json/123-box_json/img.png train_data/labelme_json/124-box_json/img.png train_data/labelme_json/125-box_json/img.png train_data/labelme_json/126-box_json/img.png train_data/labelme_json/127-box_json/img.png train_data/labelme_json/128-box_json/img.png train_data/labelme_json/129-box_json/img.png train_data/labelme_json/13-box_json/img.png train_data/labelme_json/130-box_json/img.png train_data/labelme_json/131-box_json/img.png
………………..train_data/labelme_json/101-box_json/img.pngtrain_data/labelme_json/102-box_json/img.png
train_data/labelme_json/103-box_json/img.png train_data/labelme_json/104-box_json/img.png train_data/labelme_json/105-box_json/img.png train_data/labelme_json/106-box_json/img.png
代码块六
# Load and display random samples
image_ids = np.random.choice(dataset_train.image_ids, 10)
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)
————————————-
输出：
代码块七
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)
# 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’)
———————————————————-
输出：
代码块八
# 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=1,
layers=“all”)
———————————————————-
输出：
讯享网Starting at epoch 1. LR=0.0001Checkpoint Path: G:TensorflowProjectMask_RCNN-mastersamples0820shapeslogsshapesT1503mask_rcnnshapes{epoch:04d}.h5 Selecting layers to train conv1 (Conv2D) bn_conv1 (BatchNorm) res2a_branch2a (Conv2D) bn2a_branch2a (BatchNorm) res2a_branch2b (Conv2D) bn2a_branch2b (BatchNorm) res2a_branch2c (Conv2D) res2a_branch1 (Conv2D) bn2a_branch2c (BatchNorm) bn2a_branch1 (BatchNorm) res2b_branch2a (Conv2D) bn2b_branch2a (BatchNorm) res2b_branch2b (Conv2D) bn2b_branch2b (BatchNorm) res2b_branch2c (Conv2D) bn2b_branch2c (BatchNorm) res2c_branch2a (Conv2D) bn2c_branch2a (BatchNorm) res2c_branch2b (Conv2D) bn2c_branch2b (BatchNorm) res2c_branch2c (Conv2D) bn2c_branch2c (BatchNorm) res3a_branch2a (Conv2D) bn3a_branch2a (BatchNorm) res3a_branch2b (Conv2D) bn3a_branch2b (BatchNorm) res3a_branch2c (Conv2D) res3a_branch1 (Conv2D) bn3a_branch2c (BatchNorm) bn3a_branch1 (BatchNorm) res3b_branch2a (Conv2D) bn3b_branch2a (BatchNorm) res3b_branch2b (Conv2D) bn3b_branch2b (BatchNorm) res3b_branch2c (Conv2D) bn3b_branch2c (BatchNorm) res3c_branch2a (Conv2D) bn3c_branch2a (BatchNorm) res3c_branch2b (Conv2D) bn3c_branch2b (BatchNorm) res3c_branch2c (Conv2D) bn3c_branch2c (BatchNorm) res3d_branch2a (Conv2D) bn3d_branch2a (BatchNorm) res3d_branch2b (Conv2D) bn3d_branch2b (BatchNorm) res3d_branch2c (Conv2D) bn3d_branch2c (BatchNorm) res4a_branch2a (Conv2D) bn4a_branch2a (BatchNorm) res4a_branch2b (Conv2D) bn4a_branch2b (BatchNorm) res4a_branch2c (Conv2D) res4a_branch1 (Conv2D) bn4a_branch2c (BatchNorm) bn4a_branch1 (BatchNorm) res4b_branch2a (Conv2D) bn4b_branch2a (BatchNorm) res4b_branch2b (Conv2D) bn4b_branch2b (BatchNorm) res4b_branch2c (Conv2D) bn4b_branch2c (BatchNorm) res4c_branch2a (Conv2D) bn4c_branch2a (BatchNorm) res4c_branch2b (Conv2D) bn4c_branch2b (BatchNorm) res4c_branch2c (Conv2D) bn4c_branch2c (BatchNorm) res4d_branch2a (Conv2D) bn4d_branch2a (BatchNorm) res4d_branch2b (Conv2D) bn4d_branch2b (BatchNorm) res4d_branch2c (Conv2D) bn4d_branch2c (BatchNorm) res4e_branch2a (Conv2D) bn4e_branch2a (BatchNorm) res4e_branch2b (Conv2D) bn4e_branch2b (BatchNorm) res4e_branch2c (Conv2D) bn4e_branch2c (BatchNorm) res4f_branch2a (Conv2D) bn4f_branch2a (BatchNorm) res4f_branch2b (Conv2D) bn4f_branch2b (BatchNorm) res4f_branch2c (Conv2D) bn4f_branch2c (BatchNorm) res4g_branch2a (Conv2D) bn4g_branch2a (BatchNorm) res4g_branch2b (Conv2D) bn4g_branch2b (BatchNorm) res4g_branch2c (Conv2D) bn4g_branch2c (BatchNorm) res4h_branch2a (Conv2D) bn4h_branch2a (BatchNorm) res4h_branch2b (Conv2D) bn4h_branch2b (BatchNorm) res4h_branch2c (Conv2D) bn4h_branch2c (BatchNorm) res4i_branch2a (Conv2D) bn4i_branch2a (BatchNorm) res4i_branch2b (Conv2D) bn4i_branch2b (BatchNorm) res4i_branch2c (Conv2D) bn4i_branch2c (BatchNorm) res4j_branch2a (Conv2D) bn4j_branch2a (BatchNorm) res4j_branch2b (Conv2D) bn4j_branch2b (BatchNorm) res4j_branch2c (Conv2D) bn4j_branch2c (BatchNorm) res4k_branch2a (Conv2D) bn4k_branch2a (BatchNorm) res4k_branch2b (Conv2D) bn4k_branch2b (BatchNorm) res4k_branch2c (Conv2D) bn4k_branch2c (BatchNorm) res4l_branch2a (Conv2D) bn4l_branch2a (BatchNorm) res4l_branch2b (Conv2D) bn4l_branch2b (BatchNorm) res4l_branch2c (Conv2D) bn4l_branch2c (BatchNorm) res4m_branch2a (Conv2D) bn4m_branch2a (BatchNorm) res4m_branch2b (Conv2D) bn4m_branch2b (BatchNorm) res4m_branch2c (Conv2D) bn4m_branch2c (BatchNorm) res4n_branch2a (Conv2D) bn4n_branch2a (BatchNorm) res4n_branch2b (Conv2D) bn4n_branch2b (BatchNorm) res4n_branch2c (Conv2D) bn4n_branch2c (BatchNorm) res4o_branch2a (Conv2D) bn4o_branch2a (BatchNorm) res4o_branch2b (Conv2D) bn4o_branch2b (BatchNorm) res4o_branch2c (Conv2D) bn4o_branch2c (BatchNorm) res4p_branch2a (Conv2D) bn4p_branch2a (BatchNorm) res4p_branch2b (Conv2D) bn4p_branch2b (BatchNorm) res4p_branch2c (Conv2D) bn4p_branch2c (BatchNorm) res4q_branch2a (Conv2D) bn4q_branch2a (BatchNorm) res4q_branch2b (Conv2D) bn4q_branch2b (BatchNorm) res4q_branch2c (Conv2D) bn4q_branch2c (BatchNorm) res4r_branch2a (Conv2D) bn4r_branch2a (BatchNorm) res4r_branch2b (Conv2D) bn4r_branch2b (BatchNorm) res4r_branch2c (Conv2D) bn4r_branch2c (BatchNorm) res4s_branch2a (Conv2D) bn4s_branch2a (BatchNorm) res4s_branch2b (Conv2D) bn4s_branch2b (BatchNorm) res4s_branch2c (Conv2D) bn4s_branch2c (BatchNorm) res4t_branch2a (Conv2D) bn4t_branch2a (BatchNorm) res4t_branch2b (Conv2D) bn4t_branch2b (BatchNorm) res4t_branch2c (Conv2D) bn4t_branch2c (BatchNorm) res4u_branch2a (Conv2D) bn4u_branch2a (BatchNorm) res4u_branch2b (Conv2D) bn4u_branch2b (BatchNorm) res4u_branch2c (Conv2D) bn4u_branch2c (BatchNorm) res4v_branch2a (Conv2D) bn4v_branch2a (BatchNorm) res4v_branch2b (Conv2D) bn4v_branch2b (BatchNorm) res4v_branch2c (Conv2D) bn4v_branch2c (BatchNorm) res4w_branch2a (Conv2D) bn4w_branch2a (BatchNorm) res4w_branch2b (Conv2D) bn4w_branch2b (BatchNorm) res4w_branch2c (Conv2D) bn4w_branch2c (BatchNorm) res5a_branch2a (Conv2D) bn5a_branch2a (BatchNorm) res5a_branch2b (Conv2D) bn5a_branch2b (BatchNorm) res5a_branch2c (Conv2D) res5a_branch1 (Conv2D) bn5a_branch2c (BatchNorm) bn5a_branch1 (BatchNorm) res5b_branch2a (Conv2D) bn5b_branch2a (BatchNorm) res5b_branch2b (Conv2D) bn5b_branch2b (BatchNorm) res5b_branch2c (Conv2D) bn5b_branch2c (BatchNorm) res5c_branch2a (Conv2D) bn5c_branch2a (BatchNorm) res5c_branch2b (Conv2D) bn5c_branch2b (BatchNorm) res5c_branch2c (Conv2D) bn5c_branch2c (BatchNorm) fpn_c5p5 (Conv2D) fpn_c4p4 (Conv2D) fpn_c3p3 (Conv2D) fpn_c2p2 (Conv2D) fpn_p5 (Conv2D) fpn_p2 (Conv2D) fpn_p3 (Conv2D) fpn_p4 (Conv2D) In model: rpn_modelrpn_conv_shared (Conv2D) rpn_class_raw (Conv2D) rpn_bbox_pred (Conv2D)mrcnn_mask_conv1 (TimeDistributed) mrcnn_mask_bn1 (TimeDistributed) mrcnn_mask_conv2 (TimeDistributed) mrcnn_mask_bn2 (TimeDistributed) mrcnn_class_conv1 (TimeDistributed) mrcnn_class_bn1 (TimeDistributed) mrcnn_mask_conv3 (TimeDistributed) mrcnn_mask_bn3 (TimeDistributed) mrcnn_class_conv2 (TimeDistributed) mrcnn_class_bn2 (TimeDistributed) mrcnn_mask_conv4 (TimeDistributed) mrcnn_mask_bn4 (TimeDistributed) mrcnn_bbox_fc (TimeDistributed) mrcnn_mask_deconv (TimeDistributed) mrcnn_class_logits (TimeDistributed) mrcnn_mask (TimeDistributed)
讯享网
版权声明：本文内容由互联网用户自发贡献，该文观点仅代表作者本人。本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容，请联系我们，一经查实，本站将立刻删除。
如需转载请保留出处：https://51itzy.com/kjqy/207523.html