[深度学习] TensorFlow上FCN模型验证

最新推荐文章于 2019-01-24 16:21:08 发布

LLM硬着陆

最新推荐文章于 2019-01-24 16:21:08 发布

阅读量2.1k

点赞数 2

分类专栏： Deep Learning 文章标签：全卷积网络 FCN Tensorflow 深度学习语义分割

本文链接：https://blog.csdn.net/weixin_41028208/article/details/83545941

版权

本文提供了一种简单的方法来验证全卷积网络（FCN）模型在TensorFlow上的效果，特别是对于语义分割任务。通过将图片放入指定文件夹并切换到可视化模式，可以对data_dir中的图像进行验证。

摘要由CSDN通过智能技术生成

针对 https://blog.csdn.net/weixin_41028208/article/details/81568310 中好多留言，不知道如何用自己的数据验证模型结果，我特意从原程序中摘出来了一个程序，用来验证data_dir中的图片

一个简单的办法，把图片放到valid_images里，然后改成visualize模式

from __future__ import print_function
import tensorflow as tf
import numpy as np
import os
import TensorflowUtils as utils
import read_MITSceneParsingData as scene_parsing
import datetime
import BatchDatsetReader as dataset
from six.moves import xrange
import matplotlib.pyplot as plt
import scipy.misc as misc
import cv2

FLAGS = tf.flags.FLAGS
tf.flags.DEFINE_integer("batch_size", "5", "batch size for training")
tf.flags.DEFINE_string("logs_dir", "logs/", "path to logs directory")
tf.flags.DEFINE_string("data_dir", "data/", "path to dataset")
tf.flags.DEFINE_string("output_dir", "output/", "path to output dir")
tf.flags.DEFINE_float("learning_rate", "1e-4", "Learning rate for Adam Optimizer")
tf.flags.DEFINE_string("model_dir", "model/", "Path to vgg model mat")
tf.flags.DEFINE_bool('debug', "False", "Debug mode: True/ False")

gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=1)

os.environ["CUDA_VISIBLE_DEVICES"] = '1' #use GPU with ID=1  

MODEL_URL = 'http://www.vlfeat.org/matconvnet/models/beta16/imagenet-vgg-verydeep-19.mat'

# 迭代的最大次数
MAX_ITERATION = int(1e5 + 1)
# 分类的个数
NUM_OF_CLASSESS = 151
# 图片尺寸
IMAGE_SIZE = 1000

# vgg_net：根据权重构建VGG网络
def vgg_net(weights, image):
    layers = (
        'conv1_1', 'relu1_1', 'conv1_2', 'relu1_2', 'pool1',
        'conv2_1', 'relu2_1', 'conv2_2', 'relu2_2', 'pool2',
        'conv3_1', 'relu3_1', 'conv3_2', 'relu3_2', 'conv3_3',
        'relu3_3', 'conv3_4', 'relu3_4', 'pool3',
        'conv4_1', 'relu4_1', 'conv4_2', 'relu4_2', 'conv4_3',
        'relu4_3', 'conv4_4', 'relu4_4', 'pool4',
        'conv5_1', 'relu5_1', 'conv5_2', 'relu5_2', 'conv5_3',
        'relu5_3', 'conv5_4', 'relu5_4'
    )

    net = {
   }
    current = image
    for i, name in enumerate(layers):
        kind = name[:4]
        if kind == 'conv':
            kernels, bias =