ckpt下载 deeplabv3_tensorflow语义分割api使用(deeplab训练cityscapes)

最新推荐文章于 2022-08-22 18:48:22 发布

weixin_39699313

最新推荐文章于 2022-08-22 18:48:22 发布

阅读量138

点赞数

文章标签： ckpt下载 deeplabv3

本文链接：https://blog.csdn.net/weixin_39699313/article/details/111802070

版权

本文档详细介绍了如何在TensorFlow1.8环境中，使用deeplabv3进行Cityscapes数据集的语义分割。内容包括环境配置、数据集转换、训练脚本、验证测试和可视化测试的步骤，以及遇到的问题和解决方案。通过转换Cityscapes数据集为TFRecords格式，并训练预定义的模型，最终得到训练和验证的miou_1.0指标。

摘要由CSDN通过智能技术生成

遇到的坑：

1. 环境：

- tensorflow1.8+CUDA9.0+cudnn7.0+annaconda3+py3.5

- 使用最新的tensorflow1.12或者1.10都不行，报错：报错不造卷积算法(convolution algorithm...)

2. 数据集转换

#Exit immediately if a command exits with a non-zero status.

set -e

CURRENT_DIR=$(pwd)

WORK_DIR="."

#Root path for Cityscapes dataset.

CITYSCAPES_ROOT="${WORK_DIR}/cityscapes"

#Create training labels.

python "${CITYSCAPES_ROOT}/cityscapesscripts/preparation/createTrainIdLabelImgs.py"

#Build TFRecords of the dataset.#First, create output directory for storing TFRecords.

OUTPUT_DIR="${CITYSCAPES_ROOT}/tfrecord"mkdir-p "${OUTPUT_DIR}"BUILD_SCRIPT="${CURRENT_DIR}/build_cityscapes_data.py"echo"Converting Cityscapes dataset..."python"${BUILD_SCRIPT}"\--cityscapes_root="${CITYSCAPES_ROOT}"\--output_dir="${OUTPUT_DIR}" \

- 首先当前conda环境下安装cityscapesScripts模块，要支持py3.5才行；

- 由于cityscapesscripts/preparation/createTrainIdLabelImgs.py里面默认会把数据集gtFine下面的test,train,val文件夹json文件都转为TrainIdlandelImgs.png;然而在test文件下有很多json文件编码格式是错误的，大约十几张，每次报错，然后将其剔除！！！

- 然后执行build_cityscapes_data.py将img,lable转换为tfrecord格式。

3. 训练cityscapes代码

- 将训练代码写成脚本文件：train_deeplab_cityscapes.sh

#!/bin/bash

#CUDA_VISIBLE_DEVICES=0,1,2,3 python train.py --backbone resnet --lr 0.01 --workers 4 --epochs 40 --batch-size 16 --gpu-ids 0,1,2,3 --checkname deeplab-resnet --eval-interval 1 --dataset coco

PATH_TO_INITIAL_CHECKPOINT='/home/rjw/tf-models/research/deeplab/pretrain_models/deeplabv3_cityscapes_train/model.ckpt'PATH_TO_TRAIN_DIR='/home/rjw/tf-models/research/deeplab/datasets/cityscapes/exp/train_on_train_set/train/'PATH_TO_DATASET='/home/rjw/tf-models/research/deeplab/datasets/cityscapes/tfrecord'WORK_DIR='/home/rjw/tf-models/research/deeplab'

#From tensorflow/models/research/

python "${WORK_DIR}"/train.py \--logtostderr \--training_number_of_steps=40000\--train_split="train"\--model_variant="xception_65"\--atrous_rates=6\--atrous_rates=12\--atrous_rates=18\--output_stride=16\--decoder_output_stride=4\--train_crop_size=513\--train_crop_size=513\--train_batch_size=1\--fine_tune_batch_norm=False \--dataset="cityscapes"\--tf_initial_checkpoint=${PATH_TO_INITIAL_CHECKPOINT} \--train_logdir=${PATH_TO_TRAIN_DIR} \--dataset_dir=${PATH_TO_DATASET}

参数分析：

training_number_of_steps：训练迭代次数；

train_crop_size：训练图片的裁剪大小，因为我的GPU只有8G，故我将这个设置为513了；

train_batch_size: 训练的batchsize，也是因为硬件条件，故保持1；

fine_tune_batch_norm=False ：是否使用batch_norm，官方建议，如果训练的batch_size小于12的话，须将该参数设置为False，这个设置很重要，否则的话训练时会在2000步左右报错

tf_initial_checkpoint：预训练的初始checkpoint，这里设置的即是前面下载的../research/deeplab/backbone/deeplabv3_cityscapes_train/model.ckpt.index

train_logdir: 保存训练权重的目录，注意在开始的创建工程目录的时候就创建了，这里设置为"../research/deeplab/exp/train_on_train_set/train/"

dataset_dir:数据集的地址，前面创建的TFRecords目录。这里设置为"../dataset/cityscapes/tfrecord"

4.验证测试

- 验证脚本：

#!/bin/bash

#CUDA_VISIBLE_DEVICES=0,1,2,3 python train.py --backbone resnet --lr 0.01 --workers 4 --epochs 40 --batch-size 16 --gpu-ids 0,1,2,3 --checkname deeplab-resnet --eval-interval 1 --dataset coco

PATH_TO_INITIAL_CHECKPOINT='/home/rjw/tf-models/research/deeplab/pretrain_models/deeplabv3_cityscapes_train/'PATH_TO_CHECKPOINT='/home/rjw/tf-models/research/deeplab/datasets/cityscapes/exp/train_on_train_set/train/'PATH_TO_EVAL_DIR='/home/rjw/tf-models/research/deeplab/datasets/cityscapes/exp/train_on_train_set/eval/'PATH_TO_DATASET='/home/rjw/tf-models/research/deeplab/datasets/cityscapes/tfrecord'WORK_DIR='/home/rjw/tf-models/research/deeplab'

#From tensorflow/models/research/

python "${WORK_DIR}"/eval.py \--logtostderr \--eval_split="val"\--model_variant="xception_65"\--atrous_rates=6\--atrous_rates=12\--atrous_rates=18\--output_stride=16\--decoder_output_stride=4\--eval_crop_size=1025\--eval_crop_size=2049\--dataset="cityscapes"\--checkpoint_dir=${PATH_TO_INITIAL_CHECKPOINT} \--eval_logdir=${PATH_TO_EVAL_DIR} \--dataset_dir=${PATH_TO_DATASET}

- rusult:model.ckpt-40000为在初始化模型上训练40000次迭代的模型；后面用初始化模型测试miou_1.0还是很低，不知道是不是有什么参数设置的问题！！！

- 注意，如果使用官方提供的checkpoint，压缩包中是没有checkpoint文件的，需要手动添加一个checkpoint文件；初始化模型中是没有提供chekpoint文件的。

INFO:tensorflow:Restoring parameters from /home/rjw/tf-models/research/deeplab/datasets/cityscapes/exp/train_on_train_set/train/model.ckpt-40000INFO:tensorflow:Running local_init_op.

INFO:tensorflow:Done running local_init_op.

INFO:tensorflow:Starting evaluation at2018-12-18-07:13:08INFO:tensorflow:Evaluation [50/500]

INFO:tensorflow:Evaluation [100/500]

INFO:tensorflow:Evaluation [150/500]

INFO:tensorflow:Evaluation [200/500]

INFO:tensorflow:Evaluation [250/500]

INFO:tensorflow:Evaluation [300/500]

INFO:tensorflow:Evaluation [350/500]

INFO:tensorflow:Evaluation [400/500]

INFO:tensorflow:Evaluation [450/500]

miou_1.0[0.478293568]

INFO:tensorflow:Waitingfor new checkpoint at /home/rjw/tf-models/research/deeplab/pretrain_models/deeplabv3_cityscapes_train/INFO:tensorflow:Found new checkpoint at/home/rjw/tf-models/research/deeplab/pretrain_models/deeplabv3_cityscapes_train/model.ckpt

INFO:tensorflow:Graph was finalized.2018-12-18 15:18:05.210957: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1435] Adding visible gpu devices: 02018-12-18 15:18:05.211047: I tensorflow/core/common_runtime/gpu/gpu_device.cc:923] Device interconnect StreamExecutor with strength 1edge matrix:2018-12-18 15:18:05.211077: I tensorflow/core/common_runtime/gpu/gpu_device.cc:929] 02018-12-18 15:18:05.211100: I tensorflow/core/common_runtime/gpu/gpu_device.cc:942] 0: N2018-12-18 15:18:05.211645: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1053] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9404 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1080 Ti, pci bus id: 0000:01:00.0, compute capability: 6.1)

INFO:tensorflow:Restoring parametersfrom /home/rjw/tf-models/research/deeplab/pretrain_models/deeplabv3_cityscapes_train/model.ckpt

INFO:tensorflow:Running local_init_op.

INFO:tensorflow:Done running local_init_op.

INFO:tensorflow:Starting evaluation at2018-12-18-07:18:06INFO:tensorflow:Evaluation [50/500]

INFO:tensorflow:Evaluation [100/500]

INFO:tensorflow:Evaluation [150/500]

INFO:tensorflow:Evaluation [200/500]

INFO:tensorflow:Evaluation [250/500]

INFO:tensorflow:Evaluation [300/500]

INFO:tensorflow:Evaluation [350/500]

INFO:tensorflow:Evaluation [400/500]

INFO:tensorflow:Evaluation [450/500]

miou_1.0[0.496331513]

5.可视化测试

- 在vis目录下生成分割结果图

#!/bin/bash

#CUDA_VISIBLE_DEVICES=0,1,2,3 python train.py --backbone resnet --lr 0.01 --workers 4 --epochs 40 --batch-size 16 --gpu-ids 0,1,2,3 --checkname deeplab-resnet --eval-interval 1 --dataset coco

PATH_TO_CHECKPOINT='/home/rjw/tf-models/research/deeplab/datasets/cityscapes/exp/train_on_train_set/train/'PATH_TO_VIS_DIR='/home/rjw/tf-models/research/deeplab/datasets/cityscapes/exp/train_on_train_set/vis/'PATH_TO_DATASET='/home/rjw/tf-models/research/deeplab/datasets/cityscapes/tfrecord'WORK_DIR='/home/rjw/tf-models/research/deeplab'

#From tensorflow/models/research/

python "${WORK_DIR}"/vis.py \--logtostderr \--vis_split="val"\--model_variant="xception_65"\--atrous_rates=6\--atrous_rates=12\--atrous_rates=18\--output_stride=16\--decoder_output_stride=4\--vis_crop_size=1025\--vis_crop_size=2049\--dataset="cityscapes"\--colormap_type="cityscapes"\--checkpoint_dir=${PATH_TO_CHECKPOINT} \--vis_logdir=${PATH_TO_VIS_DIR} \--dataset_dir=${PATH_TO_DATASET}

reference：

weixin_39699313

关注

0
点赞
踩
0

收藏

觉得还不错? 一键收藏
0
评论
ckpt下载 deeplabv3_tensorflow语义分割api使用(deeplab训练cityscapes)

遇到的坑：1. 环境：- tensorflow1.8+CUDA9.0+cudnn7.0+annaconda3+py3.5- 使用最新的tensorflow1.12或者1.10都不行，报错：报错不造卷积算法(convolution algorithm...)2. 数据集转换#Exit immediately if a command exits with a non-zero status.set ...
复制链接

扫一扫