mmclassification数据集并训练

mmclassification数据集并训练

1.数据集准备

import numpy as np
import os
import shutil

生成train.txt和val.txt

train_path = './train'
train_out = './train.txt'
val_path = './valid'
val_out = './val.txt'

data_train_out = './train_filelist'
data_val_out = './val_filelist'


def get_filelist(input_path,output_path):
    with open(output_path,'w') as f:
        for dir_path,dir_names,file_names in os.walk(input_path):   #dir_path 文件夹作为标签
            if dir_path != input_path:
                label = int(dir_path.split('\\')[-1]) -1  
            #print(label)
            for filename in file_names:
                f.write(filename +' '+str(label)+"\n")

def move_imgs(input_path,output_path):
    for dir_path, dir_names, file_names in os.walk(input_path):
        for filename in file_names:
            #print(os.path.join(dir_path,filename))
            source_path = os.path.join(dir_path,filename)

            shutil.copyfile(source_path, os.path.join(output_path,filename))

get_filelist(train_path,train_out)
get_filelist(val_path,val_out)
move_imgs(train_path,data_train_out)
move_imgs(val_path,data_val_out)

dataset

import numpy as np

from .builder import DATASETS
from .base_dataset import BaseDataset

修改configs文件

# Copyright (c) OpenMMLab. All rights reserved.
from .base_dataset import BaseDataset
from .builder import (DATASETS, PIPELINES, SAMPLERS, build_dataloader,
                      build_dataset, build_sampler)
from .cifar import CIFAR10, CIFAR100
from .dataset_wrappers import (ClassBalancedDataset, ConcatDataset,
                               KFoldDataset, RepeatDataset)
from .imagenet import ImageNet
from .imagenet21k import ImageNet21k
from .mnist import MNIST, FashionMNIST
from .multi_label import MultiLabelDataset
from .samplers import DistributedSampler, RepeatAugSampler
from .voc import VOC
from .my_filelist import MyFilelist  #右边是我的py文件的名字，右边是我自己起的类名

# 初始化函数，注册机制
__all__ = [
    'BaseDataset', 'ImageNet', 'CIFAR10', 'CIFAR100', 'MNIST', 'FashionMNIST',
    'VOC', 'MultiLabelDataset', 'build_dataloader', 'build_dataset',
    'DistributedSampler', 'ConcatDataset', 'RepeatDataset',
    'ClassBalancedDataset', 'DATASETS', 'PIPELINES', 'ImageNet21k', 'SAMPLERS',
    'build_sampler', 'RepeatAugSampler', 'KFoldDataset', 'MyFilelist'
]

@DATASETS.register_module()
class MyFilelist(BaseDataset):
    CLASSES = [
        '有102个。。。',  #0号
        '我懒得写名字了，有102个。。。',  #1号
           ]

#加载标注
    def load_annotations(self):
        assert isinstance(self.ann_file, str)
#这些东西根据自己的数据自己写的
        data_infos = []
        with open(self.ann_file) as f:
            samples = [x.strip().split(' ') for x in f.readlines()]
            for filename, gt_label in samples:
                info = {'img_prefix': self.data_prefix}
                info['img_info'] = {'filename': filename}
                info['gt_label'] = np.array(gt_label, dtype=np.int64)
                data_infos.append(info)
            return data_infos

修改mmclassification代码

#-*-coding:utf-8-*-
model = dict(
    type='ImageClassifier',
    backbone=dict(
        type='ResNet',
        depth=18,
        num_stages=4,
        out_indices=(3, ),
        style='pytorch'),
    neck=dict(type='GlobalAveragePooling'),
    head=dict(
        type='LinearClsHead',
        num_classes=102, #
        in_channels=512,
        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
        topk=(1, 5)))
dataset_type = 'ImageNet'
img_norm_cfg = dict(
    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(type='RandomResizedCrop', size=224),  #look capbility of GPU
    dict(type='RandomFlip', flip_prob=0.5, direction='horizontal'),
    dict(
        type='Normalize',
        mean=[123.675, 116.28, 103.53],
        std=[58.395, 57.12, 57.375],
        to_rgb=True),
    dict(type='ImageToTensor', keys=['img']),
    dict(type='ToTensor', keys=['gt_label']),
    dict(type='Collect', keys=['img', 'gt_label'])
]
test_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(type='Resize', size=(256, -1)),
    dict(type='CenterCrop', crop_size=224),
    dict(
        type='Normalize',
        mean=[123.675, 116.28, 103.53],
        std=[58.395, 57.12, 57.375],
        to_rgb=True),
    dict(type='ImageToTensor', keys=['img']),
    dict(type='Collect', keys=['img'])
]
data = dict(
    samples_per_gpu=8,
    workers_per_gpu=2,
    train=dict(
        type='MyFilelist',
        data_prefix='./train_filelist',   #site of train
        ann_file='./train.txt', 
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(type='RandomResizedCrop', size=224),
            dict(type='RandomFlip', flip_prob=0.5, direction='horizontal'),
            dict(
                type='Normalize',
                mean=[123.675, 116.28, 103.53],
                std=[58.395, 57.12, 57.375],
                to_rgb=True),
            dict(type='ImageToTensor', keys=['img']),
            dict(type='ToTensor', keys=['gt_label']),
            dict(type='Collect', keys=['img', 'gt_label'])
        ]),
    val=dict(
        type='MyFilelist',
        data_prefix='F:./val_filelist',
        ann_file='./val.txt',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(type='Resize', size=(256, -1)),
            dict(type='CenterCrop', crop_size=224),
            dict(
                type='Normalize',
                mean=[123.675, 116.28, 103.53],
                std=[58.395, 57.12, 57.375],
                to_rgb=True),
            dict(type='ImageToTensor', keys=['img']),
            dict(type='Collect', keys=['img'])
        ]),
    test=dict(
        type='MyFilelist',
        data_prefix='./val_filelist',
        ann_file='./val.txt',  # ?????
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(type='Resize', size=(256, -1)),
            dict(type='CenterCrop', crop_size=224),
            dict(
                type='Normalize',
                mean=[123.675, 116.28, 103.53],
                std=[58.395, 57.12, 57.375],
                to_rgb=True),
            dict(type='ImageToTensor', keys=['img']),
            dict(type='Collect', keys=['img'])
        ]))
evaluation = dict(interval=1, metric='accuracy')
optimizer = dict(type='SGD', lr=0.1, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=None)
lr_config = dict(policy='step', step=[30, 60, 90])
runner = dict(type='EpochBasedRunner', max_epochs=100)
checkpoint_config = dict(interval=50)
log_config = dict(interval=100, hooks=[dict(type='TextLoggerHook')])
dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = None
resume_from = None
workflow = [('train', 1)]
work_dir = './work_dirs/resnet18_8xb32_in1k'
gpu_ids = [0]

训练成功