AI实战训练营&MMPretrain代码实战
一 安装MMPretrain
首先默认大家都是安装好mmcv以及mim的，用mim的话比较方便，不会出现奇奇怪怪去的错误。
- 安装一下openmim ，用来编译下面这个是我用的服务器的基本配置信息。
pip3 install openmim
- 我们直接从官网git
git clone https://github.com/open-mmlab/mmpretrain.git
- 第二步 对git下来的代码编译 先得cd到mmpretrain目录里面 。注意 ： **e后面有个 .**代表本级目录
cd mmpretrain
mim install -e .
如果需要多模态的话，需要执行下面的命令
mim install -e ".[multimodal]"
最后就是验证安装。
如果出现上面的信息，就说明安装成功了！！！
二 解析MMPretrain
我们首先导入mmpretrain中的下面库。
from mmpretrain import get_model,list_models,inference_model
接着我们用list_model可以查看具体的模型，我们以resnet18为例子：
list_models(task='Image Classification',pattern='resnet18')
# 第一个参数是 图分类
代码运行结果：
[‘resnet18_8xb16_cifar10’, ‘resnet18_8xb32_in1k’]
然后我们测试一下 get_model，用这个模型做预测推理
model = get_model('resnet18_8xb16_cifar10')
type(model)
代码运行结果：
mmpretrain.models.classifiers.image.ImageClassifier
导入下面这个库，可以进行推理，但是得加上模型参数，不然不准确
inference_model(model,'./mmpretrain/demo/bird.JPEG',show=True)
可以看到，如果不加参数的话，推理出来的结果就会很离谱。
三 作业
这里是用ResNet50做分类，我们选择mmpretrain文件夹下的configs文件夹下的resnet中的resnet50_8xb32_in1k.py 文件内容如下。
我们根据上面的文件，写出自己的配置文件，下面是我写的配置文件
- resnet50.py 记录了主干网络情况 注意类别数得改成30，因为这里是30分类，预训练模型一定不要选错
# model settings
model = dict(
type='ImageClassifier',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(3, ),
style='pytorch'),
neck=dict(type='GlobalAveragePooling'),
head=dict(
type='LinearClsHead',
num_classes=30,
in_channels=2048,
loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
topk=(1, 5),
),
# 在这里我们会加载预训练模型，方便训练，这里可以直接去官网下载 init_cfg=dict(type='Pretrained',checkpoint='https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_8xb32_in1k_20210831-ea4938fc.pth')
)
- imagenet_bs32.py 记录了图像处理流程 注意：这里的数据类型要改成’CustomDataset’，因为我们是按照train-类别-图片的形式划分的数据集
# dataset settings
dataset_type = 'CustomDataset'
data_preprocessor = dict(
num_classes=30,
# RGB format normalization parameters
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
# convert image from BGR to RGB
to_rgb=True,
)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='RandomResizedCrop', scale=224),
dict(type='RandomFlip', prob=0.5, direction='horizontal'),
dict(type='PackInputs'),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='ResizeEdge', scale=256, edge='short'),
dict(type='CenterCrop', crop_size=224),
dict(type='PackInputs'),
]
train_dataloader = dict(
batch_size=32,
num_workers=4,
dataset=dict(
type=dataset_type,
data_root='/gemini/code/mmpretrain/data/train',
pipeline=train_pipeline),
sampler=dict(type='DefaultSampler', shuffle=True),
)
val_dataloader = dict(
batch_size=32,
num_workers=2,
dataset=dict(
type=dataset_type,
data_root='/gemini/code/mmpretrain/data/val',
pipeline=test_pipeline),
sampler=dict(type='DefaultSampler', shuffle=False),
)
val_evaluator = dict(type='Accuracy', topk=(1, 5))
# # If you want standard test, please manually configure the test dataset
test_dataloader = val_dataloader
test_evaluator = val_evaluator
- imagenet_bs256.py 记录了训练中的各种参数 auto_scale_lr = dict(base_batch_size=256) 这个是多卡训练，我们用不到，可以注销掉，然后学习率稍微调小一点
# optimizer
optim_wrapper = dict(
optimizer=dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001))
# learning policy
param_scheduler = dict(
type='MultiStepLR', by_epoch=True, milestones=[30, 60, 90], gamma=0.1)
# train, val, test setting
train_cfg = dict(by_epoch=True, max_epochs=50, val_interval=1)
val_cfg = dict()
test_cfg = dict()
# NOTE: `auto_scale_lr` is for automatically scaling LR,
# based on the actual training batch size.
# auto_scale_lr = dict(base_batch_size=256)
- default_runtime.py 记录了训练中间过程像日志什么的
# defaults to use registries in mmpretrain
default_scope = 'mmpretrain'
# configure default hooks
default_hooks = dict(
# record the time of every iteration.
timer=dict(type='IterTimerHook'),
# print log every 100 iterations.
logger=dict(type='LoggerHook', interval=100),
# enable the parameter scheduler.
param_scheduler=dict(type='ParamSchedulerHook'),
# save checkpoint per epoch.
checkpoint=dict(type='CheckpointHook', interval=1 , max_keep_ckpts=10, save_best='auto'),
# set sampler seed in distributed evrionment.
sampler_seed=dict(type='DistSamplerSeedHook'),
# validation results visualization, set True to enable it.
visualization=dict(type='VisualizationHook', enable=False),
)
# configure environment
env_cfg = dict(
# whether to enable cudnn benchmark
cudnn_benchmark=False,
# set multi process parameters
mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
# set distributed parameters
dist_cfg=dict(backend='nccl'),
)
# set visualizer
vis_backends = [dict(type='LocalVisBackend')]
visualizer = dict(type='UniversalVisualizer', vis_backends=vis_backends)
# set log level
log_level = 'INFO'
# load from which checkpoint
load_from = None
# whether to resume training from the loaded checkpoint
resume = False
# Defaults to use random seed and disable `deterministic`
randomness = dict(seed=None, deterministic=False)
以上是我的配置文件。
然后运行即可：
mim train mmpretrain resnet50.py --work_dir=./work
附:将数据集转成CustomDataset类型的代码
import os
import sys
import shutil
import numpy as np
def load_data(data_path):
count = 0
data = {
}
for dir_name in os.listdir(data_path):
dir_path = os.path.join(data_path,dir_name)
if not os.path.isdir(dir_path):
continue
data[dir_name] = []
for file_name in os.listdir(dir_path):
file_path = os.path.join(dir_path,file_name)
if not os.path.isfile(file_path):
continue
data[dir_name].append(file_path)
count += len(data[dir_name])
print('{}:{}'.format(dir_name,len(data[dir_name])))
print('total of image:{}'.format(count))
return data
def copy_dataset(src_img_list,data_index,target_path):
target_img_list = []
for index in data_index:
src_img = src_img_list[index]
img_name = os.path.split(src_img)[-1]
shutil.copy(src_img, target_path)
target_img_list.append(os.path.join(target_path, img_name))
return target_img_list
def write_file(data,file_name):
if isinstance(data,dict):
write_data = []
for lab,img_list in data.items():
for img in img_list:
write_data.append("{} {}".format(img, lab))
else:
write_data = data
with open(file_name, "w") as f:
for line in write_data:
f.write(line + "\n")
print("{} write over!".format(file_name))
def split_data(src_data_path, target_data_path, train_rate=0.8):
src_data_dict = load_data(src_data_path)
classes = []
train_dataset, val_dataset = {
}, {
}
train_count, val_count = 0, 0
for i, (cls_name, img_list) in enumerate(src_data_dict.items()):
img_data_size = len(img_list)
random_index = np.random.choice(img_data_size, img_data_size,replace=False)
train_data_size = int(img_data_size * train_rate)
train_data_index = random_index[:train_data_size]
val_data_index = random_index[train_data_size:]
train_data_path = os.path.join(target_data_path, "train", cls_name)
val_data_path = os.path.join(target_data_path, "val", cls_name)
os.makedirs(train_data_path, exist_ok=True)
os.makedirs(val_data_path, exist_ok=True)
classes.append(cls_name)
train_dataset[i] = copy_dataset(img_list, train_data_index,train_data_path)
val_dataset[i] = copy_dataset(img_list, val_data_index, val_data_path)
print("target {} train:{}, val:{}".format(cls_name,len(train_dataset[i]), len(val_dataset[i])))
train_count += len(train_dataset[i])
val_count += len(val_dataset[i])
print("train size:{}, val size:{}, total:{}".format(train_count, val_count,train_count + val_count))
write_file(classes, os.path.join(target_data_path, "classes.txt"))
write_file(train_dataset, os.path.join(target_data_path, "train.txt"))
write_file(val_dataset, os.path.join(target_data_path, "val.txt"))
def main():
src_data_path = sys.argv[1]
target_data_path = sys.argv[2]
split_data(src_data_path, target_data_path, train_rate=0.9)