Openmmlab无法加载预训练模型的问题

这两天在调试mmsegmentation和mmdetection，可能是因为自己的原因，预训练模型死活加载不了预训练的模型，无法正常的索引到预训练模型的地址，最后通过降低版本的方式成功地加载了预训练模型并跑了起来，具体的流程如下：

解决过程

安装pytorch和torchvision

我是30系列的显卡，所以需要的cuda版本需要是11以上。

conda install pytorch==1.9.0 torchvision==0.10.0 cudatoolkit=11.1 -c pytorch -c conda-forge

安装mmcv-full

pip install mmcv-full==1.3.10 -f https://download.openmmlab.com/mmcv/dist/cu111/torch1.9.0/index.html

安装apex

git clone https://github.com/NVIDIA/apex
pip install -v --disable-pip-version-check --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" ./

安装mmdetection，我使用的是SwinTransformer/Swin-Transformer-Object-Detection这个版本的

git clone https://github.com/SwinTransformer/Swin-Transformer-Object-Detection.git
pip install -v -e .

安装mmpycocotools

pip uninstall pycocotools
pip install mmpycocotools

测试的代码如下，当时我主要是想测试一下mmdetection在dota数据集上的表现：

from mmcv import Config
from mmdet.datasets import build_dataset
from mmdet.models import build_detector
from mmdet.apis import train_detector
from mmdet.apis import set_random_seed
import os.path as osp
import mmcv
import numpy as np
from mmdet.datasets.builder import DATASETS
from mmdet.datasets.custom import CustomDataset
import warnings
# warnings.filterwarnings('ignore')
# 目前的解决方案，要不重写一个dataset的类，要不统一都弄成coco的形式。
cfg = Config.fromfile('./configs/fcos/fcos_r50_caffe_fpn_gn-head_mstrain_640-800_2x_coco.py')
# todo 1. 定义数据集
# 目前这个数据有大问题，咱首先得处理coco格式，然后得写个带可视化得api方便查看，奶奶得。
cfg.dataset_type = 'CocoDataset'  # todo 数据集格式
cfg.classes = ('plane', 'baseball-diamond', 'bridge', 'ground-track-field', 'small-vehicle', 'large-vehicle',
                   'ship', 'tennis-court', 'basketball-court', 'storage-tank',
                   'soccer-ball-field', 'roundabout', 'harbor', 'swimming-pool', 'helicopter', 'container-crane',)  # todo 类名
data_images = '/home/lyc/data/scm/remote/dota1.5hbb/PNGImages/images/'  # todo 数据集根路径
cfg.data.train.ann_file = '/home/lyc/data/scm/remote/dota1.5hbb/dota_train.json'  # todo json文件路径
cfg.data.val.ann_file = '/home/lyc/data/scm/remote/dota1.5hbb/dota_val.json'  # todo 验证集json文件路径
cfg.data.test.ann_file = '/home/lyc/data/scm/remote/dota1.5hbb/dota_val.json'  # todo 测试集json文件路径
cfg.data.train.type = cfg.dataset_type
cfg.data.val.type = cfg.dataset_type
cfg.data.test.type = cfg.dataset_type
cfg.data.train.classes = cfg.classes
cfg.data.val.classes = cfg.classes
cfg.data.test.classes = cfg.classes
cfg.data.train.img_prefix = data_images #
cfg.data.val.img_prefix = data_images
cfg.data.test.img_prefix = data_images
cfg.data.samples_per_gpu = 4  # Batch size of a single GPU used in testing 默认是8x2
cfg.data.workers_per_gpu = 1 # Worker to pre-fetch data for each single GPU

# *************** transform **************
train_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(type='LoadAnnotations', with_bbox=True),
    dict(
        type='Resize',
        img_scale=(1024, 1024),
        # multiscale_mode='value',
        keep_ratio=True),
    dict(type='RandomFlip', flip_ratio=0.5),
    dict(
        type='Normalize',
        mean=[102.9801, 115.9465, 122.7717],
        std=[1.0, 1.0, 1.0],
        to_rgb=False),
    dict(type='Pad', size_divisor=32),
    dict(type='DefaultFormatBundle'),
    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
]
test_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(
        type='MultiScaleFlipAug',
        img_scale=(1024, 1024),
        flip=False,
        transforms=[
            dict(type='Resize', keep_ratio=True),
            dict(type='RandomFlip'),
            dict(
                type='Normalize',
                mean=[102.9801, 115.9465, 122.7717],
                std=[1.0, 1.0, 1.0],
                to_rgb=False),
            dict(type='Pad', size_divisor=32),
            dict(type='ImageToTensor', keys=['img']),
            dict(type='Collect', keys=['img'])
        ])
]



cfg.data.train.pipeline = cfg.train_pipeline
cfg.data.val.pipeline = cfg.test_pipeline
cfg.data.test.pipeline = cfg.test_pipeline

# modify num classes of the model in box head
cfg.model.bbox_head.num_classes = len(cfg.classes)
#cfg.load_from = '../checkpoints/resnet50_caffe-788b5fa3.pth'
cfg.work_dir = '../tutorial_exps/2-dota_fcos_1024_backbone'
# The original learning rate (LR) is set for 8-GPU training.
# We divide it by 8 since we only use one GPU.
cfg.optimizer.lr = 0.02 / 8
cfg.lr_config.warmup = None
cfg.log_config.interval = 10
# Change the evaluation metric since we use customized dataset.
# cfg.evaluation.metric = 'mAP'
cfg.evaluation.metric = 'bbox'
cfg.evaluation.save_best = 'bbox_mAP'
# We can set the evaluation interval to reduce the evaluation times
cfg.evaluation.interval = 1
# We can set the checkpoint saving interval to reduce the storage cost
cfg.checkpoint_config.interval = 12
# Set seed thus the results are more reproducible
cfg.seed = 0
set_random_seed(0, deterministic=False)
# cfg.gpu_ids = range(1)
cfg.gpu_ids = (0,)
# We can initialize the logger for training and have a look
# at the final config used for training
print(f'Config:\n{cfg.pretty_text}')
# 保存模型的各种参数（一定要记得嗷）
cfg.dump(F'{cfg.work_dir}/customformat_fcos.py')
# 训练主要进程
# Build dataset
datasets = [build_dataset(cfg.data.train)]
print(cfg.data.train)
print(datasets[0])
print(datasets[0].CLASSES)
# Build the detector
model = build_detector(
    cfg.model, train_cfg=cfg.get('train_cfg'), test_cfg=cfg.get('test_cfg'))
print("数据集加载完毕！")
# Add an attribute for visualization convenience
model.CLASSES = datasets[0].CLASSES
# Create work_dir
mmcv.mkdir_or_exist(osp.abspath(cfg.work_dir))
train_detector(model, datasets, cfg, distributed=False, validate=True)

！！！成功下载权重文件

附上第一轮的结果，好像不会太离谱了

# 改之前
DONE (t=8.48s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.005
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=1000 ] = 0.020
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=1000 ] = 0.001
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.001
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.005
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.009
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.035
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=300 ] = 0.035
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=1000 ] = 0.035
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.010
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.030
# 改了之后
Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.076
Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=1000 ] = 0.187
Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=1000 ] = 0.049
Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.008
Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.092
Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.101
Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.167
Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=300 ] = 0.167
Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=1000 ] = 0.167
Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.032
Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.182
Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.246