mmetection之Hybrid Task Cascade训练自己的数据集（VIA标注）

旧城等待， 2022-11-27 05:20 313阅读 0赞

[https://github.com/open-mmlab/mmdetection][https_github.com_open-mmlab_mmdetection]

根据官网配置好mmdetection所需环境，我用的pytorch1.4.0，cuda10，按照官方文档要求配置就可以[https://github.com/open-mmlab/mmdetection/blob/master/docs/install.md][https_github.com_open-mmlab_mmdetection_blob_master_docs_install.md]

主要介绍如何将VIA标注的数据集转换成HTC需要的格式，在VIA[http://www.robots.ox.ac.uk/~vgg/software/via/via-1.0.6.html][http_www.robots.ox.ac.uk_vgg_software_via_via-1.0.6.html]

上使用多边形标注将自己的数据集标注好，我的数据集TRAIN-2477张图片，VAL-788张图片，对应json文件分别为train\_end.json和val\_end.json

一，将via标注的数据集转换为常用的coco格式，转换工具[https://download.csdn.net/download/qq\_37754309/12710210][https_download.csdn.net_download_qq_37754309_12710210]  
二，转换为常用coco格式的json文件后还需要生成htc需要的stuffthingmaps文件夹下面的图片

1，进入https://github.com/nightrome/cocostuffapi下载后将PythonAPI/pycocotools/cocostuffhelper.py中第140行到150行改为

# Create label map
        #labelMap = cocoSegmentationToSegmentationMap(coco, imgId, includeCrowd=includeCrowd)
        labelMap = cocoSegmentationToSegmentationMap(coco, imgId, checkUniquePixelLabel=False, includeCrowd=includeCrowd)
        labelMap = labelMap.astype(np.int8)
        labelMap = labelMap + 91
    # Get color map and convert to PIL's format
        cmap = getCMap()
        cmap = (cmap * 255).astype(int)
        padding = np.zeros((256-cmap.shape[0], 3), np.int8)
        cmap = np.vstack((cmap, padding))
        cmap = cmap.reshape((-1))
        cmap = np.uint8(cmap).tolist()
        assert len(cmap) == 768, 'Error: Color map must have exactly 256*3 elements!'

2，将PythonAPI/cocostuff/cocoSegmentationToPngDemo.py复制到PythonAPI下，即PythonAPI/cocoSegmentationToPngDemo.py

将PythonAPI/cocoSegmentationToPngDemo.py中第75行到88行注释掉并将annPath设置为我们在第一步中转换好的json文件

def cocoSegmentationToPngDemo(dataDir='coco/', dataTypeAnn='train2017', dataTypeRes='examples', \
            pngFolderName='export_png', isAnnotation=True, exportImageLimit=2477):
        # Define paths
        annPath = '/home/fst/work/dataset/instances_train2017.json'
        if isAnnotation:
            pngFolder = '%s/annotations/%s' % (dataDir, pngFolderName)

根据上图路径生成的图片放在PythonAPI/coco/annotations/export\_png文件夹下面，但此图片是彩色的，而stuffthingmaps中所需要的图片为灰度图，使用opencv对export\_png下的图片进行灰度化，生成stuffthingmaps下的train2017和val2017文件夹下的图片

mmdetection
    ├── mmdet
    ├── tools
    ├── configs
    ├── data
    │   ├── coco
    │   │   ├── annotations
    │   │   │   ├── instances_train2017.json(第一步中转换出的coco格式的json文件)
    │   │   │   ├── instances_val2017.json(第一步中转换出的coco格式的json文件)
    │   │   ├── train2017（原图）
    │   │   ├── val2017（原图）
    |   |     ├── stuffthingmaps
    │   │   │   ├── train2017（第二步灰度化后的图片）
    │   │   │   ├── val2017（第二步灰度化后的图片）

准备好数据集以后就可以开始训练了

sudo python3 train.py /mmdetection-master/configs/htc/htc\_x101\_32x4d\_fpn\_16x1\_20e\_coco.py

我的htc\_x101\_32x4d\_fpn\_16x1\_20e\_coco.py配置如下

_base_ = './htc_r50_fpn_1x_coco.py'
    model = dict(
        pretrained='open-mmlab://resnext101_32x4d',
        backbone=dict(
            type='ResNeXt',
            depth=101,
            groups=32,
            base_width=4,
            num_stages=4,
            out_indices=(0, 1, 2, 3),
            frozen_stages=1,
            norm_cfg=dict(type='BN', requires_grad=True),
            norm_eval=True,
            style='pytorch'))
    data = dict(samples_per_gpu=2, workers_per_gpu=1)
    optimizer = dict(type='SGD', lr=0.001, momentum=0.9, weight_decay=0.0001)
    optimizer_config = dict(grad_clip=dict(max_norm=5, norm_type=2))
    # learning policy
    lr_config = dict(step=[16, 19])
    total_epochs = 20

等待它训练完就可以进行测试啦。

如果想要对训练过程进行可视化，只需在配置文件中加入如下代码即可，使用tensorboard进行可视化

log_config = dict(
        interval=50,
        hooks=[
            dict(type='TextLoggerHook'),
            dict(type='TensorboardLoggerHook')
        ])

如果训练意外中断，需要继续训练时，可使用以下语句

python3 tools/train.py configs下的配置文件 --resume-from work_dirs下之前训练好的模型

测试代码

import os
    import cv2
    from mmdet.apis import init_detector, inference_detector, show_result_pyplot
    import mmcv
    import time
    config_file = '/mmdetection-master/work_dirs/htc_x101_32x4d_fpn_16x1_20e_coco0810/htc_x101_32x4d_fpn_16x1_20e_coco.py'##训练后生成的配置文件
    checkpoint_file = '/mmdetection-master/work_dirs/htc_x101_32x4d_fpn_16x1_20e_coco0810/epoch_20.pth'#训练后生成的模型文件
    
    # build the model from a config file and a checkpoint file
    model = init_detector(config_file, checkpoint_file, device='cuda:0')
    img_path = '/test/0813/'#测试图片路径
    for filename in os.listdir(img_path):
        img = os.path.join(img_path, filename)
        result = inference_detector(model, img)
        img = model.show_result(img, result, score_thr=0.6, show=False)
        # visualize the results in a new window
        cv2.imwrite('/test_result/0813/'+filename, img)

[https_github.com_open-mmlab_mmdetection]: https://github.com/open-mmlab/mmdetection
[https_github.com_open-mmlab_mmdetection_blob_master_docs_install.md]: https://github.com/open-mmlab/mmdetection/blob/master/docs/install.md
[http_www.robots.ox.ac.uk_vgg_software_via_via-1.0.6.html]: http://www.robots.ox.ac.uk/~vgg/software/via/via-1.0.6.html
[https_download.csdn.net_download_qq_37754309_12710210]: https://download.csdn.net/download/qq_37754309/12710210