【Paddle打比赛】基于PaddleDetection未知工作服识别

# 下载PaddleDetection，当前版本为realse/2.3版本!git clone https://gitee.com/paddlepaddle/PaddleDetection.git --depth=1

# 安装%cd ~/PaddleDetection# 安装依赖!pip install -r requirements.txt# 本地安装!pip install -e ./

# 查看版本!pip list|grep paddledet

# 切换至尊版GPU环境32Gb显卡运行!nvidia-smi

# 解压缩数据集到data目录# 此处建议解压到data目录，关闭时不保存，启动时速度较快，强烈推荐%cd ~
!unzip -qoa data/data124244/省厅-未知工作服属性识别-算法赛-A榜数据.zip -d data

# 重命名数据集!mv data/省厅-工服识别-算法赛-A榜数据 data/data_a

# 安装PaddleX!pip install paddlex

# 按照PaddleX要求规范目录命名!mv data/data_a/train/images data/data_a/train/JPEGImages

# 利用PaddleX对数据集进行分隔!paddlex --split_dataset --format VOC --dataset_dir data/data_a/train/ --val_value 0.2

2022-01-03 12:27:08 [INFO]	Dataset split starts...
2022-01-03 12:27:08 [INFO]	Dataset split done.
2022-01-03 12:27:08 [INFO]	Train samples: 736
2022-01-03 12:27:08 [INFO]	Eval samples: 183
2022-01-03 12:27:08 [INFO]	Test samples: 0
2022-01-03 12:27:08 [INFO]	Split files saved in data/data_a/train/

_BASE_: [  '../datasets/voc.yml',
  '../runtime.yml',
  '_base_/optimizer_270e.yml',
  '_base_/yolov3_darknet53.yml',
  '_base_/yolov3_reader.yml',]snapshot_epoch: 5weights: output/yolov3_darknet53_270e_voc/model_final

# set collate_batch to false because ground-truth info is needed
# on voc dataset and should not collate data in batch when batch size
# is larger than 1.EvalReader:
  collate_batch: false

metric: VOC
map_type: 11point
num_classes: 2# 训练集TrainDataset:
  !VOCDataSet
    dataset_dir: /home/aistudio/data/data_a/train/
    anno_path: /home/aistudio/data/data_a/train/train_list.txt
    label_list: /home/aistudio/data/data_a/train/labels.txt
    data_fields: ['image', 'gt_bbox', 'gt_class', 'difficult']# 测试集EvalDataset:
  !VOCDataSet
    dataset_dir: /home/aistudio/data/data_a/train/
    anno_path: /home/aistudio/data/data_a/train/val_list.txt
    label_list: /home/aistudio/data/data_a/train/labels.txt
    data_fields: ['image', 'gt_bbox', 'gt_class', 'difficult']# 预测集TestDataset:
  !ImageFolder  	 # 预测标签配置
    anno_path: /home/aistudio/data/data_a/train/labels.txt

#GPU模式use_gpu: true# 日志打印间隔log_iter: 20# 保存目录save_dir: outputsnapshot_epoch: 500print_flops: false

# 训练轮次配置epoch: 270# 学习率配置LearningRate:
  base_lr: 0.001
  schedulers:
  - !PiecewiseDecay
    gamma: 0.1
    milestones:
    - 216
    - 243
  - !LinearWarmup
    start_factor: 0.
    steps: 4000OptimizerBuilder:
  optimizer:
    momentum: 0.9
    type: Momentum
  regularizer:
    factor: 0.0005
    type: L2

architecture: YOLOv3pretrain_weights: https://paddledet.bj.bcebos.com/models/pretrained/DarkNet53_pretrained.pdparamsnorm_type: sync_bnYOLOv3:
  backbone: DarkNet
  neck: YOLOv3FPN
  yolo_head: YOLOv3Head
  post_process: BBoxPostProcessDarkNet:
  depth: 53
  return_idx: [2, 3, 4]# use default config# YOLOv3FPN:YOLOv3Head:
  anchors: [[10, 13], [16, 30], [33, 23],
            [30, 61], [62, 45], [59, 119],
            [116, 90], [156, 198], [373, 326]]  anchor_masks: [[6, 7, 8], [3, 4, 5], [0, 1, 2]]  loss: YOLOv3LossYOLOv3Loss:
  ignore_thresh: 0.7
  downsample: [32, 16, 8]  label_smooth: falseBBoxPostProcess:
  decode:
    name: YOLOBox
    conf_thresh: 0.005
    downsample_ratio: 32
    clip_bbox: true
  nms:
    name: MultiClassNMS
    keep_top_k: 100
    score_threshold: 0.01
    nms_threshold: 0.45
    nms_top_k: 1000

worker_num: 2TrainReader:
  inputs_def:
    num_max_boxes: 50
  sample_transforms:
    - Decode: {}    - Mixup: {alpha: 1.5, beta: 1.5}    - RandomDistort: {}    - RandomExpand: {fill_value: [123.675, 116.28, 103.53]}    - RandomCrop: {}    - RandomFlip: {}  batch_transforms:
    - BatchRandomResize: {target_size: [320, 352, 384, 416, 448, 480, 512, 544, 576, 608], random_size: True, random_interp: True, keep_ratio: False}    - RandomDistort: {}    - NormalizeBox: {}    - PadBox: {num_max_boxes: 50}    - BboxXYXY2XYWH: {}    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}    - Permute: {}    - Gt2YoloTarget: {anchor_masks: [[6, 7, 8], [3, 4, 5], [0, 1, 2]], anchors: [[10, 13], [16, 30], [33, 23], [30, 61], [62, 45], [59, 119], [116, 90], [156, 198], [373, 326]], downsample_ratios: [32, 16, 8]}  batch_size: 20
  shuffle: true
  drop_last: true
  mixup_epoch: 250
  use_shared_memory: trueEvalReader:
  inputs_def:
    num_max_boxes: 50
  sample_transforms:
    - Decode: {}    - Resize: {target_size: [608, 608], keep_ratio: False, interp: 2}    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}    - Permute: {}  batch_size: 20TestReader:
  inputs_def:
    image_shape: [3, 608, 608]  sample_transforms:
    - Decode: {}    - Resize: {target_size: [608, 608], keep_ratio: False, interp: 2}    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}    - Permute: {}  batch_size: 1

# 数据集配置，其他可采取默认!cp -f  ~/voc.yml ~/PaddleDetection/configs/datasets/voc.yml

# 训练%cd ~/PaddleDetection/

!python tools/train.py -c ./configs/yolov3/yolov3_darknet53_270e_voc.yml 
     --use_vdl=true 
    --vdl_log_dir=vdl_dir/scalar 
    --eval -o use_gpu=true

[01/03 23:08:05] ppdet.engine INFO: Epoch: [10] [ 0/36] learning_rate: 0.000090 loss_xy: 5.516527 loss_wh: 3.053876 loss_obj: 12.486687 loss_cls: 1.317490 loss: 22.319881 eta: 8:48:30 batch_cost: 3.1413 data_cost: 2.6554 ips: 6.3668 images/s
[01/03 23:09:07] ppdet.engine INFO: Epoch: [10] [20/36] learning_rate: 0.000095 loss_xy: 6.114716 loss_wh: 3.206046 loss_obj: 13.324018 loss_cls: 1.355693 loss: 24.122631 eta: 8:44:56 batch_cost: 3.0901 data_cost: 2.5885 ips: 6.4723 images/s
[01/03 23:10:03] ppdet.engine INFO: Epoch: [11] [ 0/36] learning_rate: 0.000099 loss_xy: 5.409023 loss_wh: 2.845924 loss_obj: 12.471905 loss_cls: 1.237947 loss: 21.803427 eta: 8:44:45 batch_cost: 3.4201 data_cost: 2.8799 ips: 5.8477 images/s
[01/03 23:11:06] ppdet.engine INFO: Epoch: [11] [20/36] learning_rate: 0.000104 loss_xy: 5.595372 loss_wh: 2.837581 loss_obj: 12.333159 loss_cls: 1.263098 loss: 22.268236 eta: 8:41:59 batch_cost: 3.1570 data_cost: 2.5889 ips: 6.3351 images/s
[01/03 23:12:03] ppdet.engine INFO: Epoch: [12] [ 0/36] learning_rate: 0.000108 loss_xy: 5.279551 loss_wh: 2.735991 loss_obj: 11.844409 loss_cls: 1.155111 loss: 21.146755 eta: 8:41:51 batch_cost: 3.4755 data_cost: 3.0134 ips: 5.7545 images/s
[01/03 23:13:10] ppdet.engine INFO: Epoch: [12] [20/36] learning_rate: 0.000113 loss_xy: 5.620305 loss_wh: 2.650487 loss_obj: 11.757578 loss_cls: 1.057634 loss: 21.237453 eta: 8:40:36 batch_cost: 3.3526 data_cost: 2.9166 ips: 5.9655 images/s
[01/03 23:14:04] ppdet.engine INFO: Epoch: [13] [ 0/36] learning_rate: 0.000117 loss_xy: 5.811560 loss_wh: 2.833800 loss_obj: 12.568821 loss_cls: 1.326491 loss: 21.987259 eta: 8:39:42 batch_cost: 3.3750 data_cost: 2.8388 ips: 5.9260 images/s
[01/03 23:15:10] ppdet.engine INFO: Epoch: [13] [20/36] learning_rate: 0.000122 loss_xy: 5.573336 loss_wh: 2.614874 loss_obj: 11.848093 loss_cls: 1.017949 loss: 20.871216 eta: 8:37:56 batch_cost: 3.2704 data_cost: 2.7479 ips: 6.1155 images/s
[01/03 23:16:04] ppdet.engine INFO: Epoch: [14] [ 0/36] learning_rate: 0.000126 loss_xy: 5.268225 loss_wh: 2.517870 loss_obj: 10.861967 loss_cls: 1.058530 loss: 19.757854 eta: 8:37:08 batch_cost: 3.3716 data_cost: 2.8755 ips: 5.9318 images/s
[01/03 23:17:06] ppdet.engine INFO: Epoch: [14] [20/36] learning_rate: 0.000131 loss_xy: 5.842254 loss_wh: 2.545744 loss_obj: 12.144636 loss_cls: 1.203430 loss: 21.758163 eta: 8:34:32 batch_cost: 3.1135 data_cost: 2.5847 ips: 6.4237 images/s
[01/03 23:17:52] ppdet.utils.checkpoint INFO: Save checkpoint: output/yolov3_darknet53_270e_voc
[01/03 23:17:53] ppdet.engine INFO: Eval iter: 0[01/03 23:17:57] ppdet.metrics.metrics INFO: Accumulating evaluatation results...
[01/03 23:17:57] ppdet.metrics.metrics INFO: mAP(0.50, 11point) = 18.91%
[01/03 23:17:57] ppdet.engine INFO: Total sample number: 183, averge FPS: 37.56547376000298[01/03 23:17:57] ppdet.engine INFO: Best test bbox ap is 0.189.
[01/03 23:18:01] ppdet.utils.checkpoint INFO: Save checkpoint: output/yolov3_darknet53_270e_voc

# 单个预测%cd ~/PaddleDetection/

!python tools/infer.py -c ./configs/yolov3/yolov3_darknet53_270e_voc.yml   
    -o use_gpu=true --infer_img=../data/data_a/train/JPEGImages/chef910-0000.jpg

# 打印预测结果from PIL import Image

img=Image.open('output/chef910-0000.jpg')
img

%cd ~/PaddleDetection/# 其他颜色工作服预测!python tools/infer.py -c./configs/yolov3/yolov3_darknet53_270e_voc.yml    
    -o use_gpu=true --infer_dir=../data/data_a/test-A/othercolor/images/ 
    --save_txt=True 
    --draw_threshold=0.5# 白色工作服预测!python tools/infer.py -c./configs/yolov3/yolov3_darknet53_270e_voc.yml    
    -o use_gpu=true --infer_dir=../data/data_a/test-A/whitecolor/images/ 
    --save_txt=True 
    --draw_threshold=0.5

# 可视化预测结果from PIL import Image

img=Image.open('output/chef910-0298.jpg')
img

%cd ~# 新建result_dir!mkdir result_dir# 拷贝txt预测结果文件到result_dir!cp -r PaddleDetection/output/*.txt result_dir

#!/usr/bin/python# -*- coding: UTF-8 -*-"""
@author:livingbody
@file:test.py
@time:2022/01/04
"""import pandas as pdimport os# 修改标签# chefclothes为1# otherclothes为0def fix_clothes(data):
    print(data)    if data == 'chefclothes':        return 1
    else:        return 0# 坐标格式化数据，保留小数点后1位def fix_pint(data):
    data1 = float('%.1f' % data)    return data1# 概率格式化，保留小数点后2位def fix_pint2(data):
    data1 = float('%.2f' % data)    return data1# 获取预测结果def get_data(file_name):
    data = pd.read_csv(file_name, index_col=None, header=None, sep=' ')
    data[0] = data[0].apply(fix_clothes)
    data[1] = data[1].apply(fix_pint2)    for i in range(2, len(data.columns)):
        data[i] = data[i].apply(fix_pint)    return data# 获取单个预测文件数据def get_single_data(file_name):
    # 获取txt文件名
    temp = file_name.split('\')[-1]    # 获取图片文件名
    temp = temp.split('.')[0] + '.jpg'
    mylist = []
    data = None
    try:
        data = get_data(file_name)    except:        # 如文件为空，返回None
        return None    
    for index, row in data.iterrows():
        row = row.tolist()        # 第2列概率
        # 第3列左上顶点x值
        # 第4列左上顶点y值
        
        # 第1列为标签，int
        row[0] = int(row[0])        # 第5列右下顶点x值
        # 第6列右下顶点y值
        # PaddleDetection预测结果为：左上x 左上y  宽度  高度，此处需要转换
        row[4] = row[2] + row[4]
        row[4] = float('%.1f' % row[4])
        row[5] = row[3] + row[5]
        row[5] = float('%.1f' % row[5])        for i in range(len(row)):
            row[i] = str(row[i])
        row = temp + ' ' + ' '.join(row)        # print(row)  # 输出每行的索引值
        mylist.append(row)    return mylist# 输出结果到提交文件def get_all_data():
    mylist = []    for dirpath, dirname, filenames in os.walk('./result_dir'):        for filename in filenames:            if '.txt' in filename:                print(filename)
                tmp = get_single_data(os.path.join(dirpath, filename))                if tmp == None:                    continue
                mylist.extend(tmp)    return mylistif __name__ == '__main__':
    all_data = get_all_data()    with open('myresult.txt', 'w') as f:        for item in all_data:
            f.write(item + '
')

!head myresult.txt