【已部署】利用PaddleX静物物品智能识别并使用Vue前端部署

!pip install paddlex==2.0rc -q

Dataset/ # 目标检测数据集根目录
|--Annotations/ # 标注文件所在目录
|  |--PartA_00000.xml
|  |--PartB_00000.xml
|  |--...
|  |--... 
|--JPEGImages/ # 原图文件所在目录
|  |--PartA_00000.jpg
|  |--PartB_00000.jpg
|  |--...
|  |--...
|

# 解压数据集文件夹中!unzip -d ./ data/data96807/DatasetId_190936_1624526988.zip

# 清理一下jpeg和xml不匹配问题import os,shutil

jpeg = 'MyDataset/JPEGImages'jpeg_list = os.listdir(jpeg)

anno = 'MyDataset/Annotations'anno_list = os.listdir(anno)for pic in jpeg_list:
    name = pic.split('.')[0]
    anno_name = name + '.xml'
    #print(anno_name)
    if anno_name not in anno_list:
        os.remove(os.path.join(jpeg,pic))

# 划分数据集!paddlex --split_dataset --format VOC --dataset_dir MyDataset --val_value 0.2 --test_value 0.1

2021-10-25 21:02:25 [INFO]	Dataset split starts...
2021-10-25 21:02:25 [INFO]	Dataset split done.
2021-10-25 21:02:25 [INFO]	Train samples: 714
2021-10-25 21:02:25 [INFO]	Eval samples: 204
2021-10-25 21:02:25 [INFO]	Test samples: 102
2021-10-25 21:02:25 [INFO]	Split files saved in MyDataset

import paddlex as pdxfrom paddlex import transforms

train_transforms = transforms.Compose([
    transforms.RandomCrop(crop_size=224),
    transforms.RandomHorizontalFlip(),
    transforms.Normalize()
])
eval_transforms = transforms.Compose([
    transforms.ResizeByShort(short_size=256),
    transforms.CenterCrop(crop_size=224),
    transforms.Normalize()
])

# 定义训练和验证所用的数据集# API说明：https://github.com/PaddlePaddle/PaddleX/blob/release/2.0-rc/paddlex/cv/datasets/voc.py#L29train_dataset = pdx.datasets.VOCDetection(
    data_dir='MyDataset',
    file_list='MyDataset/train_list.txt',
    label_list='MyDataset/labels.txt',
    transforms=train_transforms,
    shuffle=True)

eval_dataset = pdx.datasets.VOCDetection(
    data_dir='MyDataset',
    file_list='MyDataset/val_list.txt',
    label_list='MyDataset/labels.txt',
    transforms=eval_transforms,
    shuffle=False)

# 初始化模型，并进行训练# 可使用VisualDL查看训练指标，参考https://github.com/PaddlePaddle/PaddleX/tree/release/2.0-rc/tutorials/train#visualdl可视化训练指标num_classes = len(train_dataset.labels)
model = pdx.models.YOLOv3(num_classes=num_classes, backbone='MobileNetV3_ssld')

# API说明：https://github.com/PaddlePaddle/PaddleX/blob/release/2.0-rc/paddlex/cv/models/detector.py#L155# 各参数介绍与调整说明：https://paddlex.readthedocs.io/zh_CN/develop/appendix/parameters.htmlmodel.train(
    num_epochs=300,
    train_dataset=train_dataset,
    train_batch_size=8,
    eval_dataset=eval_dataset,
    learning_rate=0.001 / 8,
    warmup_steps=1000,
    warmup_start_lr=0.0,
    save_interval_epochs=20,
    lr_decay_epochs=[216, 243, 275],
    save_dir='output/yolov3_mobilenet')

!paddlex --export_inference --model_dir=output/yolov3_mobilenet/best_model --save_dir=output/inference_model

import globimport numpy as npimport threadingimport timeimport randomimport osimport base64import cv2import jsonimport paddlex as pdx# 可以修改为自己图片路径image_name = 'MyDataset/JPEGImages/PartB_00234.jpg' model = pdx.load_model('output/yolov3_mobilenet/best_model')

img = cv2.imread(image_name)
result = model.predict(img)

keep_results = []
areas = []
f = open('result.txt','a')
count = 0for dt in np.array(result):
    cname, bbox, score = dt['category'], dt['bbox'], dt['score']    if score < 0.5:        continue
    keep_results.append(dt)
    count+=1
    f.write(str(dt)+'\n')
    f.write('\n')
    areas.append(bbox[2] * bbox[3])
areas = np.asarray(areas)
sorted_idxs = np.argsort(-areas).tolist()
keep_results = [keep_results[k]                for k in sorted_idxs] if len(keep_results) > 0 else []print(keep_results)print(count)
f.write("the total number is :"+str(int(count)))
f.close()

pdx.visualize_detection(image_name, result, threshold=0.5, save_dir='./output/yolov3_mobilenet')