基于Oxford-IIIT Pet数据集实现PaddleHub猫咪一键抠图

! git clone https://gitee.com/paddlepaddle/PaddleSeg.git  --depth=1

# 解压缩数据集!mkdir dataset
!tar -xvf data/data50154/images.tar.gz -C dataset/
!tar -xvf data/data50154/annotations.tar.gz -C dataset/

# 查看list文件!head -n 10 dataset/annotations/list.txt

# 删除文件前6行描述头，方便pandas读取!sed -i '1,6d' dataset/annotations/list.txt

!head dataset/annotations/list.txt

import pandas as pdimport shutilimport os# Image CLASS-ID SPECIES BREED ID# ID: 1:37 Class ids# SPECIES: 1:Cat 2:Dog# BREED ID: 1-25:Cat 1:12:Dog# All images with 1st letter as captial are cat images# images with small first letter are dog images# ._Abyssinian_100.pngdef copyfile(animal, filename):
    # image\label列表
    file_list = []
    image_file = filename + '.jpg'
    label_file = filename + '.png'

    if os.path.exists(os.path.join('dataset/images', image_file)):
        shutil.copy(os.path.join('dataset/images', image_file), os.path.join(f'{animal}/images', image_file))
        shutil.copy(os.path.join('dataset/annotations/trimaps', label_file),
                    os.path.join(f'{animal}/labels', label_file))
        temp = os.path.join('images/', image_file) + ' ' + os.path.join('labels/',label_file) + '\n'
        file_list.append(temp)    with open(os.path.join(animal, animal + '.txt'), 'a') as f:
        f.writelines(file_list)if __name__ == "__main__":

    data = pd.read_csv('dataset/annotations/list.txt', header=None, sep=' ')
    data.head()

    cat = data[data[2] == 1]
    dog = data[data[2] == 2]    for item in cat[0]:
        copyfile('cat', item)    for item in dog[0]:
        copyfile('dog', item)

# 删除无用数据!rm dataset/ -rf

├── cat.txt
├── images
│   ├── Abyssinian_100.jpg
│   ├── Abyssinian_101.jpg
│   ├── ...├── labels
│   ├── Abyssinian_100.png
│   ├── Abyssinian_101.png
│   ├── ...

images/Abyssinian_1.jpg labels/Abyssinian_1.png
images/Abyssinian_10.jpg labels/Abyssinian_10.png
images/Abyssinian_100.jpg labels/Abyssinian_100.png...

%cd ~from PIL import Image

img=Image.open('cat/images/Abyssinian_123.jpg')print(img)
img

img=Image.open('cat/labels/Abyssinian_123.png')print(img)
img

# 执行一次即可import pandas as pdimport osimport matplotlib.pyplot as pltimport numpy as npfrom PIL import Imagedef re_label(filename):
    img = plt.imread(filename) * 255.0
    img_label = np.zeros((img.shape[0], img.shape[1]), np.uint8)    for i in range(img.shape[0]):        for j in range(img.shape[1]):
            value = img[i, j]            if value == 2:
                img_label[i, j] = 1
    label0 = Image.fromarray(np.uint8(img_label))
    label0.save( filename)

data=pd.read_csv("cat/cat.txt", header=None, sep=' ') 
for item in data[1]:
    re_label(os.path.join('cat', item))print('处理完毕！')

import osfrom sklearn.model_selection import train_test_splitimport pandas as pddef break_data(target, rate=0.2):
    origin_dataset = pd.read_csv("cat/cat.txt", header=None, sep=' ')  # 加入参数
    train_data, test_data = train_test_split(origin_dataset, test_size=rate)
    train_data,eval_data=train_test_split(train_data, test_size=rate)
    train_filename = os.path.join(target, 'train.txt')
    test_filename = os.path.join(target, 'test.txt')
    eval_filename = os.path.join(target, 'eval.txt')

    train_data.to_csv(train_filename, index=False, sep=' ',  header=None)
    test_data.to_csv(test_filename, index=False, sep=' ', header=None)
    eval_data.to_csv(eval_filename, index=False, sep=' ', header=None)    print('train_data:',len(train_data))    print('test_data:',len(test_data))    print('eval_data:',len(eval_data))if __name__ == '__main__':
    break_data(target='cat', rate=0.2)

# 查看!head cat/train.txt

# 已配置好，可以不用复制了# !cp PaddleSeg/configs/quick_start/bisenet_optic_disc_512x512_1k.yml ~/bisenet_optic_disc_512x512_1k.yml

batch_size: 600iters: 5000train_dataset:   
  type: Dataset
  dataset_root: /home/aistudio/cat/
  train_path: /home/aistudio/cat/train.txt
  num_classes: 2
  transforms:
    - type: ResizeStepScaling
      min_scale_factor: 0.5
      max_scale_factor: 2.0
      scale_step_size: 0.25
    - type: RandomPaddingCrop
      crop_size: [224, 224]    - type: RandomHorizontalFlip
    - type: RandomDistort
      brightness_range: 0.4
      contrast_range: 0.4
      saturation_range: 0.4
    - type: Normalize
  mode: trainval_dataset: 
  type: Dataset
  dataset_root: /home/aistudio/cat/
  val_path: /home/aistudio/cat/eval.txt
  num_classes: 2
  transforms:
    - type: Normalize
  mode: valoptimizer:
  type: sgd
  momentum: 0.9
  weight_decay: 0.0005lr_scheduler:
  type: PolynomialDecay
  learning_rate: 0.05
  end_lr: 0
  power: 0.9loss:
  types:
    - type: CrossEntropyLoss
  coef: [1]model:
  type: FCN
  backbone:
    type: HRNet_W18_Small_V1
    align_corners: False
  num_classes: 2
  pretrained: Null

%cd ~/PaddleSeg/
! python train.py --config  ../bisenet_optic_disc_512x512_1k.yml\
    --do_eval \
    --use_vdl \
    --save_interval 100 \
    --save_dir output

2021-11-13 19:30:52 [INFO]	[TRAIN] epoch: 1105, iter: 2210/5000, loss: 0.1849, lr: 0.029586, batch_cost: 8.8180, reader_cost: 7.73956, ips: 68.0427 samples/sec | ETA 06:50:022021-11-13 19:32:18 [INFO]	[TRAIN] epoch: 1110, iter: 2220/5000, loss: 0.1768, lr: 0.029490, batch_cost: 8.6004, reader_cost: 7.52235, ips: 69.7641 samples/sec | ETA 06:38:292021-11-13 19:33:47 [INFO]	[TRAIN] epoch: 1115, iter: 2230/5000, loss: 0.1791, lr: 0.029395, batch_cost: 8.8851, reader_cost: 7.80702, ips: 67.5288 samples/sec | ETA 06:50:112021-11-13 19:35:14 [INFO]	[TRAIN] epoch: 1120, iter: 2240/5000, loss: 0.1835, lr: 0.029299, batch_cost: 8.6699, reader_cost: 7.59314, ips: 69.2053 samples/sec | ETA 06:38:482021-11-13 19:36:41 [INFO]	[TRAIN] epoch: 1125, iter: 2250/5000, loss: 0.1815, lr: 0.029204, batch_cost: 8.7713, reader_cost: 7.68169, ips: 68.4051 samples/sec | ETA 06:42:002021-11-13 19:38:08 [INFO]	[TRAIN] epoch: 1130, iter: 2260/5000, loss: 0.1833, lr: 0.029108, batch_cost: 8.7045, reader_cost: 7.62504, ips: 68.9299 samples/sec | ETA 06:37:302021-11-13 19:39:35 [INFO]	[TRAIN] epoch: 1135, iter: 2270/5000, loss: 0.1741, lr: 0.029013, batch_cost: 8.7032, reader_cost: 7.61708, ips: 68.9401 samples/sec | ETA 06:35:592021-11-13 19:41:03 [INFO]	[TRAIN] epoch: 1140, iter: 2280/5000, loss: 0.1810, lr: 0.028917, batch_cost: 8.8020, reader_cost: 7.72264, ips: 68.1664 samples/sec | ETA 06:39:012021-11-13 19:42:33 [INFO]	[TRAIN] epoch: 1145, iter: 2290/5000, loss: 0.1799, lr: 0.028821, batch_cost: 8.9336, reader_cost: 7.84692, ips: 67.1623 samples/sec | ETA 06:43:302021-11-13 19:44:02 [INFO]	[TRAIN] epoch: 1150, iter: 2300/5000, loss: 0.1756, lr: 0.028726, batch_cost: 8.9216, reader_cost: 7.84517, ips: 67.2524 samples/sec | ETA 06:41:282021-11-13 19:44:02 [INFO]	Start evaluating (total_samples: 380, total_iters: 380)...380/380 [==============================] - 15s 40ms/step - batch_cost: 0.0394 - reader cost: 0.0012021-11-13 19:44:17 [INFO]	[EVAL] #Images: 380 mIoU: 0.7640 Acc: 0.8681 Kappa: 0.7330 2021-11-13 19:44:17 [INFO]	[EVAL] Class IoU: [0.7378 0.7902]2021-11-13 19:44:17 [INFO]	[EVAL] Class Acc: [0.7925 0.9347]2021-11-13 19:44:17 [INFO]	[EVAL] The model with the best validation mIoU (0.7874) was saved at iter 2100.

!python val.py \
       --config  /home/aistudio/bisenet_optic_disc_512x512_1k.yml\
       --model_path output/best_model/model.pdparams

380/380 [==============================] - 15s 41ms/step - batch_cost: 0.0405 - reader cost: 0.002021-11-13 19:48:35 [INFO]	[EVAL] #Images: 380 mIoU: 0.7874 Acc: 0.8838 Kappa: 0.7616 2021-11-13 19:48:35 [INFO]	[EVAL] Class IoU: 
[0.7566 0.8181]2021-11-13 19:48:35 [INFO]	[EVAL] Class Acc: 
[0.8349 0.9211]

!python export.py \
       --config /home/aistudio/bisenet_optic_disc_512x512_1k.yml\
       --model_path output/best_model/model.pdparams

 op_type, op_type, EXPRESSION_MAP[method_name]))/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:322: UserWarning: /tmp/tmp_l3u6xjv.py:58The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))2021-11-03 01:01:11 [INFO]	Model is saved in ./output.

Deploy:
  model: model.pdmodel
  params: model.pdiparams
  transforms:
  - type: Normalize

# 安装paddleseg!pip install -e .

# 预测%cd ~/PaddleSeg/
!python deploy/python/infer.py --config output/deploy.yaml  --image_path /home/aistudio/cat/images/Bombay_130.jpg

# 打印原图from PIL import Image
img=Image.open('/home/aistudio/cat/images/Bombay_130.jpg')
img

# 打印输出图，颜色可调from PIL import Image
img=Image.open('/home/aistudio/PaddleSeg/output/Bombay_130.png')
img

hub run catseg_mobile --input_path .\cat1.jpg

<br/>