def train():
from paddlex.cls 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()
])
train_dataset = pdx.datasets.ImageNet(
data_dir=f'{data_dir}/mini_imagenet_veg',
file_list=f'{data_dir}/mini_imagenet_veg/train_list.txt',
label_list=f'{data_dir}/mini_imagenet_veg/labels.txt',
transforms=train_transforms)
eval_dataset = pdx.datasets.ImageNet(
data_dir=f'{data_dir}/mini_imagenet_veg',
file_list=f'{data_dir}/mini_imagenet_veg/val_list.txt',
label_list=f'{data_dir}/mini_imagenet_veg/labels.txt',
transforms=eval_transforms)
num_classes = len(train_dataset.labels)
model = pdx.cls.MobileNetV3_large_ssld(num_classes=num_classes)
model.train(num_epochs=12,
train_dataset=train_dataset,
train_batch_size=32,
eval_dataset=eval_dataset,
lr_decay_epochs=[6, 8],
save_interval_epochs=1,
learning_rate=0.00625,
save_dir=f'{output_dir}/output/mobilenetv3_large_ssld',
use_vdl=True)
def train():
from paddlex.cls 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()
])
train_dataset = pdx.datasets.ImageNet(
data_dir=f'{data_dir}/vegetables_cls',
file_list=f'{data_dir}/vegetables_cls/train_list.txt',
label_list=f'{data_dir}/vegetables_cls/labels.txt',
transforms=train_transforms,
shuffle=True)
eval_dataset = pdx.datasets.ImageNet(
data_dir=f'{data_dir}/vegetables_cls',
file_list=f'{data_dir}/vegetables_cls/val_list.txt',
label_list=f'{data_dir}/vegetables_cls/labels.txt',
transforms=eval_transforms)
num_classes = len(train_dataset.labels)
model = pdx.cls.MobileNetV2(num_classes=num_classes)
model.train(num_epochs=10,
train_dataset=train_dataset,
train_batch_size=32,
eval_dataset=eval_dataset,
lr_decay_epochs=[4, 6, 8],
save_interval_epochs=1,
learning_rate=0.025,
save_dir=f'{output_dir}/mobilenetv2',
use_vdl=True)
def CBGetNewCompose():
global AllCompose
global BchangeState
BchangeState = True
AllCompose = transforms.Compose([
transforms.RandomDistort(brightness_range=Brightness,
brightness_prob=1,
contrast_range=Contrastness,
contrast_prob=1,
saturation_range=Saturation,
saturation_prob=1,
hue_range=Hue,
hue_prob=1)
])
if globalimg is not None:
if State is False:
postimg()
draw_img(transimg)
def build_transforms(self, transforms_info, to_rgb=True):
if self.model_type == "classifier":
from paddlex.cls import transforms
elif self.model_type == "detector":
from paddlex.det import transforms
elif self.model_type == "segmenter":
from paddlex.seg import transforms
op_list = list()
for op_info in transforms_info:
op_name = list(op_info.keys())[0]
op_attr = op_info[op_name]
if not hasattr(transforms, op_name):
raise Exception(
"There's no operator named '{}' in transforms of {}".
format(op_name, self.model_type))
op_list.append(getattr(transforms, op_name)(**op_attr))
eval_transforms = transforms.Compose(op_list)
if hasattr(eval_transforms, 'to_rgb'):
eval_transforms.to_rgb = to_rgb
self.arrange_transforms(eval_transforms)
return eval_transforms
def train(model_dir=None, sensitivities_file=None, eval_metric_loss=0.05):
# 下载和解压蔬菜分类数据集
veg_dataset = 'https://bj.bcebos.com/paddlex/datasets/vegetables_cls.tar.gz'
pdx.utils.download_and_decompress(veg_dataset, path='./')
# 定义训练和验证时的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
train_dataset = pdx.datasets.ImageNet(
data_dir='vegetables_cls',
file_list='vegetables_cls/train_list.txt',
label_list='vegetables_cls/labels.txt',
transforms=train_transforms,
shuffle=True)
eval_dataset = pdx.datasets.ImageNet(
data_dir='vegetables_cls',
file_list='vegetables_cls/val_list.txt',
label_list='vegetables_cls/labels.txt',
transforms=eval_transforms)
num_classes = len(train_dataset.labels)
model = pdx.cls.MobileNetV2(num_classes=num_classes)
if model_dir is None:
# 使用imagenet数据集预训练模型权重
pretrain_weights = "IMAGENET"
else:
# 使用传入的model_dir作为预训练模型权重
assert os.path.isdir(model_dir), "Path {} is not a directory".format(
model_dir)
pretrain_weights = model_dir
save_dir = './output/mobilenetv2'
if sensitivities_file is not None:
# DEFAULT 指使用模型预置的参数敏感度信息作为裁剪依据
if sensitivities_file != "DEFAULT":
assert os.path.exists(
sensitivities_file), "Path {} not exist".format(
sensitivities_file)
save_dir = './output/mobilenetv2_prune'
model.train(
num_epochs=10,
train_dataset=train_dataset,
train_batch_size=32,
eval_dataset=eval_dataset,
lr_decay_epochs=[4, 6, 8],
learning_rate=0.025,
pretrain_weights=pretrain_weights,
save_dir=save_dir,
use_vdl=True,
sensitivities_file=sensitivities_file,
eval_metric_loss=eval_metric_loss)
# 说明文档：https://paddlex.readthedocs.io/zh_CN/develop/appendix/parameters.html#gpu
import os
os.environ['CUDA_VISIBLE_DEVICES'] = '0'
from paddlex.cls import transforms
import paddlex as pdx
# 下载和解压蔬菜分类数据集
# veg_dataset = 'https://bj.bcebos.com/paddlex/datasets/vegetables_cls.tar.gz'
# pdx.utils.download_and_decompress(veg_dataset, path='./')
# 定义训练和验证时的transforms
# API说明https://paddlex.readthedocs.io/zh_CN/develop/apis/transforms/cls_transforms.html
train_transforms = transforms.Compose([
transforms.RandomHorizontalFlip(),
transforms.RandomRotate(),
transforms.RandomDistort(),
transforms.Normalize()
])
# eval_transforms = transforms.Compose([
# transforms.Normalize()
# ])
# 定义训练和验证所用的数据集
# API说明：https://paddlex.readthedocs.io/zh_CN/develop/apis/datasets.html#paddlex-datasets-imagenet
train_dataset = pdx.datasets.ImageNet(
data_dir='/home/aistudio/data/data67498/train',
file_list='/home/aistudio/data/data67498/train/train_list.txt',
label_list='/home/aistudio/data/data67498/train/labels.txt',
transforms=train_transforms,
shuffle=True)
# eval_dataset = pdx.datasets.ImageNet(
with open(os.path.join('train_list.txt'), 'w') as f:
for i, cls_fold in enumerate(os.listdir(base)):
cls_base = os.path.join(base, cls_fold)
files = os.listdir(cls_base)
print('{} train num:'.format(cls_fold), len(files))
for pt in files:
img = os.path.join(cls_fold, pt)
info = img + ' ' + str(i) + '\n'
f.write(info)
with open(os.path.join('labels.txt'), 'w') as f:
for i, cls_fold in enumerate(os.listdir(base)):
f.write(cls_fold + '\n')
train_transforms = transforms.Compose(
[transforms.RandomCrop(crop_size=224),
transforms.Normalize()])
train_dataset = pdx.datasets.ImageNet(data_dir=base,
file_list='train_list.txt',
label_list='labels.txt',
transforms=train_transforms,
shuffle=True)
num_classes = len(train_dataset.labels)
model = pdx.cls.ResNet18(num_classes=num_classes)
model.train(num_epochs=20,
train_dataset=train_dataset,
train_batch_size=32,
lr_decay_epochs=[5, 10, 15],
learning_rate=2e-2,
[(xmin, ymax), (xmax, ymax)]
]
if color == "R":
color = (0, 0, 255)
elif color == "G":
color = (0, 255, 0)
elif color == "B":
color = (255, 0, 0)
for l in lines:
cv2.line(img, l[0], l[1], color, 2)
cls_model = pdx.load_model('output/gear_clas/')
cls_trans = cls_transforms.Compose([
# cls_transforms.Resize(),
cls_transforms.Normalize()
])
det_model = pdx.load_model('output/gear_det/')
det_trans = det_transforms.Compose([
det_transforms.Resize(),
det_transforms.Normalize()
])
vid_dir = "/home/aistudio/plane/vid-split/train/"
itv = 5
bs = 4
for vid_name in tqdm(os.listdir(vid_dir)):
print(vid_name)
vidcap = cv2.VideoCapture(osp.join(vid_dir, vid_name))
import os
# 选择使用0号卡
os.environ['CUDA_VISIBLE_DEVICES'] = '0'
import paddle.fluid as fluid
from paddlex.cls import transforms
import paddlex as pdx
# 下载和解压蔬菜分类数据集
veg_dataset = 'https://bj.bcebos.com/paddlex/datasets/vegetables_cls.tar.gz'
pdx.utils.download_and_decompress(veg_dataset, path='./')
# 定义训练和验证时的transforms
train_transforms = transforms.Compose(
[transforms.RandomCrop(crop_size=224),
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
train_dataset = pdx.datasets.ImageNet(
data_dir='vegetables_cls',
file_list='vegetables_cls/train_list.txt',
label_list='vegetables_cls/labels.txt',
transforms=train_transforms,
shuffle=True)
eval_dataset = pdx.datasets.ImageNet(data_dir='vegetables_cls',
file_list='vegetables_cls/val_list.txt',
from paddlex.cls import transforms
import paddlex
import cv2
base = './data'
train_transforms = transforms.Compose([
transforms.ResizeByShort(256),
transforms.RandomCrop(crop_size=224),
transforms.RandomRotate(rotate_range=30, prob=0.5),
transforms.RandomDistort(),
transforms.Normalize()
])
train_dataset = paddlex.datasets.ImageNet(data_dir=base,
file_list='train_list.txt',
label_list='labels.txt',
transforms=train_transforms,
shuffle=True)
model = paddlex.load_model('weights/final')
im = cv2.imread('test.jpg')
print(model.evaluate(eval_dataset=train_dataset))
import paddle.fluid as fluid
import seaborn as sns
import numpy as np
import matplotlib.pyplot as plt
from PIL import Image
#定义训练/验证图像处理流程transforms
from paddlex.cls import transforms
train_transforms = transforms.Compose([
transforms.RandomCrop(crop_size=224),
transforms.RandomHorizontalFlip(),
transforms.RandomDistort(brightness_range=0.9,
brightness_prob=0.5,
contrast_range=0.9,
contrast_prob=0.5,
saturation_range=0.9,
saturation_prob=0.5,
hue_range=18,
hue_prob=0.5),
transforms.Normalize()
])
eval_transforms = transforms.Compose([
transforms.ResizeByShort(short_size=256),
transforms.CenterCrop(crop_size=224),
transforms.Normalize()
])
# 定义dataset加载图像分类数据集
train_dataset = pdx.datasets.ImageNet(data_dir='garbage_data',
x = np.asarray(x).astype('float32')
#x = cv2.imread("work/"+path,cv2.IMREAD_COLOR)
x = cv2.cvtColor(x, cv2.COLOR_RGB2BGR) / 255.0
x = (cv2.resize(x, (1024, 1024)) - 0.5) / 0.5
return x
transform_ops = transforms.Compose([
#transforms.Normalize([0.5,0.5,0.5],[0.5,0.5,0.5]) # this will do 1/255.0
transforms.RandomHorizontalFlip(prob=0.5),
transforms.RandomRotate(rotate_range=30, prob=0.5),
transforms.RandomCrop(crop_size=224,
lower_scale=0.7,
lower_ratio=3. / 4,
upper_ratio=4. / 3),
transforms.RandomDistort(brightness_range=0.1,
brightness_prob=0.5,
contrast_range=0.1,
contrast_prob=0.5,
saturation_range=0.1,
saturation_prob=0.0,
hue_range=0.1,
hue_prob=0.0)
])
def transform(img):
#print("before transform: ",img.shape)
img = transform_ops(img)[0]
#print("after transform: ",img.shape)
return img
