为此,您需要编写一个自定义数据生成器。
导入必要的库
import os
import pandas as pd
from skimage.io import imread # Used for image processing
from skimage.transform import resize # Used for image processing
import json
import numpy as np
定义我们自己的数据生成器
我点击了this链接以了解如何执行此操作。并根据您的问题对其进行定制。
我们需要填写以下功能。
class DataGenerator(tf.keras.utils.Sequence):
'Generates data for Keras'
def __init__(self,directory,target_json,batch_size=32,target_size=(128,128),shuffle=True):
...
def __len__(self):
'Denotes the number of batches per epoch'
...
def __getitem__(self,index):
'Generate one batch of data'
...
def on_epoch_end(self):
'Updates indexes after each epoch'
...
def __data_generation(self,list_paths,list_paths_wo_ext):
'Generates data containing batch_size samples' # X : (n_samples,*dim,n_channels)
...
让我们看看我们定义了哪些变量
self.target_size = # Final size of the images
self.batch_size = # Batch size
self.target_json = # Path to the json file
self.directory = # Where the training data is
self.img_paths = # Contains image paths with extension
self.img_paths_wo_ext = # Contains the image paths without extension
self.targets = # The dataframe containing targets loaded from the json
self.shuffle = # Shuffle data at start of each epoch?
JSON文件
您的JSON文件必须完全以这种格式。这也可能正是您拥有的。但是请确保它是这种格式的100%。
{'dir20': {'frame_00001_rgb': {'x': 363.693829827852,'y': 278.2191728859505},'frame_00002_rgb': {'x': 330.9709780765119,'y': 283.34142472069004}},'dir21': {'frame_00001_rgb': {'x': 363.693829827852,'dir22': {'frame_00001_rgb': {'x': 363.693829827852,'dir23': {'frame_00001_rgb': {'x': 363.693829827852,'dir24': {'frame_00001_rgb': {'x': 212.5232358,'y': 156.3342191728855},'frame_00002_rgb': {'x': 230.6949709780735,'y': 253.7534142472069}}}
接下来,我们需要将其转换为熊猫数据框。为此,我们定义以下功能。由于文件的性质,它有点复杂。但是,这就是正在发生的事情。
- 加载json并创建一个数据框,其中包含诸如
dir20.frame_00002_rgb.x
之类的列。
- 通过将列划分为3个级别(例如dir20,frame_00002,x)来创建多索引
- 使用
stack
将dir*
和frame_*
都作为索引
- 重新设置索引格式,使其包含每个图像的完整路径,并且每个记录都有两列(
x
和y
)。
def json_to_df(json_path,directory):
with open(json_path,'r') as f:
s = json.load(f)
df = pd.io.json.json_normalize(s)
ind = pd.MultiIndex.from_tuples([col.split('.') for col in df.columns])
df.columns = ind
df = df.stack(level=[0,1])
df = df.set_index(df.index.droplevel(0))
df = df.set_index(pd.Index([os.path.sep.join([directory]+list(c)) for c in df.index.values]))
return df
其余代码
我不会深入探讨其他部分的情况,因为这很简单。但实际上,通过读取图像,调整大小并从生成的数据帧中获取正确的x
,y
值,我们实际上是获得了一批数据。
完整代码
这是数据生成器的完整代码。
class DataGenerator(tf.keras.utils.Sequence):
'Generates data for Keras'
def __init__(self,shuffle=True):
'Initialization'
self.target_size = target_size
self.batch_size = batch_size
self.target_json = target_json
self.directory = directory
self.img_paths = []
self.img_paths_wo_ext = []
for root,dirs,files in os.walk(directory):
for file in files:
if file.lower().endswith(".jpg") or file.lower().endswith(".png"):
self.img_paths.append(os.path.join(root,file))
self.img_paths_wo_ext.append(os.path.splitext(os.path.join(root,file))[0])
def json_to_df(json_path,1])
df = df.set_index(df.index.droplevel(0))
df = df.set_index(pd.Index([os.path.sep.join([directory]+list(c)) for c in df.index.values]))
return df
self.targets = json_to_df(self.target_json,self.directory)
self.shuffle = shuffle
self.on_epoch_end()
def __len__(self):
'Denotes the number of batches per epoch'
return int(np.floor(len(self.img_paths) / self.batch_size))
def __getitem__(self,index):
'Generate one batch of data'
# Generate indexes of the batch
indexes = self.indexes[index*self.batch_size:(index+1)*self.batch_size]
# Find list of IDs
list_paths = [self.img_paths[k] for k in indexes]
list_paths_wo_ext = [self.img_paths_wo_ext[k] for k in indexes]
# Generate data
X,y = self.__data_generation(list_paths,list_paths_wo_ext)
return X,y
def on_epoch_end(self):
'Updates indexes after each epoch'
self.indexes = np.arange(len(self.img_paths))
if self.shuffle == True:
np.random.shuffle(self.indexes)
def __data_generation(self,n_channels)
# Initialization
X = np.empty((self.batch_size,*self.target_size,3))
y = self.targets.loc[list_paths_wo_ext].values
# Generate data
for i,ID in enumerate(list_paths):
# Store sample
X[i,] = resize(imread(ID),self.target_size)
return X,y
使用数据生成器
这是您使用数据生成器的方式。
train_datagen = iter(DataGenerator(train_data_dir,'./train/data.json',batch_size=2))
x,y = next(train_datagen)
print(x)
print(y)
给出,
[[0.01377145 0.01377145 0.01377145]
[0.00242393 0.00242393 0.00242393]
[0. 0. 0. ]
...
[0.0037837 0.0037837 0.0037837 ]
[0.0037837 0.0037837 0.0037837 ]
[0.0037837 0.0037837 0.0037837 ]]
...
[[0.37398897 0.3372549 0.17647059]
[0.38967525 0.35294118 0.19215686]
[0.42889093 0.39215686 0.23137255]
...
[0.72156863 0.62889093 0.33085172]
[0.71372549 0.61176471 0.31764706]
[0.70588235 0.59359681 0.30340074]]]]
[[363.69382983 278.21917289]
[330.97097808 283.34142472]]
本文链接:https://www.f2er.com/2851342.html