在这里，我使用了 PIL库来加载图像，并且它不是用于图像数据集的单个数据，而是使用 numpy库转换numpy数组。它非常适合单个图像数据。
现在，我想从图像数据集转换为numpy数组。将在何处显示培训，测试和验证数据。
下面，我分享了将单个图像数据转换为numpy数组的代码。
导入了所需的库
from PIL import Image
from numpy import asarray
加载图像
image = Image.open('flower/1.jpg')
将图像转换为numpy数组
data = asarray(image)
#data is array format of image
答案 0 :(得分：1)
如果您只想将numpy数组转换回image，那么以下代码片段应该可以工作。如果要复制整个数据集的过程，则需要在每个图像上调用它。如何执行取决于您要构建的模型（图像分类，对象检测等）以及构建它所用的模型（tensorflow，theano等）
解决方案1
from PIL import Image
from numpy import asarray
image = Image.open('flower/1.jpg')
data = asarray(image)
img_w, img_h = 200, 200
img = Image.fromarray(data, 'RGB')
img.save('test.png')
img.show()
由于您正在处理图像分类问题。以下代码可以很好地为您服务。根据您的问题对其进行自定义。我已经在代码中注释了您需要进行更改的地方。
解决方案2
from PIL import ImageFile
ImageFile.LOAD_TRUNCATED_IMAGES = True
import os
import numpy as np
import pandas as pd
import cv2
from glob import glob
import tensorflow as tf
from tensorflow.keras.layers import *
from tensorflow.keras.applications import MobileNetV2 #Change Here: Select the classification architecture you need
from tensorflow.keras.callbacks import ModelCheckpoint, ReduceLROnPlateau
from tensorflow.keras.optimizers import Adam
from sklearn.model_selection import train_test_split
def build_model(size, num_classes):
inputs = Input((size, size, 3))
backbone = MobileNetV2(input_tensor=inputs, include_top=False, weights="imagenet") #Change Here: Select the classification architecture you need
backbone.trainable = True
x = backbone.output
x = GlobalAveragePooling2D()(x)
x = Dropout(0.2)(x) #Chage Here: Try different droput values b/w .2 to .8
x = Dense(1024, activation="relu")(x)
x = Dense(num_classes, activation="softmax")(x)
model = tf.keras.Model(inputs, x)
return model
def read_image(path, size):
image = cv2.imread(path, cv2.IMREAD_COLOR)
train_datagen = ImageDataGenerator(rescale=1./255,
rotation_range=30, #Change Here: Select any rotation range b/w 10 to 90
zoom_range = 0.3,
width_shift_range=0.2, #Change Here: Select width shift as per your images. My advice- try b/w .2 to .5
height_shift_range=0.2, #Change Here: Select height shift as per your images., My advice try b/w .2 to .5
horizontal_flip = 'true')
image = train_datagen.flow_from_directory(path, shuffle=False, batch_size=10, seed=10) #Change Here: Select batch_size as per your need
image = cv2.resize(image, (size, size))
image = image / 255.0
image = image.astype(np.float32)
return image
def parse_data(x, y):
x = x.decode()
num_class = 120 #Change Here: num_class should be equal to types of blood cells you have in your dataset i.e. number of labels
size = 224 #Change Here: Select size as per your chosen model architecture
image = read_image(x, size)
label = [0] * num_class
label[y] = 1
label = np.array(label)
label = label.astype(np.int32)
return image, label
def tf_parse(x, y):
x, y = tf.numpy_function(parse_data, [x, y], [tf.float32, tf.int32])
x.set_shape((224, 224, 3))
y.set_shape((120))
return x, y
def tf_dataset(x, y, batch=8): #Change Here: Choose default batch size as per your needs
dataset = tf.data.Dataset.from_tensor_slices((x, y))
dataset = dataset.map(tf_parse)
dataset = dataset.batch(batch)
dataset = dataset.repeat()
return dataset
if __name__ == "__main__":
path = "/content/gdrive/My Drive/Dog Breed Classification/" #Change Here: Give path to your parent directory
train_path = os.path.join(path, "train/*")
test_path = os.path.join(path, "test/*")
labels_path = os.path.join(path, "labels.csv") #Change Here: Give name of your csv file
labels_df = pd.read_csv(labels_path)
breed = labels_df["breed"].unique() #Change Here: replace breed with the column name, denoting class, in your csv file
print("Number of Breed: ", len(breed))
breed2id = {name: i for i, name in enumerate(breed)} #Change Here: replace breed & id with the column names denoting class & image file in your csv file
#repeat the same every place where breed or id is mentioned
ids = glob(train_path)
labels = []
for image_id in ids:
# print(image_id,"\n\n\n")
image_id = image_id.split("/")[-1]
breed_name = list(labels_df[labels_df.id == image_id]["breed"])[0]
breed_idx = breed2id[breed_name]
labels.append(breed_idx)
## Spliting the dataset
train_x, valid_x = train_test_split(ids, test_size=0.2, random_state=42) #Change Here: select test size as per your need. My advice go between .2 to .3
train_y, valid_y = train_test_split(labels, test_size=0.2, random_state=42)
## Parameters
size = 224 #Change Here: Select size as per your chosen model architecture
num_classes = 120 #Change Here: num_class should be equal to types of blood cells you have in your dataset i.e. number of labels
lr = 1e-4 #Change Here: Select as per you need. My advice chose any where b/w 1e-4 to 1e-2
batch = 16 #Change Here: Select as per your need
epochs = 50 #Change Here: Select as per your need
## Model
model = build_model(size, num_classes)
model.compile(loss="categorical_crossentropy", optimizer=Adam(lr), metrics=["acc"])
# model.summary()
## Dataset
train_dataset = tf_dataset(train_x, train_y, batch=batch)
valid_dataset = tf_dataset(valid_x, valid_y, batch=batch)
## Training
callbacks = [
ModelCheckpoint("/content/gdrive/My Drive/Dog Breed Classification/Model/model-1-{epoch:02d}.h5", #Change Here :Give the path where you want to store your model
verbose=1, save_best_only=True),
ReduceLROnPlateau(factor=0.1, patience=5, min_lr=1e-6)] #Change Here: Set factor, patience, min_lr as per your need. My advice leave as it is and then change to see if model performance improves.
train_steps = (len(train_x)//batch) + 1
valid_steps = (len(valid_x)//batch) + 1
model.fit(train_dataset,
steps_per_epoch=train_steps,
validation_steps=valid_steps,
validation_data=valid_dataset,
epochs=epochs,
callbacks=callbacks)