Machine learning Tensorflow训练时间与我的代码有关
目的:区分一个细胞是寄生的(Mallia ed)还是未感染的 数据集来自Kaggle: 进口:Machine learning Tensorflow训练时间与我的代码有关,machine-learning,neural-network,artificial-intelligence,conv-neural-network,tensorflow2.0,Machine Learning,Neural Network,Artificial Intelligence,Conv Neural Network,Tensorflow2.0,目的:区分一个细胞是寄生的(Mallia ed)还是未感染的 数据集来自Kaggle: 进口: import numpy as np import pandas as pd import matplotlib.pyplot as plt import seaborn as sns import os from sklearn.metrics import classification_report, confusion_matrix from tensorflow.keras.models
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import os
from sklearn.metrics import classification_report, confusion_matrix
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout, MaxPool2D, Conv2D, Flatten
from tensorflow.keras.callbacks import EarlyStopping
from tensorflow.keras.preprocessing.image import ImageDataGenerator
from matplotlib.image import imread
路径:
file_path = "/whatever-you-store-the-data/cell_images/"
test_path = "/whatever-you-store-the-data/cell_images/test/"
train_path = "/whatever-you-store-the-data/cell_images/train/"
图像的平均大小为(130、130、3)#(宽度、高度、颜色通道):
图像数据生成器:
image_gen = ImageDataGenerator(rotation_range=20,
width_shift_range=0.1,
height_shift_range=0.1,
shear_range=0.1,
zoom_range=0.1,
horizontal_flip=True,
vertical_flip=True,
fill_mode="nearest")
模型:
model = Sequential()
model.add(Conv2D(32, (3, 3), input_shape=image_shape, activation="relu"))
model.add(MaxPool2D((2, 2)))
model.add(Dropout(0.5))
model.add(Conv2D(64, (3, 3), activation="relu"))
model.add(MaxPool2D((2, 2)))
model.add(Dropout(0.2))
model.add(Conv2D(64, (3, 3), activation="relu"))
model.add(MaxPool2D((2, 2)))
model.add(Dropout(0.2))
model.add(Flatten())
model.add(Dense(128, activation="relu"))
model.add(Dropout(0.5))
model.add(Dense(1, activation="sigmoid"))
model.compile(loss="binary_crossentropy",
optimizer="adam",
metrics=["accuracy"])
提前停止回调:
early_stop = EarlyStopping(monitor="val_loss",
patience=5,
verbose=1,
mode="min")
发电机:
train_image_gen = image_gen.flow_from_directory(train_path,
target_size=image_shape[:2],
color_mode="rgb",
batch_size=32,
class_mode="binary")
test_image_gen = image_gen.flow_from_directory(test_path,
target_size=image_shape[:2],
color_mode="rgb",
batch_size=32,
class_mode="binary",
shuffle=False)
拟合模型:
results = model.fit_generator(train_image_gen,
epochs=20,
validation_data=test_image_gen,
callbacks=[early_stop])
以下是输出:
Epoch 1/20
390/Unknown - 9339s 24s/step - loss: 4.4232 - accuracy: 0.5135
首先,为什么它是n/未知的形式,更重要的是,为什么它需要9339秒。这不是问题所在,问题在于为什么训练的估计时间一直在增加,开始于240秒左右,然后随着时间的推移而增加,最终达到9339秒。这里发生了什么?我该如何解决这个问题?你有一个公共笔记本可以共享吗?你可能想退房。希望有帮助@Khoo,在您的代码中,您正在使用
Pickle
文件。但是站点中是否存在Pickle文件。
Epoch 1/20
390/Unknown - 9339s 24s/step - loss: 4.4232 - accuracy: 0.5135