深度学习模型训练非常慢的Jetson Nano
提问于 2019-12-13 16:49:12
我最近买了一台Jetson Nano，我对它的一切都很惊讶。但我不知道发生了什么，因为我用keras创建了一个非常简单的神经网络，它需要很长的时间。我知道这需要很长时间，因为我在PC的CPU上运行了相同的ANN，而且它比jetson nano还要快。
代码如下：
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
dataset = pd.read_csv('Churn_Modelling.csv')
X = dataset.iloc[:, 3:13].values
y = dataset.iloc[:, 13].values
from sklearn.preprocessing import LabelEncoder, OneHotEncoder
labelencoder_X_1 = LabelEncoder()
X[:, 1] = labelencoder_X_1.fit_transform(X[:, 1])
labelencoder_X_2 = LabelEncoder()
X[:, 2] = labelencoder_X_2.fit_transform(X[:, 2])
onehotencoder = OneHotEncoder(categorical_features = [1])
X = onehotencoder.fit_transform(X).toarray()
X = X[:, 1:]
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 0)
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)
from tensorflow import keras
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense
classifier = Sequential()
classifier.add(Dense(units = 6, kernel_initializer = 'uniform', activation = 'relu', input_dim = 11))
classifier.add(Dense(units = 6, kernel_initializer = 'uniform', activation = 'relu'))
classifier.add(Dense(units = 1, kernel_initializer = 'uniform', activation = 'sigmoid'))
classifier.compile(optimizer = 'adam', loss = 'binary_crossentropy', metrics = ['accuracy'])
classifier.fit(X_train, y_train, batch_size = 10, epochs = 100)
y_pred = classifier.predict(X_test)
y_pred = (y_pred > 0.5)当然，我应该提到的是，我正确地安装了TensorFlow GPU库，而不是普通的TensorFlow，实际上我使用了这个链接中的资源：TensorFlow GPU Jetson Nano
回答 2
Stack Overflow用户
发布于 2020-01-01 12:27:42
Jetson Nano主要用于推理。即使训练是可能的，也不是首选的。这个link可能会有所帮助。您可以尝试使用Nvidia的Transfer Learning Toolkit和Deepstream，在Nano上实现理想和高效的使用。
Stack Overflow用户
发布于 2019-12-13 18:06:06
页面原文内容由Stack Overflow提供。腾讯云小微IT领域专用引擎提供翻译支持
原文链接：
https://stackoverflow.com/questions/59326722
复制相关文章
点击加载更多
腾讯云开发者
