Question

我最近购买了Jetson Nano，对此一切感到惊讶。但是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，并且它花费了很长时间。我知道花了很长时间，因为我在PC的CPU中运行了相同的ANN，并且它比jetson nano更快。

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)

我应该提到，当然，我正确安装了TensorFlow GPU库，而不是正常的TensorFlow，实际上，我使用了以下链接中的资源：TensorFlow GPU Jetson Nano

Answer 1

Jetson Nano主要用于推理。即使可能，也不优选训练。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上实现理想和有效的使用。

Answer 2

@Juan Carlos Jchr

嘿，只需选中https://stackexchange.com/sites

我认为您的问题会在这里得到更好的回答：https://ai.stackexchange.com/

深度学习模型训练速度非常慢的Jetson Nano

2 个答案: