TensorFlow
没有胡子的猫
这个作者很懒,什么都没留下…
展开
-
使用TensorFlow实现GRU
使用TensorFlow实现GRU使用Cell实现# 以Cell方式实现GRU# %%import osimport numpy as npimport tensorflow as tffrom tensorflow import kerasfrom tensorflow.keras import layers, losses, optimizers, Sequential# 指定GPUos.environ["CUDA_VISIBLE_DEVICES"] = "2"tf.rand原创 2021-08-26 17:04:53 · 3930 阅读 · 0 评论 -
使用TensorFlow实现LSTM
使用TensorFlow实现LSTM使用Cell实现# 以Cell方式实现LSTM# %%import osimport numpy as npimport tensorflow as tffrom tensorflow import kerasfrom tensorflow.keras import layers, losses, optimizers, Sequential# 指定GPUos.environ["CUDA_VISIBLE_DEVICES"] = "1"tf.ra原创 2021-08-26 17:04:06 · 2591 阅读 · 0 评论 -
使用TensorFlow实现RNN
使用TensorFlow实现RNN使用Cell实现# 以cell方式实现RNN# %%import osimport numpy as npimport tensorflow as tffrom tensorflow import kerasfrom tensorflow.keras import layers, losses, optimizers, Sequential# 指定GPUos.environ["CUDA_VISIBLE_DEVICES"] = "1"tf.rand原创 2021-08-26 17:03:45 · 772 阅读 · 0 评论 -
tensorflow.keras.Model compile fit evaluate应用
tensorflow.keras.Model compile fit evaluate应用import tensorflow as tffrom tensorflow.keras import datasets, layers, optimizers, Sequential, metrics数据预处理def preprocess(x, y): """ x is a simple image, not a batch """ x = tf.cast(x, dt原创 2021-08-24 17:34:59 · 383 阅读 · 0 评论 -
tensorflow.keras metrics应用
tensorflow.keras metrics应用不使用metrics实现的博客参考:import tensorflow as tffrom tensorflow.keras import datasets, layers, optimizers, Sequential, metrics更改数据类型并归一化def preprocess(x, y): x = tf.cast(x, dtype=tf.float32) / 255. y = tf.cast(y, dt原创 2021-08-24 17:33:53 · 418 阅读 · 0 评论 -
tensorflow.keras.layers keras.Model 自定义层应用
tensorflow.keras.layers keras.Model 自定义层应用import tensorflow as tffrom tensorflow.keras import datasets, layers, optimizers, Sequential, metricsfrom tensorflow import keras数据预处理def preprocess(x, y): """ x is a simple image, not a batch原创 2021-08-24 17:33:11 · 902 阅读 · 0 评论 -
TensorFlow常用操作
指定GPU终端指定CUDA_VISIBLE_DEVICES=0 nohup python demo.py >> base_log.out 2>&1 &程序指定import osos.environ["CUDA_VISIBLE_DEVICES"] = "1"TensorFlow常用操作检测GPU是否可用import tensorflow as tftf.test.is_gpu_available()...原创 2021-08-24 17:31:59 · 95 阅读 · 0 评论 -
Tensorflow模型保存与加载
Tensorflow模型保存与加载import osos.environ['TF_CPP_MIN_LOG_LEVEL']='2'import tensorflow as tffrom tensorflow.keras import datasets, layers, optimizers, Sequential, metricsdef preprocess(x, y): """ x is a simple image, not a batch """原创 2021-08-24 17:30:56 · 417 阅读 · 0 评论 -
TensorFlow实现手写数字识别
TensorFlow实现手写数字识别import tensorflow as tffrom tensorflow.keras import datasets, layers, optimizers, Sequential, metricsimport matplotlib.pyplot as plt# 设置GPU使用方式# 获取GPU列表gpus = tf.config.experimental.list_physical_devices('GPU')print(gpus)if g原创 2021-08-24 17:30:01 · 533 阅读 · 0 评论 -
TensorFlow学习笔记(一)TensorFlow基础
TensorFlow学习笔记(一)TensorFlow基础import tensorflow as tfimport tensorflow.keras as kerasimport tensorflow.keras.layers as layers# physical_devices = tf.config.experimental.list_physical_devices('GPU')# assert len(physical_devices) > 0, "Not enough GPU原创 2021-08-24 17:29:04 · 503 阅读 · 1 评论