如何使用GPU運行TensorFlow

Jabes關注

2019.12.15 15:17:03字數 635閱讀 5,778

如何使用GPU運行TensorFlow

這里主要考慮如何讓tensorflow和keras運行在GPU上：

1. 檢查顯卡類型和計算能力**

查看筆記本顯卡型號，以及計算能力
下載個 GPU 查看器，名字為TechPowerUp GPU-Z
下載地址是：
https://www.techpowerup.com/download/gpu-z/
我的電腦顯示是這樣的：

 

image.png

我筆記本獨立顯卡產品型號是NVIDA GeForce MX250，但是核心型號是GP108。

 

 

image.png

確定對應顯卡 GPU 的計算能力
去 NVIDIA 官網查看 https://developer.nvidia.com/cuda-gpus
不過我沒有查到計算能力，只看到了相關產品參數https://www.geforce.com/hardware/notebook-gpus/geforce-mx250/features

2. 安裝CUDA

下載地址：https://developer.nvidia.com/cuda-downloads
安裝包有點大，下載慢，需要耐心等待。安裝 cuda 的時候，會詢問是否安裝顯卡驅動，說明 cuda 安裝程序里包含了的顯卡驅動；
建議先不要安裝 cuda 里的顯卡驅動，待安裝完 cuda 后，執行例子程序，如果報錯再檢查顯卡驅動是否正確，避免覆蓋原來的顯卡驅動。

安裝完后執行 nvcc -V 檢查

 

 

 

 

image.png

然后運行例子：
例子在C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v10.2\extras\demo_suite/deviceQuery.exe

 

 

 

至此已經安裝 cuda 成功

3. 安裝cuDNN

cuDNN 是一個為了優化深度學習計算的類庫，它能將模型訓練的計算優化之后，再通過 CUDA 調用 GPU 進行運算，當然你也可直接使用 GUDA，而不通過 cuDNN ，但運算效率會低好多

cuDNN 下載地址:https://developer.nvidia.com/cudnn
下載過程會有一堆調查問卷，友好度不好！選擇跟CUDA對應的版本 cuDNN
將文件解壓，例如解壓到D:\software\cuda
解壓后有三個子目錄:bin,include,lib。將bin目錄(例如 D:\software\cuda\bin)添加到環境變量 PATH 中。或者將三個文件夾的內容拷貝到CUDA對應的目錄即可。

 

 

4. 重新安裝tensorflow

之前安裝的tensorflow這樣安裝的pip install tensorflow==1.13.0，現在我換成了pip install tensorflow-gpu==1.15.0.

5. 測試代碼

最后對GPU進行一下測試，使用如下代碼：

#導入相關的庫 import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data import os import time from tensorflow.contrib.tensorboard.plugins import projector import matplotlib.pyplot as plt import numpy as np #這里用slim這個API來進行卷積網絡構建 slim = tf.contrib.slim #定義卷積神經網絡模型 #網絡架構是卷積網絡--最大池化--卷積網絡--最大池化---flatten---MLP-softmax的全連接MLP def model(inputs, is_training, dropout_rate, num_classes, scope='Net'): inputs = tf.reshape(inputs, [-1, 28, 28, 1]) with tf.variable_scope(scope): with slim.arg_scope([slim.conv2d, slim.fully_connected], normalizer_fn=slim.batch_norm): net = slim.conv2d(inputs, 32, [5, 5], padding='SAME', scope='conv1') net = slim.max_pool2d(net, 2, stride=2, scope='maxpool1') tf.summary.histogram("conv1", net) net = slim.conv2d(net, 64, [5, 5], padding='SAME', scope='conv2') net = slim.max_pool2d(net, 2, stride=2, scope='maxpool2') tf.summary.histogram("conv2", net) net = slim.flatten(net, scope='flatten') fc1 = slim.fully_connected(net, 1024, scope='fc1') tf.summary.histogram("fc1", fc1) net = slim.dropout(fc1, dropout_rate, is_training=is_training, scope='fc1-dropout') net = slim.fully_connected(net, num_classes, scope='fc2') return net, fc1 def create_sprite_image(images): """更改圖片的shape""" if isinstance(images, list): images = np.array(images) img_h = images.shape[1] img_w = images.shape[2] n_plots = int(np.ceil(np.sqrt(images.shape[0]))) sprite_image = np.ones((img_h * n_plots, img_w * n_plots)) for i in range(n_plots): for j in range(n_plots): this_filter = i * n_plots + j if this_filter < images.shape[0]: this_img = images[this_filter] sprite_image[i * img_h:(i + 1) * img_h, j * img_w:(j + 1) * img_w] = this_img return sprite_image def vector_to_matrix_mnist(mnist_digits): """把正常的mnist數字圖片(batch,28*28)這個格式，轉換為新的張量形狀(batch,28,28)""" return np.reshape(mnist_digits, (-1, 28, 28)) def invert_grayscale(mnist_digits): """處理下圖片顏色，黑色變白，白色邊黑""" return 1 - mnist_digits if __name__ == "__main__": # 定義參數 #學習率 learning_rate = 1e-4 #定義迭代參數 total_epoch = 600 #定義批量 batch_size = 200 #程序運行中打印頻率 display_step = 20 #程序運行中保存結果的頻率 save_step = 100 load_checkpoint = False checkpoint_dir = "checkpoint" checkpoint_name = 'model.ckpt' #結果存放的路徑 logs_path = "logs" #定義我們使用多少個圖片 test_size = 10000 #定義第二層路徑 projector_path = 'projector' # 網絡參數 n_input = 28 * 28 # 每個圖片是28*28個像素，也就是784個特征 n_classes = 10 # MNIST數據集有0-9是個類別的結果 dropout_rate = 0.5 # Dropout的比率 mnist = input_data.read_data_sets('MNIST-data', one_hot=True) # 定義計算圖 x = tf.placeholder(tf.float32, [None, n_input], name='InputData') y = tf.placeholder(tf.float32, [None, n_classes], name='LabelData') is_training = tf.placeholder(tf.bool, name='IsTraining') keep_prob = dropout_rate logits, fc1 = model(x, is_training, keep_prob, n_classes) with tf.name_scope('Loss'): loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=logits, labels=y)) tf.summary.scalar("loss", loss) with tf.name_scope('Accuracy'): correct_pred = tf.equal(tf.argmax(logits, 1), tf.argmax(y, 1)) accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32)) tf.summary.scalar("accuracy", accuracy) optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(loss) projector_dir = os.path.join(logs_path, projector_path) path_metadata = os.path.join(projector_dir,'metadata.tsv') path_sprites = os.path.join(projector_dir, 'mnistdigits.png') # 檢查結果目錄的狀態 if not os.path.exists(projector_dir): os.makedirs(projector_dir) # 這里進行嵌入 mnist_test = input_data.read_data_sets('MNIST-data', one_hot=False) batch_x_test = mnist_test.test.images[:test_size] batch_y_test = mnist_test.test.labels[:test_size] embedding_var = tf.Variable(tf.zeros([test_size, 1024]), name='embedding') assignment = embedding_var.assign(fc1) config = projector.ProjectorConfig() embedding = config.embeddings.add() embedding.tensor_name = embedding_var.name embedding.metadata_path = os.path.join(projector_path,'metadata.tsv') embedding.sprite.image_path = os.path.join(projector_path, 'mnistdigits.png') embedding.sprite.single_image_dim.extend([28,28]) # 初始化變量 init = tf.global_variables_initializer() # 'Saver' op to save and restore all the variables saver = tf.train.Saver() merged_summary_op = tf.summary.merge_all() # 運行計算圖 with tf.Session() as sess: sess.run(init) # Restore model weights from previously saved model prev_model = tf.train.get_checkpoint_state(checkpoint_dir) if load_checkpoint: if prev_model: saver.restore(sess, prev_model.model_checkpoint_path) print('Checkpoint found, {}'.format(prev_model)) else: print('No checkpoint found') summary_writer = tf.summary.FileWriter(logs_path, graph=tf.get_default_graph()) projector.visualize_embeddings(summary_writer, config) start_time = time.time() # 開始訓練 for epoch in range(total_epoch): batch_x, batch_y = mnist.train.next_batch(batch_size) # reshapeX = np.reshape(batch_x, [-1, 28, 28, 1]) # 開始反向傳播算法 sess.run(optimizer, feed_dict={x: batch_x, y: batch_y, is_training: True}) if epoch % display_step == 0: # 計算損失和精度 cost, acc, summary = sess.run([loss, accuracy, merged_summary_op], feed_dict={x: batch_x, y: batch_y, is_training: False}) elapsed_time = time.time() - start_time start_time = time.time() print('epoch {}, training accuracy: {:.4f}, loss: {:.5f}, time: {}' .format(epoch, acc, cost, elapsed_time)) summary_writer.add_summary(summary, epoch) if epoch % save_step == 0: # 保存訓練的結果 sess.run(assignment, feed_dict={x: mnist.test.images[:test_size], y: mnist.test.labels[:test_size], is_training: False}) checkpoint_path = os.path.join(checkpoint_dir, checkpoint_name) save_path = saver.save(sess, checkpoint_path) print("Model saved in file: {}".format(save_path)) # 保存結果 saver.save(sess, os.path.join(logs_path, "model.ckpt"), 1) # 創建可視化的圖片 to_visualise = batch_x_test to_visualise = vector_to_matrix_mnist(to_visualise) to_visualise = invert_grayscale(to_visualise) sprite_image = create_sprite_image(to_visualise) # 保存可視化的圖片 plt.imsave(path_sprites, sprite_image, cmap='gray') # 寫文件 with open(path_metadata, 'w') as f: f.write("Index\tLabel\n") for index, label in enumerate(batch_y_test): f.write("%d\t%d\n" % (index, label)) print("訓練完成") 

訓練過程還是很快的。
最后再看看t-SNE：

 

 

 

6. 最后看看運行中GPU的情況

這個可直接通過之前下載的GPU-Z軟件查看：