Google Cloud от Collab до Real TPU Странное имя ошибки - PullRequest
Новая
       67

Google Cloud от Collab до Real TPU Странное имя ошибки

0 голосов
/ 08 мая 2020

Итак, я использую GCP с процессором и графическим процессором, но решил попробовать TPU, поэтому я начал создавать виртуальную машину, затем установить все необходимые библиотеки python, затем создать TPU и попробовать с этой треской (Image Generi c Classification), (Я уже пробовал этот код в Google Collab и работал, но на реальном TPU получил ошибку tan 

%tensorflow_version 2.x
import tensorflow as tf
tf.compat.v1.enable_eager_execution()
# importing libraries 
from keras.preprocessing.image import ImageDataGenerator 
from keras.models import Sequential 
from keras.layers import Conv2D, MaxPooling2D 
from keras.layers import Activation, Dropout, Flatten, Dense 
from keras import backend as K 
print("TF version:", tf.__version__)
import os
import pprint # for pretty printing our device stats

if 'COLAB_TPU_ADDR' not in os.environ:
    print('ERROR: Not connected to a TPU runtime; please see the first cell in this notebook for instructions!')
else:
    tpu_address = 'grpc://' + os.environ['tpu1']
    print ('TPU address is', tpu_address)

    with tf.compat.v1.Session(tpu_address) as session:
      devices = session.list_devices()

    print('TPU devices:')
    pprint.pprint(devices)

tpu = tf.distribute.cluster_resolver.TPUClusterResolver()  # TPU detection
print('Running on TPU ', tpu.cluster_spec().as_dict()['worker'])
tf.config.experimental_connect_to_cluster(tpu)
tf.tpu.experimental.initialize_tpu_system(tpu)
strategy = tf.distribute.experimental.TPUStrategy(tpu)


img_width, img_height = 224, 224

train_data_dir = 'dataset/training_set/'
validation_data_dir = 'dataset/test_set'
nb_train_samples = 801 
nb_validation_samples = 201
epochs = 10
batch_size = 16

if K.image_data_format() == 'channels_first': 
    input_shape = (3, img_width, img_height) 
else: 
    input_shape = (img_width, img_height, 3) 

with strategy.scope():
    model = Sequential() 
    model.add(Conv2D(32, (2, 2), input_shape = input_shape)) 
    model.add(Activation('relu')) 
    model.add(MaxPooling2D(pool_size =(2, 2))) 

    model.add(Conv2D(32, (2, 2))) 
    model.add(Activation('relu')) 
    model.add(MaxPooling2D(pool_size =(2, 2))) 

    model.add(Conv2D(64, (2, 2))) 
    model.add(Activation('relu')) 
    model.add(MaxPooling2D(pool_size =(2, 2))) 

    model.add(Flatten()) 
    model.add(Dense(64)) 
    model.add(Activation('relu')) 
    model.add(Dropout(0.5)) 
    model.add(Dense(1)) 
    model.add(Activation('sigmoid')) 

    model.compile(loss ='binary_crossentropy', 
                        optimizer ='rmsprop', 
                    metrics =['accuracy']) 

    train_datagen = ImageDataGenerator( 
                    rescale = 1. / 255, 
                    shear_range = 0.2, 
                    zoom_range = 0.2, 
                horizontal_flip = True) 

    test_datagen = ImageDataGenerator(rescale = 1. / 255) 

    train_generator = train_datagen.flow_from_directory(train_data_dir, 
                                target_size =(img_width, img_height), 
                        batch_size = batch_size, class_mode ='binary') 

    validation_generator = test_datagen.flow_from_directory( 
                                        validation_data_dir, 
                    target_size =(img_width, img_height), 
            batch_size = batch_size, class_mode ='binary') 

    model.fit_generator(train_generator, 
        steps_per_epoch = nb_train_samples // batch_size, 
        epochs = epochs, validation_data = validation_generator, 
        validation_steps = nb_validation_samples // batch_size) 

    model.evaluate(validation_generator,batch_size=None)

    model.save_weights('model_saved.h5')

Как видите, я установил имя TPU «tpu1». Я не знаю, что не так, уже попробуйте это 

gcloud config set project your-project-name
gcloud config set compute/zone us-central1-b
and yes the TPU is ready already tried with --> gcloud compute tpus list

Traceback (most recent call last):
  File "cnn2.py", line 14, in <module>
    tpu = tf.contrib.cluster_resolver.TPUClusterResolver() # TPU detection
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/distribute/cluster_resolver/tpu_cluster_resolver.py", line 264, in __init__
    raise RuntimeError('You need to specify a TPU Name if you are running in '
RuntimeError: You need to specify a TPU Name if you are running in the Google Cloud environment.
...