Я попытался использовать тензорную доску для визуализации классификатора изображений с помощью DNN. Я уверен, что путь к каталогу правильный, однако данные не отображаются. Когда я попробовал tensorboard --inspect --logdir='PATH/'
, возвращается: файлы событий не найдены в logdir 'PATH /'
Я думаю, что что-то не так с моим кодированием.
График
batch_size = 500
graph = tf.Graph()
with graph.as_default():
# Input data. For the training data, we use a placeholder that will be fed
# at run time with a training minibatch.
with tf.name_scope('train_input'):
tf_train_dataset = tf.placeholder(tf.float32,
shape=(batch_size, image_size * image_size),
name = 'train_x_input')
tf_train_labels = tf.placeholder(tf.float32, shape=(batch_size, num_labels),
name = 'train_y_input')
with tf.name_scope('validation_input'):
tf_valid_dataset = tf.constant(valid_dataset, name = 'valid_x_input')
tf_test_dataset = tf.constant(test_dataset, name = 'valid_y_input')
# Variables.
with tf.name_scope('layer'):
with tf.name_scope('weights'):
weights = tf.Variable(
tf.truncated_normal([image_size * image_size, num_labels]),
name = 'W')
variable_summaries(weights)
with tf.name_scope('biases'):
biases = tf.Variable(tf.zeros([num_labels]), name = 'B')
variable_summaries(biases)
# Training computation.
with tf.name_scope('Wx_plus_b'):
logits = tf.matmul(tf_train_dataset, weights) + biases
tf.summary.histogram('logits', logits)
with tf.name_scope('loss'):
loss = tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits(labels=tf_train_labels, logits=logits),
name = 'loss')
tf.summary.histogram('loss', loss)
tf.summary.scalar('loss_scalar', loss)
# Optimizer.
with tf.name_scope('optimizer'):
optimizer = tf.train.GradientDescentOptimizer(0.5).minimize(loss)
# Predictions for the training, validation, and test data.
train_prediction = tf.nn.softmax(logits)
valid_prediction = tf.nn.softmax(tf.matmul(tf_valid_dataset, weights) + biases)
test_prediction = tf.nn.softmax(tf.matmul(tf_test_dataset, weights) + biases)
Бегать
num_steps = 1001
t1 = time.time()
with tf.Session(graph=graph) as session:
merged = tf.summary.merge_all()
writer = tf.summary.FileWriter('C:/Users/Dr_Chenxy/Documents/pylogs', session.graph)
tf.global_variables_initializer().run()
print("Initialized")
for step in range(num_steps):
# Pick an offset within the training data, which has been randomized.
# Note: we could use better randomization across epochs.
offset = (step * batch_size) % (train_labels.shape[0] - batch_size) # 1*128 % (200000 - 128)
# Generate a minibatch.
batch_data = train_dataset[offset:(offset + batch_size), :] # choose training set for this iteration
batch_labels = train_labels[offset:(offset + batch_size), :] # choose labels for this iteration
# Prepare a dictionary telling the session where to feed the minibatch.
# The key of the dictionary is the placeholder node of the graph to be fed,
# and the value is the numpy array to feed to it.
feed_dict = {tf_train_dataset : batch_data, tf_train_labels : batch_labels}
_, l, predictions = session.run([optimizer, loss, train_prediction], feed_dict=feed_dict)
if (step % 100 == 0):
print("Minibatch loss at step %d: %f" % (step, l))
print("Minibatch accuracy: %.1f%%" % accuracy(predictions, batch_labels))
print("Validation accuracy: %.1f%%" % accuracy(
valid_prediction.eval(), valid_labels))
print("Test accuracy: %.1f%%" % accuracy(test_prediction.eval(), test_labels))
t2 = time.time()
print('Running time', t2-t1, 'seconds')