def test_input_fn(data_dir, params):
"""Test input function for the MNIST dataset.
Args:
data_dir: (string) path to the data directory
params: (dict) contains hyperparameters of the model
"""
dataset = mnist_dataset.test(data_dir)
dataset = dataset.batch(params['batch_size'])
dataset = dataset.prefetch(
1) # make sure you always have one batch ready to serve
return dataset
def main(argv):
args = parser.parse_args(argv[1:])
'''创建模型'''
with open(args.model_config) as f:
params = json.load(f)
tf.logging.info("创建模型....")
config = tf.estimator.RunConfig(model_dir=args.model_dir,
tf_random_seed=100) # config
cls = tf.estimator.Estimator(model_fn=my_model,
config=config,
params=params) # 建立模型
'''预测得到embeddings'''
tf.logging.info("预测....")
predictions = cls.predict(
input_fn=lambda: test_input_fn(args.data_dir, params))
embeddings = np.zeros((10000, params['embedding_size']))
for i, p in enumerate(predictions):
embeddings[i] = p['embeddings']
tf.logging.info("embeddings shape: {}".format(embeddings.shape))
'''获得testset 的label 数据，并保存为metadata.tsv 文件'''
with tf.Session() as sess:
# Obtain the test labels
dataset = mnist_dataset.test(args.data_dir)
dataset = dataset.map(lambda img, lab: lab)
dataset = dataset.batch(10000)
labels_tensor = dataset.make_one_shot_iterator().get_next()
labels = sess.run(labels_tensor)
np.savetxt(os.path.join(args.log_dir, 'metadata.tsv'), labels, fmt='%d')
shutil.copy(args.sprite_filename, args.log_dir)
'''可视化embeddings'''
with tf.Session() as sess:
# 1. Variable
embedding_var = tf.Variable(embeddings, name="mnist_embeddings")
#tf.global_variables_initializer().run() # 不需要
# 2. 保存到文件中，embeddings.ckpt
saver = tf.train.Saver()
sess.run(embedding_var.initializer)
saver.save(sess, os.path.join(args.log_dir, 'embeddings.ckpt'))
# 3. 关联metadata.tsv, 和mnist_10k_sprite.png
summary_writer = tf.summary.FileWriter(args.log_dir)
config = projector.ProjectorConfig()
embedding = config.embeddings.add()
embedding.tensor_name = embedding_var.name
embedding.metadata_path = 'metadata.tsv'
embedding.sprite.image_path = 'mnist_10k_sprite.png'
embedding.sprite.single_image_dim.extend([28, 28])
projector.visualize_embeddings(summary_writer, config)
def eval_input_fn():
return dataset.test(FLAGS.data_dir).batch(
FLAGS.batch_size).make_one_shot_iterator().get_next()
def eval_input_fn():
return dataset.test(FLAGS.data_dir).batch(FLAGS.batch_size).repeat()
def eval_data():
data = dataset.test(FLAGS.data_dir)
data = data.cache()
data = data.batch(FLAGS.batch_size)
return data
def eval_input_fn():
ds = mnist_dataset.test('/tmp/mnist')
ds = ds.batch(32)
return ds
with tf.GradientTape() as tape:
y = self.input(x)
for layer in self.layers:
y = layer(y, train=train)
loss = tf.reduce_mean(
tf.losses.sparse_softmax_cross_entropy(labels=labels,
logits=y.outputs))
grads = tape.gradient(loss, self.layers[-1].weights)
return y, grads, loss
def update(self, grads):
self.optimiser.apply_gradients(zip(grads, self.layers[-1].weights))
train_ds = mnist_dataset.train("../data/")
test_ds = mnist_dataset.test("../data/").batch(32)
network = Net()
log_interval = 1000
for epoch in range(3):
start_time = time.time()
# Training
train_ds_shuffle = train_ds.shuffle(60000).batch(32)
for (batch, (images, labels)) in enumerate(train_ds_shuffle):
logits, grads, loss = network.forward(images, labels, train=True)
pred = tf.nn.top_k(logits.outputs).indices[:, 0]
