我正在使用以下代码在 InceptionV1 上训练花卉数据集。此处提供此代码
import os
from datasets import flowers
from nets import inception
from preprocessing import inception_preprocessing
slim = tf.contrib.slim
image_size = inception.inception_v1.default_image_size
def get_init_fn():
"""Returns a function run by the chief worker to warm-start the training."""
checkpoint_exclude_scopes=["InceptionV1/Logits", "InceptionV1/AuxLogits"]
exclusions = [scope.strip() for scope in checkpoint_exclude_scopes]
variables_to_restore = []
for var in slim.get_model_variables():
excluded = False
for exclusion in exclusions:
if var.op.name.startswith(exclusion):
excluded = True
break
if not excluded:
variables_to_restore.append(var)
return slim.assign_from_checkpoint_fn(
os.path.join(checkpoints_dir, 'inception_v1.ckpt'),
variables_to_restore)
train_dir = '/tmp/inception_finetuned/'
with tf.Graph().as_default():
tf.logging.set_verbosity(tf.logging.INFO)
dataset = flowers.get_split('train', flowers_data_dir)
images, _, labels = load_batch(dataset, height=image_size, width=image_size)
# Create the model, use the default arg scope to configure the batch norm parameters.
with slim.arg_scope(inception.inception_v1_arg_scope()):
logits, _ = inception.inception_v1(images, num_classes=dataset.num_classes, is_training=True)
# Specify the loss function:
one_hot_labels = slim.one_hot_encoding(labels, dataset.num_classes)
slim.losses.softmax_cross_entropy(logits, one_hot_labels)
total_loss = slim.losses.get_total_loss()
# Create some summaries to visualize the training process:
tf.scalar_summary('losses/Total Loss', total_loss)
# Specify the optimizer and create the train op:
optimizer = tf.train.AdamOptimizer(learning_rate=0.01)
train_op = slim.learning.create_train_op(total_loss, optimizer)
# Run the training:
final_loss = slim.learning.train(
train_op,
logdir=train_dir,
init_fn=get_init_fn(),
number_of_steps=2)
print('Finished training. Last batch loss %f' % final_loss)
我使用以下代码评估了模型,得到了 58.34% 的准确率
import numpy as np
import tensorflow as tf
from datasets import flowers
from nets import inception
slim = tf.contrib.slim
image_size = inception.inception_v1.default_image_size
batch_size = 3
with tf.Graph().as_default():
tf.logging.set_verbosity(tf.logging.INFO)
dataset = flowers.get_split('train', flowers_data_dir)
images, images_raw, labels = load_batch(dataset, height=image_size, width=image_size)
# Create the model, use the default arg scope to configure the batch norm parameters.
with slim.arg_scope(inception.inception_v1_arg_scope()):
logits, _ = inception.inception_v1(images, num_classes=dataset.num_classes, is_training=True)
predictions = tf.argmax(logits, 1)
checkpoint_path = tf.train.latest_checkpoint(train_dir)
init_fn = slim.assign_from_checkpoint_fn(
checkpoint_path,
slim.get_variables_to_restore())
names_to_values, names_to_updates = slim.metrics.aggregate_metric_map({
'eval/Accuracy': slim.metrics.streaming_accuracy(predictions, labels),
'eval/Recall@5': slim.metrics.streaming_recall_at_k(logits, labels, 5),
})
# Define the streaming summaries to write:
for metric_name, metric_value in names_to_values.items():
tf.summary.scalar(metric_name, metric_value)
print('Running evaluation Loop...')
# Load the most recent checkpoint of variables saved
checkpoint_path = tf.train.latest_checkpoint(train_dir)
# Evaluates the model at the given checkpoint path
metric_values = slim.evaluation.evaluate_once(
master='',
checkpoint_path=checkpoint_path,
logdir=train_dir,
num_evals=100,
eval_op=list(names_to_updates.values()),
final_op=list(names_to_values.values()),
summary_op=tf.summary.merge_all())
names_to_values = dict(zip(names_to_values.keys(), metric_values))
for name in names_to_values:
print('%s: %f' % (name, names_to_values[name]))
除了配置检查点和训练目录外,我只是将代码中的“V1”替换为“V2”和“V4”,并训练了模型。
首先,对于所有 100 次迭代,“V2”和“V4”的训练损失始终保持在 4% 左右。其次,“V2”和“V4”的评估准确率都在 25% 左右
我是 TF 的新手,所以这里肯定缺少一些东西,我做错了什么?