我在路径\DLTK-master\examples\applications\IXI_HH_age_regression_resnet中使用dltk软件包https://github.com/DLTK/DLTK。在代码中进行了一些修改之后，我返回到原始代码：
def model_fn(features, labels, mode, params):
# 1. create a model and its outputs
net_output_ops = resnet_3d(
inputs=features['x'],
num_res_units=2,
num_classes=NUM_CLASSES,
filters=(16, 32, 64, 128, 256),
strides=((1, 1, 1), (2, 2, 2), (2, 2, 2), (2, 2, 2), (2, 2, 2)),
mode=mode,
kernel_regularizer=tf.contrib.layers.l2_regularizer(1e-4))
# 1.1 Generate predictions only (for `ModeKeys.PREDICT`)
if mode == tf.estimator.ModeKeys.PREDICT:
return tf.estimator.EstimatorSpec(
mode=mode,
predictions=net_output_ops,
export_outputs={'out': tf.estimator.export.PredictOutput(net_output_ops)})
# 2. set up a loss function
loss = tf.losses.mean_squared_error(
labels=labels['y'],
predictions=net_output_ops['logits'])
# 3. define a training op and ops for updating moving averages (i.e.
# for batch normalisation)
global_step = tf.train.get_global_step()
optimiser = tf.train.AdamOptimizer(
learning_rate=params["learning_rate"],
epsilon=1e-5)
update_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS)
with tf.control_dependencies(update_ops):
train_op = optimiser.minimize(loss, global_step=global_step)
# 4.2 (optional) track the rmse (scaled back by 100, see reader.py)
rmse = tf.metrics.root_mean_squared_error
mae = tf.metrics.mean_absolute_error
eval_metric_ops = {"rmse": rmse(labels['y'], net_output_ops['logits']),
"mae": mae(labels['y'], net_output_ops['logits'])}
# 5. Return EstimatorSpec object
return tf.estimator.EstimatorSpec(mode=mode,
predictions=net_output_ops,
loss=loss,
train_op=train_op,
eval_metric_ops=eval_metric_ops)
def train(args):
np.random.seed(42)
tf.set_random_seed(42)
print('Setting up...')
# Parse csv files for file names
all_filenames = pd.read_csv(
args.data_csv,
dtype=object,
keep_default_na=False,
na_values=[]).as_matrix()
train_filenames = all_filenames[:400]
val_filenames = all_filenames[400:543]
#val_filenames = []
# Set up a data reader to handle the file i/o.
reader_params = {'n_examples': 2,
'example_size': [64, 64, 64],
'extract_examples': False}
reader_example_shapes = {'features': {'x': reader_params['example_size'] + [NUM_CHANNELS, ]},
'labels': {'y': [1]}}
reader = Reader(read_fn, {'features': {'x': tf.float32},
'labels': {'y': tf.float32}})
# Get input functions and queue initialisation hooks for training and
# validation data
train_input_fn, train_qinit_hook = reader.get_inputs(
file_references=train_filenames,
mode=tf.estimator.ModeKeys.TRAIN,
example_shapes=reader_example_shapes,
batch_size=BATCH_SIZE,
shuffle_cache_size=SHUFFLE_CACHE_SIZE,
params=reader_params)
val_input_fn, val_qinit_hook = reader.get_inputs(
file_references=val_filenames,
mode=tf.estimator.ModeKeys.EVAL,
example_shapes=reader_example_shapes,
batch_size=BATCH_SIZE,
shuffle_cache_size=SHUFFLE_CACHE_SIZE,
params=reader_params)
# Instantiate the neural network estimator
nn = tf.estimator.Estimator(
model_fn=model_fn,
model_dir=args.model_path,
params={"learning_rate": 0.001},
config=tf.estimator.RunConfig())
# Hooks for validation summaries
val_summary_hook = tf.contrib.training.SummaryAtEndHook(
os.path.join(args.model_path, 'eval'))
step_cnt_hook = tf.train.StepCounterHook(
every_n_steps=EVAL_EVERY_N_STEPS, output_dir=args.model_path)
print('Starting training...')
try:
for _ in range(MAX_STEPS // EVAL_EVERY_N_STEPS):
print('heloooo')
print(_)
nn.train(input_fn=train_input_fn,
hooks=[train_qinit_hook, step_cnt_hook],
steps=EVAL_EVERY_N_STEPS)
if args.run_validation:
print('helooo again')
results_val = nn.evaluate(input_fn=val_input_fn,
hooks=[val_qinit_hook, val_summary_hook],
steps=EVAL_STEPS)
#steps=EVAL_STEPS)
print('Step = {}; val loss = {:.5f};'.format(
results_val['global_step'],
results_val['loss']))
except KeyboardInterrupt:
pass
print('Stopping now.')
# When exporting we set the expected input shape to be arbitrary.
export_dir = nn.export_savedmodel(
export_dir_base=args.model_path,
serving_input_receiver_fn=reader.serving_input_receiver_fn(
{'features': {'x': [None, None, None, NUM_CHANNELS]},
'labels': {'y': [1]}}))
print('Model saved to {}.'.format(export_dir))
但是我遇到了一些错误：
NotFoundError（请参阅上面的回溯）：从检查点还原 失败了这很可能是由于变量名或其他图形键 检查点缺少的内容。请确保您没有 根据检查点更改了期望的图形。原始错误：
在以下位置找不到密钥unit_3_0 / sub_unit0 / batch_normalization / beta 检查点[[节点保存/还原V2（在E：/ UT Projects / khanom中定义 Sajedi博士/DLTK-master/examples/applications/IXI_HH_age_regression_resnet/train.py:192） = RestoreV2 [dtypes = [DT_FLOAT，DT_FLOAT，DT_FLOAT，DT_FLOAT，DT_FLOAT，...，DT_FLOAT，DT_FLOAT，DT_FLOAT，DT_FLOAT，DT_FLOAT]， _device =“ / job：localhost /副本：0 / task：0 / device：CPU：0”]（_ arg_save / Const_0_0， 保存/恢复V2 / tensor_names，保存/恢复V2 / shape_and_slices）]]
有人可以帮助我吗？