我使用anaconda(python3.6),tensorflow 1.12.0来学习object detection在 Windows 10 上。
我用这个命令来训练:
cd E:\test\models-master\research\object_detection
python model_main.py --pipeline_config_path=training/ssd_mobilenet_v1_coco.config --model_dir=training/ --num_train_steps=10000
当模型完成训练时，出现这样的错误:
......
Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.100
Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.024
Traceback (most recent call last):
File "model_main.py", line 109, in
tf.app.run()
File "E:\Anaconda3\lib\site-packages\tensorflow\python\platform\app.py", line 125, in run
_sys.exit(main(argv))
File "model_main.py", line 105, in main
tf.estimator.train_and_evaluate(estimator, train_spec, eval_specs[0])
File "E:\Anaconda3\lib\site-packages\tensorflow\python\estimator\training.py", line 471, in train_and_evaluate
return executor.run()
File "E:\Anaconda3\lib\site-packages\tensorflow\python\estimator\training.py", line 610, in run
return self.run_local()
File "E:\Anaconda3\lib\site-packages\tensorflow\python\estimator\training.py", line 711, in run_local
saving_listeners=saving_listeners)
File "E:\Anaconda3\lib\site-packages\tensorflow\python\estimator\estimator.py", line 354, in train
loss = self._train_model(input_fn, hooks, saving_listeners)
File "E:\Anaconda3\lib\site-packages\tensorflow\python\estimator\estimator.py", line 1207, in _train_model
return self._train_model_default(input_fn, hooks, saving_listeners)
File "E:\Anaconda3\lib\site-packages\tensorflow\python\estimator\estimator.py", line 1241, in _train_model_default
saving_listeners)
File "E:\Anaconda3\lib\site-packages\tensorflow\python\estimator\estimator.py", line 1471, in _train_with_estimator_spec
_, loss = mon_sess.run([estimator_spec.train_op, estimator_spec.loss])
File "E:\Anaconda3\lib\site-packages\tensorflow\python\training\monitored_session.py", line 783, in exit
self._close_internal(exception_type)
File "E:\Anaconda3\lib\site-packages\tensorflow\python\training\monitored_session.py", line 816, in _close_internal
h.end(self._coordinated_creator.tf_sess)
File "E:\Anaconda3\lib\site-packages\tensorflow\python\training\basic_session_run_hooks.py", line 590, in end
l.end(session, last_step)
File "E:\Anaconda3\lib\site-packages\tensorflow\python\estimator\training.py", line 531, in end
self._evaluate(global_step_value)
File "E:\Anaconda3\lib\site-packages\tensorflow\python\estimator\training.py", line 537, in _evaluate
self._evaluator.evaluate_and_export())
File "E:\Anaconda3\lib\site-packages\tensorflow\python\estimator\training.py", line 924, in evaluate_and_export
is_the_final_export)
File "E:\Anaconda3\lib\site-packages\tensorflow\python\estimator\training.py", line 957, in _export_eval_result
is_the_final_export=is_the_final_export))
File "E:\Anaconda3\lib\site-packages\tensorflow\python\estimator\exporter.py", line 418, in export
is_the_final_export)
File "E:\Anaconda3\lib\site-packages\tensorflow\python\estimator\exporter.py", line 126, in export
strip_default_attrs=self._strip_default_attrs)
File "E:\Anaconda3\lib\site-packages\tensorflow\python\estimator\estimator.py", line 663, in export_savedmodel
mode=model_fn_lib.ModeKeys.PREDICT)
File "E:\Anaconda3\lib\site-packages\tensorflow\python\estimator\estimator.py", line 789, in _export_saved_model_for_mode
strip_default_attrs=strip_default_attrs)
File "E:\Anaconda3\lib\site-packages\tensorflow\python\estimator\estimator.py", line 883, in _export_all_saved_models
builder = saved_model_builder.SavedModelBuilder(temp_export_dir)
File "E:\Anaconda3\lib\site-packages\tensorflow\python\saved_model\builder_impl.py", line 97, in init
file_io.recursive_create_dir(self._export_dir)
File "E:\Anaconda3\lib\site-packages\tensorflow\python\lib\io\file_io.py", line 379, in recursive_create_dir
pywrap_tensorflow.RecursivelyCreateDir(compat.as_bytes(dirname), status)
File "E:\Anaconda3\lib\site-packages\tensorflow\python\framework\errors_impl.py", line 528, in exit
c_api.TF_GetCode(self.status.status))
tensorflow.python.framework.errors_impl.NotFoundError: Failed to create a directory: training/export\Servo\temp-b'1576742954'; No such file or directory
ssd_mobilenet_v1_coco.config中的内容:
# SSD with Mobilenet v1 configuration for MSCOCO Dataset.
# Users should configure the fine_tune_checkpoint field in the train config as
# well as the label_map_path and input_path fields in the train_input_reader and
# eval_input_reader. Search for "PATH_TO_BE_CONFIGURED" to find the fields that
# should be configured.
model {
ssd {
num_classes: 2
box_coder {
faster_rcnn_box_coder {
y_scale: 10.0
x_scale: 10.0
height_scale: 5.0
width_scale: 5.0
}
}
matcher {
argmax_matcher {
matched_threshold: 0.5
unmatched_threshold: 0.5
ignore_thresholds: false
negatives_lower_than_unmatched: true
force_match_for_each_row: true
}
}
similarity_calculator {
iou_similarity {
}
}
anchor_generator {
ssd_anchor_generator {
num_layers: 6
min_scale: 0.2
max_scale: 0.95
aspect_ratios: 1.0
aspect_ratios: 2.0
aspect_ratios: 0.5
aspect_ratios: 3.0
aspect_ratios: 0.3333
}
}
image_resizer {
fixed_shape_resizer {
height: 300
width: 300
}
}
box_predictor {
convolutional_box_predictor {
min_depth: 0
max_depth: 0
num_layers_before_predictor: 0
use_dropout: false
dropout_keep_probability: 0.8
kernel_size: 1
box_code_size: 4
apply_sigmoid_to_scores: false
conv_hyperparams {
activation: RELU_6,
regularizer {
l2_regularizer {
weight: 0.00004
}
}
initializer {
truncated_normal_initializer {
stddev: 0.03
mean: 0.0
}
}
batch_norm {
train: true,
scale: true,
center: true,
decay: 0.9997,
epsilon: 0.001,
}
}
}
}
feature_extractor {
type: 'ssd_mobilenet_v1'
min_depth: 16
depth_multiplier: 1.0
conv_hyperparams {
activation: RELU_6,
regularizer {
l2_regularizer {
weight: 0.00004
}
}
initializer {
truncated_normal_initializer {
stddev: 0.03
mean: 0.0
}
}
batch_norm {
train: true,
scale: true,
center: true,
decay: 0.9997,
epsilon: 0.001,
}
}
}
loss {
classification_loss {
weighted_sigmoid {
}
}
localization_loss {
weighted_smooth_l1 {
}
}
hard_example_miner {
num_hard_examples: 3000
iou_threshold: 0.99
loss_type: CLASSIFICATION
max_negatives_per_positive: 3
min_negatives_per_image: 0
}
classification_weight: 1.0
localization_weight: 1.0
}
normalize_loss_by_num_matches: true
post_processing {
batch_non_max_suppression {
score_threshold: 1e-8
iou_threshold: 0.6
max_detections_per_class: 100
max_total_detections: 100
}
score_converter: SIGMOID
}
}
}
train_config: {
batch_size: 10
optimizer {
rms_prop_optimizer: {
learning_rate: {
exponential_decay_learning_rate {
initial_learning_rate: 0.004
decay_steps: 800720
decay_factor: 0.95
}
}
momentum_optimizer_value: 0.9
decay: 0.9
epsilon: 1.0
}
}
#fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/model.ckpt"
#from_detection_checkpoint: true
# Note: The below line limits the training process to 200K steps, which we
# empirically found to be sufficient enough to train the pets dataset. This
# effectively bypasses the learning rate schedule (the learning rate will
# never decay). Remove the below line to train indefinitely.
num_steps: 1000
data_augmentation_options {
random_horizontal_flip {
}
}
data_augmentation_options {
ssd_random_crop {
}
}
}
train_input_reader: {
tf_record_input_reader {
input_path:'data/train.record'
}
label_map_path:'data/side_vehicle.pbtxt'
}
eval_config: {
num_examples: 8000
# Note: The below line limits the evaluation process to 10 evaluations.
# Remove the below line to evaluate indefinitely.
max_evals: 10
}
eval_input_reader: {
tf_record_input_reader {
input_path: 'data/test.record'
}
label_map_path: 'data/side_vehicle.pbtxt'
shuffle: false
num_readers: 1
}
我的训练目录中生成的ckpt文件如下所示:
我没有发现任何问题。那么问题出在哪里呢？
最佳答案
从错误来看，无法在训练文件夹内创建目录。
您能否尝试在训练文件夹(training/export/Servo)中创建导出和 Servo 文件夹并提供 model_dir 参数，如下所示:
model_dir=/training/export/Servo/
关于python - tensorflow.python.framework.errors_impl.NotFoundError : Failed to create a directory: training/export\Servo\temp-b'1576742954'，我们在Stack Overflow上找到一个类似的问题： https://stackoverflow.com/questions/59409919/