[嗨，我正在做tensorflow object detection api。我已经按照仓库中的所有主要说明进行操作了，直到现在为止一切正常，但是突然出现了一些奇怪的错误。我之前使用的是fast rcnn，现在切换到ssd mobile v2 coco。
使用命令生成推理图时
python export_inference_graph.py --input_type image_tensor --pipeline_config_path training/faster_rcnn_inception_v2_pets.config --trained_checkpoint_prefix training/model.ckpt-10250 --output_directory inference_graph
我得到以下错误：
追踪（最近一次通话）：文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/tensorflow/python/client/session.py”，行1356，在_do_call中在_run_fn中的第1341行中返回fn（* args）文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/tensorflow/python/client/session.py”选项，feed_dict，fetch_list，target_list，run_metadata）文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/tensorflow/python/client/session.py”，行1429，在_call_tf_sessionrun中run_metadata）tensorflow.python.framework.errors_impl.NotFoundError：关键转换/偏见在检查点[[{{node save / RestoreV2}}]]
中找不到在处理以上异常期间，发生了另一个异常：
追踪（最近一次通话）：文件还原中的“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/tensorflow/python/training/saver.py”，行1286{self.saver_def.filename_tensor_name：save_path}）文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/tensorflow/python/client/session.py”，第950行，正在运行run_metadata_ptr）文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/tensorflow/python/client/session.py”，行_runfeed_dict_tensor，选项，run_metadata）文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/tensorflow/python/client/session.py”，行1350，在_do_run中run_metadata）文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/tensorflow/python/client/session.py”，行1370，在_do_call中提高类型（e）（node_def，op，消息）tensorflow.python.framework.errors_impl.NotFoundError：关键转换/偏见在检查点[[node save / RestoreV2（在/home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/object_detection/exporter.py:331）]]
'save / RestoreV2'的原始堆栈跟踪：文件第162行中的“ export_inference_graph.py”tf.app.run（）文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/tensorflow/python/platform/app.py”，40号线，运行中_run（main = main，argv = argv，flags_parser = _parse_flags_tolerate_undef）文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/absl/app.py”，299行_run_main（main，args）文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/absl/app.py”，_run_main中的第250行sys.exit（main（argv））文件“ export_inference_graph.py”，第158行，位于主目录中write_inference_graph = FLAGS.write_inference_graph）文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/object_detection/exporter.py”，第497行，在export_inference_graph中write_inference_graph = write_inference_graph）文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/object_detection/exporter.py”，_export_inference_graph中的第426行（文件为“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/object_detection/exporter.py”），在write_graph_and_checkpoint中的第331行tf.import_graph_def（inference_graph_def，name =“''）文件” /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py“，第507行，在new_func中返回func（* args，** kwargs）文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/tensorflow/python/framework/importer.py”，import_graph_def中的第443行_ProcessNewOps（graph）文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/tensorflow/python/framework/importer.py”，_ProcessNewOps中的第236行用于graph._add_new_tf_operations（compute_devices = False）中的new_op：＃pylint：disable = protected-access File“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/tensorflow/python/framework/ops .py”，第375行，在_add_new_tf_operations中对于c_api_util.new_tf_operations（self）文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/tensorflow/python/framework/ops.py”中的c_op，行3751，在对于c_api_util.new_tf_operations（self）文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/tensorflow/python/framework/ops.py”中的c_op，第3641行，在_create_op_from_tf_operation中ret = Operation（c_op，self）文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/tensorflow/python/framework/ops.py”，第2005行，在[[init中self._traceback = tf_stack.extract_stack（）
在处理以上异常期间，发生了另一个异常：追踪（最近一次通话）：文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/tensorflow/python/training/saver.py”，行1296，在还原中names_to_keys = object_graph_key_mapping（save_path）文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/tensorflow/python/training/saver.py”，行1614，在object_graph_key_mapping中object_graph_string = reader.get_tensor（trackable.OBJECT_GRAPH_PROTO_KEY）文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/tensorflow/python/pywrap_tensorflow_internal.py”，第678行，位于get_tensor中返回CheckpointReader_GetTensor（自身，compat.as_bytes（tensor_str））tensorflow.python.framework.errors_impl.NotFoundError：键在检查点找不到_CHECKPOINTABLE_OBJECT_GRAPH
在处理以上异常期间，发生了另一个异常：
追踪（最近一次通话）：文件“ export_inference_graph.py”，162行，在tf.app.run（）文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/tensorflow/python/platform/app.py”，40号线，运行中_run（main = main，argv = argv，flags_parser = _parse_flags_tolerate_undef）文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/absl/app.py”，299行_run_main（main，args）文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/absl/app.py”，_run_main中的第250行sys.exit（main（argv））文件“ export_inference_graph.py”，第158行，位于主目录中write_inference_graph = FLAGS.write_inference_graph）文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/object_detection/exporter.py”，第497行，在export_inference_graph中write_inference_graph = write_inference_graph）文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/object_detection/exporter.py”，_export_inference_graph中的第426行（文件为“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/object_detection/exporter.py”），第335行，在write_graph_and_checkpoint中saver.restore（sess，trained_checkpoint_prefix）文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/tensorflow/python/training/saver.py”，第1302行，在还原中err，“缺少变量名或其他图形键”）tensorflow.python.framework.errors_impl.NotFoundError：从中还原检查点失败。这很可能是由于变量名或其他检查点缺少的图形键。请确保您尚未更改基于检查点的预期图形。原版的错误：
在检查点[[节点保存/恢复V2中找不到关键转换/偏见（定义为/home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/object_detection/exporter.py:331）]]
'save / RestoreV2'的原始堆栈跟踪：文件第162行中的“ export_inference_graph.py”tf.app.run（）文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/tensorflow/python/platform/app.py”，40行_run（main = main，argv = argv，flags_parser = _parse_flags_tolerate_undef）文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/absl/app.py”，299行_run_main（main，args）文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/absl/app.py”，_run_main中的第250行sys.exit（main（argv））文件“ export_inference_graph.py”，第158行，位于主目录中write_inference_graph = FLAGS.write_inference_graph）文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/object_detection/exporter.py”，第497行，在export_inference_graph中write_inference_graph = write_inference_graph）文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/object_detection/exporter.py”，_export_inference_graph中的第426行（文件为“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/object_detection/exporter.py”），在write_graph_and_checkpoint中的第331行tf.import_graph_def（inference_graph_def，name =“''）文件” /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py“，第507行，在new_func中返回func（* args，** kwargs）文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/tensorflow/python/framework/importer.py”，import_graph_def中的第443行_ProcessNewOps（graph）文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/tensorflow/python/framework/importer.py”，_ProcessNewOps中的第236行用于graph._add_new_tf_operations（compute_devices = False）中的new_op：＃pylint：disable = protected-access File“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/tensorflow/python/framework/ops .py”，第375行，在_add_new_tf_operations中对于c_api_util.new_tf_operations（self）文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/tensorflow/python/framework/ops.py”中的c_op，行3751，在对于c_api_util.new_tf_operations（self）文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/tensorflow/python/framework/ops.py”中的c_op，第3641行，在_create_op_from_tf_operation中ret = Operation（c_op，self）文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/tensorflow/python/framework/ops.py”，第2005行，在[[init
中self._traceback = tf_stack.extract_stack（）
实际上，它一直在正确地工作，无法弄清楚现在发生了什么。我也尝试了快速rcnn（它之前已经工作了），但是它也开始失败了
这里是配置文件。我目前正在为2个班级做这件事# Faster R-CNN with Inception v2, configured for Oxford-IIIT Pets 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 {
faster_rcnn {
num_classes: 2
image_resizer {
keep_aspect_ratio_resizer {
min_dimension: 600
max_dimension: 1024
}
}
feature_extractor {
type: 'faster_rcnn_inception_v2'
first_stage_features_stride: 16
}
first_stage_anchor_generator {
grid_anchor_generator {
scales: [0.25, 0.5, 1.0, 2.0]
aspect_ratios: [0.5, 1.0, 2.0]
height_stride: 16
width_stride: 16
}
}
first_stage_box_predictor_conv_hyperparams {
op: CONV
regularizer {
l2_regularizer {
weight: 0.0
}
}
initializer {
truncated_normal_initializer {
stddev: 0.01
}
}
}
first_stage_nms_score_threshold: 0.0
first_stage_nms_iou_threshold: 0.7
first_stage_max_proposals: 300
first_stage_localization_loss_weight: 2.0
first_stage_objectness_loss_weight: 1.0
initial_crop_size: 14
maxpool_kernel_size: 2
maxpool_stride: 2
second_stage_box_predictor {
mask_rcnn_box_predictor {
use_dropout: false
dropout_keep_probability: 1.0
fc_hyperparams {
op: FC
regularizer {
l2_regularizer {
weight: 0.0
}
}
initializer {
variance_scaling_initializer {
factor: 1.0
uniform: true
mode: FAN_AVG
}
}
}
}
}
second_stage_post_processing {
batch_non_max_suppression {
score_threshold: 0.0
iou_threshold: 0.6
max_detections_per_class: 100
max_total_detections: 300
}
score_converter: SOFTMAX
}
second_stage_localization_loss_weight: 2.0
second_stage_classification_loss_weight: 1.0
}
}
train_config: {
batch_size: 1
optimizer {
momentum_optimizer: {
learning_rate: {
manual_step_learning_rate {
initial_learning_rate: 0.0002
schedule {
step: 1
learning_rate: .0002
}
schedule {
step: 900000
learning_rate: .00002
}
schedule {
step: 1200000
learning_rate: .000002
}
}
}
momentum_optimizer_value: 0.9
}
use_moving_average: false
}
gradient_clipping_by_norm: 10.0
fine_tune_checkpoint: "/home/user/Downloads/Data_Science/Git/models/research/object_detection/faster_rcnn_inception_v2_coco_2018_01_28/model.ckpt"
from_detection_checkpoint: true
load_all_detection_checkpoint_vars: false
# 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: 200000
data_augmentation_options {
random_horizontal_flip {
}
}
}
train_input_reader: {
tf_record_input_reader {
input_path: "/home/user/Downloads/Data_Science/Git/models/research/object_detection/train.record"
}
label_map_path: "/home/user/Downloads/Data_Science/Git/models/research/object_detection/training/labelmap.pbtxt"
}
eval_config: {
num_examples: 67
# 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: "C:/tensorflow1/models/research/object_detection/test.record"
}
label_map_path: "C:/tensorflow1/models/research/object_detection/training/labelmap.pbtxt"
shuffle: false
num_readers: 1
}