我在自己的数据集上训练了一个模型。现在我正在尝试使用eval.py评估模型并获得低于错误
tf.app.run()
INFO:tensorflow:depth of additional conv before box predictor: 0
INFO:tensorflow:depth of additional conv before box predictor: 0
INFO:tensorflow:depth of additional conv before box predictor: 0
INFO:tensorflow:depth of additional conv before box predictor: 0
INFO:tensorflow:depth of additional conv before box predictor: 0
INFO:tensorflow:depth of additional conv before box predictor: 0
Traceback (most recent call last):
File "<ipython-input-5-44cda3e31e6a>", line 1, in <module>
tf.app.run()
File "/Users/amit.sood/anaconda2/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 48, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "<ipython-input-4-8980f3a486a4>", line 48, in main
FLAGS.checkpoint_dir, FLAGS.eval_dir)
File "/Users/amit.sood/Documents/Analytics/github/models-master/research/object_detection/evaluator.py", line 210, in evaluate
save_graph_dir=(eval_dir if eval_config.save_graph else ''))
File "/Users/amit.sood/Documents/Analytics/github/models-master/research/object_detection/eval_util.py", line 393, in repeated_checkpoint_run
return metrics
UnboundLocalError: local variable 'metrics' referenced before assignment
我的配置文件如下所示
# SSD with Mobilenet v1, 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 {
ssd {
num_classes: 1
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 {
anchorwise_output: true
}
}
localization_loss {
weighted_smooth_l1 {
anchorwise_output: true
}
}
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: 24
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: ""
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: 2500
data_augmentation_options {
random_horizontal_flip {
}
}
data_augmentation_options {
ssd_random_crop {
}
}
}
train_input_reader: {
tf_record_input_reader {
input_path: "/Users/amit.sood/Documents/Analytics/github/Deep-Learning-master/amit/items_train_new.record"
}
label_map_path: "/Users/amit.sood/Documents/Analytics/github/Deep-Learning-master/amit/toy_label_map.pbtxt"
}
eval_config: {
num_examples: 2000
# 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: "/Users/amit.sood/Documents/Analytics/github/Deep-Learning-master/amit/items_val_new.record"
}
label_map_path: "/Users/amit.sood/Documents/Analytics/github/Deep-Learning-master/amit/toy_label_map.pbtxt"
shuffle: false
num_readers: 1
}
请告知我在这里缺少的内容
答案 0 :(得分：0)
在较新版本的Object Detection API中，由于无法加载任何检查点以执行评估（参见线程here），可能会导致此'metrics' referenced before assignment错误。 eval.py的--checkpoint_dir参数必须是检查点文件所在的目录，并且在其中，您需要检查点文本文件，其内容为
model_checkpoint_path：“name_of_checkpoint.ckpt”
all_model_checkpoint_paths：“name_of_checkpoint.ckpt”
并且它需要完全命名为“checkpoint”（现在这是硬编码的）！ “name_of_checkpoint.ckpt”是检查点文件的“.meta”和“.index”之前的所有内容。
您可以通过在object_detection中将import logging替换为from tensorflow.python.platform import tf_logging as logging中的eval_util.py来阅读日志消息，以确定是否存在此问题。