我的问题是相当基本的，但我不明白为什么我会遇到这个问题，因此我不知道如何解决它。
我正在尝试按照this tutorial或the corresponding youtube video的步骤重新训练预训练的模型。
这是我的目录结构的相关部分：
~/Desktop/models/research/object_detection$ ls
anchor_generators evaluator.py __init__.py model_main.py test_ckpt
box_coders eval_util.py inputs.py models test_data
builders eval_util_test.py inputs_test.py model_tpu_main.py test_images
CONTRIBUTING.md exporter.py matchers object_detection_tutorial.ipynb trainer.py
core exporter_test.py meta_architectures protos trainer_test.py
data export_inference_graph.py metrics __pycache__ training
data_decoders g3doc model_hparams.py README.md train.py
dataset_tools images model_lib.py samples utils
eval.py inference model_lib_test.py ssd_mobilenet_v1_coco_11_06_2017
data
├── ava_label_map_v2.1.pbtxt
├── kitti_label_map.pbtxt
├── mscoco_label_map.pbtxt
├── oid_bbox_trainable_label_map.pbtxt
├── oid_object_detection_challenge_500_label_map.pbtxt
├── pascal_label_map.pbtxt
├── pet_label_map.pbtxt
├── test_labels.csv
├── test.record
├── train_labels.csv
└── train.record
images
├── test
├── image1.jpg
├── ...
└── train
├── imageA.jpg
├── ...
models
├── embedded_ssd_mobilenet_v1_feature_extractor.py
├── embedded_ssd_mobilenet_v1_feature_extractor_test.py
├── ...
├── __init__.py
├── __pycache__
│ ├── ...
│ ├── ssd_mobilenet_v1_feature_extractor.cpython-35.pyc
│ ├── ssd_mobilenet_v2_feature_extractor.cpython-35.pyc
│ └── ssd_resnet_v1_fpn_feature_extractor.cpython-35.pyc
├── ssd_feature_extractor_test.py
├── ...
└── ssd_resnet_v1_fpn_feature_extractor_test.py
ssd_mobilenet_v1_coco_11_06_2017/
├── frozen_inference_graph.pb
├── graph.pbtxt
├── model.ckpt.data-00000-of-00001
├── model.ckpt.index
└── model.ckpt.meta
train.py
现在，当我尝试按如下方式运行train.py时：python3 train.py --logtostderr --train_dir=training/ --pipeline_config_path=training/ssd_mobilenet_v1_pets.config
我得到/home/John/Desktop/models/research/object_detection/data/object-detection.pbtxt; No such file or directory，而这实际上是AFAIK一个应该生成的输出文件！
我可以找到我使用的train.py脚本here 这是我的ssd_mobilenet_v1_pets.config的内容：
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: 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: "ssd_mobilenet_v1_coco_11_06_2017/model.ckpt"
from_detection_checkpoint: true
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: "/home/John/Desktop/models/research/object_detection/data/object-detection.pbtxt"
}
eval_config: {
num_examples: 40
}
eval_input_reader: {
tf_record_input_reader {
input_path: "data/test.record"
}
label_map_path: "/home/John/Desktop/models/research/object_detection/data/hand-detection.pbtxt"
shuffle: false
num_readers: 1
}
有人能告诉我我做错了什么吗？
答案 0 :(得分：1)
我有同样的问题。我的解决方法是在.config文件中为label_map使用相对路径。实际上，我遇到了同样的问题，但是使用了eval.py脚本。
答案 1 :(得分：0)