- Python: 3.7
- TF-gpu==1.15
- Quadro RTX 4000
- 8 GB VRAM, 64GB 系统内存
- 预训练模型: ssd_mobilenet_v1_pets.config
我刚开始使用TensorFlow对象检测API，想将其应用于我自己的图像集。我希望教它区分BGA芯片的顶视图、底视图和侧视图（如果有的话，还包括带有尺寸的表格），这些图像来自于称为数据手册的文件，展示了上述组件的精确尺寸。
images/train = 565 张图像images/test = 24 张图像
我不明白为什么只有“top”标签被识别出来。这个问题困扰了我一整天，我知道这不是因为我的csv文件或tf记录的问题，因为我已经反复调整并确保它们是正常的。
配置文件:
# 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: 4 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: 16 optimizer { rms_prop_optimizer: { learning_rate: { exponential_decay_learning_rate { initial_learning_rate: 0.004 decay_steps: 2500 decay_factor: 0.9 } } momentum_optimizer_value: 0.9 decay: 0.9 epsilon: 1.0 } } fine_tune_checkpoint: "ssd_mobilenet_v1_coco_2018_01_28/model.ckpt" from_detection_checkpoint: true load_all_detection_checkpoint_vars: 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: 4000 data_augmentation_options { random_horizontal_flip { } }}train_input_reader: { tf_record_input_reader { input_path: "data/train.record" } label_map_path: "data/object-detection.pbtxt"}eval_config: { metrics_set: "coco_detection_metrics" num_examples: 24}eval_input_reader: { tf_record_input_reader { input_path: "data/test.record" } label_map_path: "training/object-detection.pbtxt" shuffle: false num_readers: 1}标签映射:
item { id: 1 name: 'top'}item { id: 2 name: 'bottom'}item { id: 3 name: 'side'}item { id: 4 name: 'table'}
回答：
如果我理解正确的话，训练后你在检测阶段无法看到所有类别。我建议使用这个脚本来加载训练后的冻结推理图，并且不要忘记指定类别的数量。祝你好运！这是代码的链接请不要忘记如果这个问题解决了你的问题，就接受这个答案
