retrain object_detection not trained

Question

Background:

• Windows 10
• Tensorflow: 1.12

Followed the official document here . As the dataset is generated from experiment, so there are not many images available, about 50 training image and 10 test image. The pre-trained model is ssd_inception_v2_coco . When training using

python train.py --logtostderr --train_dir=training/ --pipeline_config_path=training/ssd_inception_v2_coco.config

saw the following output and the program quit.

(a million lines here...)
W0423 15:59:38.764785 21492 variables_helper.py:144] Variable [FeatureExtractor/InceptionV2/Mixed_5c_2_Conv2d_5_3x3_s2_128/BatchNorm/beta/RMSProp] is not available in checkpoint
W0423 15:59:38.765782 21492 variables_helper.py:144] Variable [FeatureExtractor/InceptionV2/Mixed_5c_2_Conv2d_5_3x3_s2_128/BatchNorm/beta/RMSProp_1] is not available in checkpoint
W0423 15:59:38.765782 21492 variables_helper.py:144] Variable [FeatureExtractor/InceptionV2/Mixed_5c_2_Conv2d_5_3x3_s2_128/BatchNorm/gamma/ExponentialMovingAverage] is not available in checkpoint
W0423 15:59:38.765782 21492 variables_helper.py:144] Variable [FeatureExtractor/InceptionV2/Mixed_5c_2_Conv2d_5_3x3_s2_128/BatchNorm/gamma/RMSProp] is not available in checkpoint
W0423 15:59:38.765782 21492 variables_helper.py:144] Variable [FeatureExtractor/InceptionV2/Mixed_5c_2_Conv2d_5_3x3_s2_128/BatchNorm/gamma/RMSProp_1] is not available in checkpoint
W0423 15:59:38.765782 21492 variables_helper.py:144] Variable [FeatureExtractor/InceptionV2/Mixed_5c_2_Conv2d_5_3x3_s2_128/weights/ExponentialMovingAverage] is not available in checkpoint
W0423 15:59:38.765782 21492 variables_helper.py:144] Variable [FeatureExtractor/InceptionV2/Mixed_5c_2_Conv2d_5_3x3_s2_128/weights/RMSProp] is not available in checkpoint
W0423 15:59:38.765782 21492 variables_helper.py:144] Variable [FeatureExtractor/InceptionV2/Mixed_5c_2_Conv2d_5_3x3_s2_128/weights/RMSProp_1] is not available in checkpoint
WARNING:tensorflow:From d:\Anaconda3\lib\site-packages\tensorflow\contrib\slim\python\slim\learning.py:737: Supervisor.__init__ (from tensorflow.python.training.supervisor) is deprecated and will be removed in a future version.
Instructions for updating:
Please switch to tf.train.MonitoredTrainingSession
W0423 15:59:39.539828 21492 tf_logging.py:125] From d:\Anaconda3\lib\site-packages\tensorflow\contrib\slim\python\slim\learning.py:737: Supervisor.__init__ (from tensorflow.python.training.supervisor) is deprecated and will be removed in a future version.
Instructions for updating:
Please switch to tf.train.MonitoredTrainingSession
2019-04-23 15:59:41.155297: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2
2019-04-23 15:59:41.385078: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1432] Found device 0 with properties:
name: GeForce GTX 1080 Ti major: 6 minor: 1 memoryClockRate(GHz): 1.7085
pciBusID: 0000:01:00.0
totalMemory: 11.00GiB freeMemory: 9.11GiB
2019-04-23 15:59:41.390824: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1511] Adding visible gpu devices: 0
2019-04-23 15:59:42.311427: I tensorflow/core/common_runtime/gpu/gpu_device.cc:982] Device interconnect StreamExecutor with strength 1 edge matrix:
2019-04-23 15:59:42.322811: I tensorflow/core/common_runtime/gpu/gpu_device.cc:988]      0
2019-04-23 15:59:42.324856: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1001] 0:   N
2019-04-23 15:59:42.327029: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1115] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 8799 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1080 Ti, pci bus id: 0000:01:00.0, compute capability: 6.1)
INFO:tensorflow:Restoring parameters from pre-trained-model/model.ckpt
I0423 15:59:46.439763 21492 tf_logging.py:115] Restoring parameters from pre-trained-model/model.ckpt
INFO:tensorflow:Running local_init_op.
I0423 15:59:46.674186 21492 tf_logging.py:115] Running local_init_op.
INFO:tensorflow:Done running local_init_op.
I0423 15:59:47.319484 21492 tf_logging.py:115] Done running local_init_op.
INFO:tensorflow:Starting Session.
I0423 15:59:54.453117 21492 tf_logging.py:115] Starting Session.
INFO:tensorflow:Saving checkpoint to path training/model.ckpt
I0423 15:59:54.647598 15672 tf_logging.py:115] Saving checkpoint to path training/model.ckpt
INFO:tensorflow:Starting Queues.
I0423 15:59:54.651614 21492 tf_logging.py:115] Starting Queues.
INFO:tensorflow:global_step/sec: 0
I0423 16:00:01.125150  4792 tf_logging.py:159] global_step/sec: 0

D:\workspace\demo>

And here is the configure file:

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
        reduce_boxes_in_lowest_layer: true
      }
    }
    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: 3
        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
            }
          }
        }
      }
    }
    feature_extractor {
      type: 'ssd_inception_v2'
      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,
        }
      }
      override_base_feature_extractor_hyperparams: true
    }
    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: 4
  optimizer {
    rms_prop_optimizer: {
      learning_rate: {
        exponential_decay_learning_rate {
          initial_learning_rate: 0.0004
          decay_steps: 5000
          decay_factor: 0.99
        }
      }
      momentum_optimizer_value: 0.9
      decay: 0.9
      epsilon: 1.0
    }
  }
  fine_tune_checkpoint: "pre-trained-model/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: 200000
  data_augmentation_options {
    random_horizontal_flip {
    }
  }
  data_augmentation_options {
    ssd_random_crop {
    }
  }
}

train_input_reader: {
  tf_record_input_reader {
    input_path: "annotations/train.record"
  }
  label_map_path: "annotations/label_map.pbtxt"
}

eval_config: {
  num_examples: 5
  # Note: The below line limits the evaluation process to 10 evaluations.
  # Remove the below line to evaluate indefinitely.
  max_evals: 5
}

eval_input_reader: {
  tf_record_input_reader {
    input_path: "annotations/test.record"
  }
  label_map_path: "annotations/label_map.pbtxt"
  shuffle: false
  num_readers: 1
}

I guess the model is not get trained because the tensorboard looks like this:

Well, any idea how to make the training start?

Answer 1

尝试将--num_train_steps=10添加到您的cmd。

Answer 2

好吧，在将图像调整为600 * 300之后，事情就有效了。