Object Detection: cannot finetune 10 classes or less by using the model ssd_resnet_50_fpn_coco

System information

• Linux Ubuntu 16.04
• TensorFlow installed from anaconda
• TensorFlow 1.7
• CUDA 9.0/cuDNN 7
• P40
• command

    python object_detection/model_main.py\
    --logtostderr \
    --pipeline_config_path=${DIR}/logo-detection/ssd_resnet50_v1_fpn_shared_box_predictor_640x640.config \
    --model_dir=${OUTPUT_DIR}

model {
  ssd {
    num_classes: 10
    image_resizer {
      fixed_shape_resizer {
        height: 640
        width: 640
      }
    }
    feature_extractor {
      type: "ssd_resnet50_v1_fpn"
      depth_multiplier: 1.0
      min_depth: 16
      conv_hyperparams {
        regularizer {
          l2_regularizer {
            weight: 0.000399999989895
          }
        }
        initializer {
          truncated_normal_initializer {
            mean: 0.0
            stddev: 0.0299999993294
          }
        }
        activation: RELU_6
        batch_norm {
          decay: 0.996999979019
          scale: true
          epsilon: 0.0010000000475
        }
      }
      override_base_feature_extractor_hyperparams: true
    }
    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
        use_matmul_gather: true
      }
    }
    similarity_calculator {
      iou_similarity {
      }
    }
    box_predictor {
      weight_shared_convolutional_box_predictor {
        conv_hyperparams {
          regularizer {
            l2_regularizer {
              weight: 0.000399999989895
            }
          }
          initializer {
            random_normal_initializer {
              mean: 0.0
              stddev: 0.00999999977648
            }
          }
          activation: RELU_6
          batch_norm {
            decay: 0.996999979019
            scale: true
            epsilon: 0.0010000000475
          }
        }
        depth: 256
        num_layers_before_predictor: 4
        kernel_size: 3
        class_prediction_bias_init: -4.59999990463
      }
    }
    anchor_generator {
      multiscale_anchor_generator {
        min_level: 3
        max_level: 7
        anchor_scale: 4.0
        aspect_ratios: 1.0
        aspect_ratios: 2.0
        aspect_ratios: 0.5
        scales_per_octave: 2
      }
    }
    post_processing {
      batch_non_max_suppression {
        score_threshold: 0.300000011921
        iou_threshold: 0.600000023842
        max_detections_per_class: 100
        max_total_detections: 100
      }
      score_converter: SIGMOID
    }
    normalize_loss_by_num_matches: true
    loss {
      localization_loss {
        weighted_smooth_l1 {
        }
      }
      classification_loss {
        weighted_sigmoid_focal {
          gamma: 2.0
          alpha: 0.25
        }
      }
      classification_weight: 1.0
      localization_weight: 1.0
    }
    encode_background_as_zeros: true
    normalize_loc_loss_by_codesize: true
    inplace_batchnorm_update: true
    freeze_batchnorm: false
  }
}
train_config {
  batch_size: 1
  data_augmentation_options {
    random_horizontal_flip {
    }
  }
  data_augmentation_options {
    random_crop_image {
      min_object_covered: 0.0
      min_aspect_ratio: 0.75
      max_aspect_ratio: 3.0
      min_area: 0.75
      max_area: 1.0
      overlap_thresh: 0.0
    }
  }
  sync_replicas: true
  optimizer {
    momentum_optimizer {
      learning_rate {
        cosine_decay_learning_rate {
          learning_rate_base: 0.0399999991059
          total_steps: 50000
          warmup_learning_rate: 0.0133330002427
          warmup_steps: 2000
        }
      }
      momentum_optimizer_value: 0.899999976158
    }
    use_moving_average: false
  }
  fine_tune_checkpoint: "/opt/ml/data/logo-detection/ssd_resnet50_v1_fpn_shared_box_predictor_640x640_coco14_sync_2018_07_03/model.ckpt"
  from_detection_checkpoint: true
  load_all_detection_checkpoint_vars: true
  fine_tune_checkpoint_type:  "detection"
  # num_steps: 25000
  startup_delay_steps: 0.0
  replicas_to_aggregate: 8
  max_number_of_boxes: 100
  unpad_groundtruth_tensors: false
}
train_input_reader {
  label_map_path: "/opt/ml/data/logo-detection/logo-label-map.pbtxt"
  tf_record_input_reader {
    input_path: "/opt/ml/data/logo-detection/dataset-train.tfrecord"
  }
}
eval_config {
  num_examples: 8000
  metrics_set: "coco_detection_metrics"
  use_moving_averages: false
}
eval_input_reader {
  label_map_path: "/opt/ml/data/logo-detection/logo-label-map.pbtxt"
  shuffle: false
  num_readers: 1
  tf_record_input_reader {
    input_path: "/opt/ml/data/logo-detection/dataset-val.tfrecord"
  }
}

Describe the problem

With commit 02a9969e94feb51966f9bacddc1836d811f8ce69 , I try to finetune ssd_resnet_50_fpn_coco for 10 classes object detection.

Source code / logs

2018-08-08 03:26:17.852738: W tensorflow/core/framework/op_kernel.cc:1273] OP_REQUIRES failed at iterator_ops.cc:891 : Invalid argument: indices[2] = 2 is not in [0, 2)
	 [[Node: Gather_4 = Gather[Tindices=DT_INT64, Tparams=DT_INT64, validate_indices=true](cond/Merge, Reshape_8)]]
Traceback (most recent call last):
  File "/usr/local/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1327, in _do_call
    return fn(*args)
  File "/usr/local/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1312, in _run_fn
    options, feed_dict, fetch_list, target_list, run_metadata)
  File "/usr/local/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1420, in _call_tf_sessionrun
    status, run_metadata)
  File "/usr/local/lib/python3.6/site-packages/tensorflow/python/framework/errors_impl.py", line 516, in __exit__
    c_api.TF_GetCode(self.status.status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: indices[2] = 2 is not in [0, 2)
	 [[Node: Gather_4 = Gather[Tindices=DT_INT64, Tparams=DT_INT64, validate_indices=true](cond/Merge, Reshape_8)]]
	 [[Node: IteratorGetNext = IteratorGetNext[output_shapes=[[1], [1,640,640,3], [1,3], [1,100], [1,100,4], [1,100,10], [1,100], [1,100], [1,100], [1]], output_types=[DT_INT32, DT_FLOAT, DT_INT32, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_INT32, DT_BOOL, DT_FLOAT, DT_INT32], _device="/job:localhost/replica:0/task:0/device:CPU:0"](Iterator)]]
	 [[Node: IteratorGetNext/_3859 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device_incarnation=1, tensor_name="edge_669_IteratorGetNext", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:GPU:0"]()]]