张量流；tensorflow.python.framework.errors“impl.InvalidArgumentError”；培训时掩码RCNN初始Resnet V2 1024x1024型号

我正在使用计算机的GPU训练一个掩码R-CNN ResNet V2 1024x1024算法。这是从下载的，我用标签标记了我的图像（尺寸为1100x1100像素）。以下是我的工作内容：

• GPU:NVIDIA GEFORCE RTX 2060
• GPU:16GB RAM，6个处理器核
• TensorFlow:2.3.1
• Python:3.8.6
• 中大：10.1
• cuDNN:7.6
• Anaconda3命令提示符

所有tfrecord文件都已生成，当我开始使用

python model\u main\u tf2.py--model\u dir=models/my\u faster\u rcnn--pipeline\u config\u path=models/my\u faster\u rcnn/pipeline.config

训练我的模型时，出现以下错误：

Traceback (most recent call last):
  File "model_main_tf2.py", line 113, in <module>
    tf.compat.v1.app.run()
  File "C:\user\anaconda3\envs\object_detection_api\lib\site-packages\tensorflow\python\platform\app.py", line 40, in run
    _run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef)
  File "C:\user\anaconda3\envs\object_detection_api\lib\site-packages\absl\app.py", line 303, in run
    _run_main(main, args)
  File "C:\user\anaconda3\envs\object_detection_api\lib\site-packages\absl\app.py", line 251, in _run_main
    sys.exit(main(argv))
  File "model_main_tf2.py", line 104, in main
    model_lib_v2.train_loop(
  File "C:\user\anaconda3\envs\object_detection_api\lib\site-packages\object_detection\model_lib_v2.py", line 564, in train_loop
    load_fine_tune_checkpoint(detection_model,
  File "C:\user\anaconda3\envs\object_detection_api\lib\site-packages\object_detection\model_lib_v2.py", line 350, in load_fine_tune_checkpoint
    features, labels = iter(input_dataset).next()
  File "C:\user\anaconda3\envs\object_detection_api\lib\site-packages\tensorflow\python\distribute\input_lib.py", line 645, in next
    return self.__next__()
  File "C:\user\anaconda3\envs\object_detection_api\lib\site-packages\tensorflow\python\distribute\input_lib.py", line 649, in __next__
    return self.get_next()
  File "C:\user\anaconda3\envs\object_detection_api\lib\site-packages\tensorflow\python\distribute\input_lib.py", line 694, in get_next
    self._iterators[i].get_next_as_list_static_shapes(new_name))
  File "C:\user\anaconda3\envs\object_detection_api\lib\site-packages\tensorflow\python\distribute\input_lib.py", line 1474, in get_next_as_list_static_shapes
    return self._iterator.get_next()
  File "C:\user\anaconda3\envs\object_detection_api\lib\site-packages\tensorflow\python\data\ops\multi_device_iterator_ops.py", line 581, in get_next
    result.append(self._device_iterators[i].get_next())
  File "C:\user\anaconda3\envs\object_detection_api\lib\site-packages\tensorflow\python\data\ops\iterator_ops.py", line 825, in get_next
    return self._next_internal()
  File "C:\user\anaconda3\envs\object_detection_api\lib\site-packages\tensorflow\python\data\ops\iterator_ops.py", line 764, in _next_internal
    return structure.from_compatible_tensor_list(self._element_spec, ret)
  File "C:\user\anaconda3\envs\object_detection_api\lib\contextlib.py", line 131, in __exit__
    self.gen.throw(type, value, traceback)
  File "C:\user\anaconda3\envs\object_detection_api\lib\site-packages\tensorflow\python\eager\context.py", line 2105, in execution_mode
    executor_new.wait()
  File "C:\user\anaconda3\envs\object_detection_api\lib\site-packages\tensorflow\python\eager\executor.py", line 67, in wait
    pywrap_tfe.TFE_ExecutorWaitForAllPendingNodes(self._handle)
tensorflow.python.framework.errors_impl.InvalidArgumentError: indices[16] = 16 is not in [0, 0)
         [[{{node GatherV2_7}}]]
         [[MultiDeviceIteratorGetNextFromShard]]
         [[RemoteCall]]

如何解决此问题？

---

是指向错误中提到的其余代码的链接，因为它不适合此线程。

您能检查数据吗？在我读到的类似的情况下，您的数据可能有问题，例如您的xmin可能比您的xmax大：这可能完全不相关，但您说您使用LabelImg标记图像，据我所知，它不处理图像。但是，您在配置中输入了

load\u instance\u masks:true

和

predict\u instance\u masks:true

。可能是因为你有边界框吗？这里有两个注释工具来标记掩码，以防万一：&&@dnl\u anoj我想你是完全正确的。这就是问题所在。我决定使用更快的RCNN 1024 x 1024。当我获得处理能力时，我认为它会工作得很好。谢谢你的想法。

# Mask R-CNN with Inception Resnet v2 (no atrous)
# Sync-trained on COCO (with 8 GPUs) with batch size 16 (1024x1024 resolution)
# Initialized from Imagenet classification checkpoint
#
# Train on GPU-8
#
# Achieves 40.4 box mAP and 35.5 mask mAP on COCO17 val

model {
  faster_rcnn {
    number_of_stages: 3
    num_classes: 1
    image_resizer {
      fixed_shape_resizer {
        height: 1024
        width: 1024
      }
    }
    feature_extractor {
      type: 'faster_rcnn_inception_resnet_v2_keras'
    }
    first_stage_anchor_generator {
      grid_anchor_generator {
        scales: [0.25, 0.5, 1.0, 2.0]
        aspect_ratios: [0.5, 1.0, 2.0]
        height_stride: 16
        width_stride: 16
      }
    }
    first_stage_box_predictor_conv_hyperparams {
      op: CONV
      regularizer {
        l2_regularizer {
          weight: 0.0
        }
      }
      initializer {
        truncated_normal_initializer {
          stddev: 0.01
        }
      }
    }
    first_stage_nms_score_threshold: 0.0
    first_stage_nms_iou_threshold: 0.7
    first_stage_max_proposals: 300
    first_stage_localization_loss_weight: 2.0
    first_stage_objectness_loss_weight: 1.0
    initial_crop_size: 17
    maxpool_kernel_size: 1
    maxpool_stride: 1
    second_stage_box_predictor {
      mask_rcnn_box_predictor {
        use_dropout: false
        dropout_keep_probability: 1.0
        fc_hyperparams {
          op: FC
          regularizer {
            l2_regularizer {
              weight: 0.0
            }
          }
          initializer {
            variance_scaling_initializer {
              factor: 1.0
              uniform: true
              mode: FAN_AVG
            }
          }
        }
        mask_height: 33
        mask_width: 33
        mask_prediction_conv_depth: 0
        mask_prediction_num_conv_layers: 4
        conv_hyperparams {
          op: CONV
          regularizer {
            l2_regularizer {
              weight: 0.0
            }
          }
          initializer {
            truncated_normal_initializer {
              stddev: 0.01
            }
          }
        }
        predict_instance_masks: true
      }
    }
    second_stage_post_processing {
      batch_non_max_suppression {
        score_threshold: 0.0
        iou_threshold: 0.6
        max_detections_per_class: 100
        max_total_detections: 100
      }
      score_converter: SOFTMAX
    }
    second_stage_localization_loss_weight: 2.0
    second_stage_classification_loss_weight: 1.0
    second_stage_mask_prediction_loss_weight: 4.0
    resize_masks: false
  }
}

train_config: {
  batch_size: 1
  num_steps: 200000
  optimizer {
    momentum_optimizer: {
      learning_rate: {
        cosine_decay_learning_rate {
          learning_rate_base: 0.008
          total_steps: 200000
          warmup_learning_rate: 0.0
          warmup_steps: 5000
        }
      }
      momentum_optimizer_value: 0.9
    }
    use_moving_average: false
  }
  gradient_clipping_by_norm: 10.0
  fine_tune_checkpoint_version: V2
  fine_tune_checkpoint: "pre-trained-models/mask_rcnn_inception_resnet_v2_1024x1024_coco17_gpu-8/checkpoint/ckpt-0"
  fine_tune_checkpoint_type: "detection"
  data_augmentation_options {
    random_horizontal_flip {
    }
  }
}

train_input_reader: {
  label_map_path: "annotations/label_map.pbtxt"
  tf_record_input_reader {
    input_path: "annotations/train.record"
  }
  load_instance_masks: true
  mask_type: PNG_MASKS
}

eval_config: {
  metrics_set: "coco_detection_metrics"
  metrics_set: "coco_mask_metrics"
  eval_instance_masks: true
  use_moving_averages: false
  batch_size: 1
  include_metrics_per_category: true
}

eval_input_reader: {
  label_map_path: "annotations/label_map.pbtxt"
  shuffle: false
  num_epochs: 1
  tf_record_input_reader {
    input_path: "annotations/test.record"
  }
  load_instance_masks: true
  mask_type: PNG_MASKS
}