add open image dataset config.

maximiliano1985 · Nov 18, 2017 · 2f52329 · 2f52329
1 parent 1f562fa
commit 2f52329
Showing 1 changed file with 146 additions and 0 deletions.
diff --git a/research/object_detection/faster_rcnn_inception_resnet_v2_atrous_oid.config b/research/object_detection/faster_rcnn_inception_resnet_v2_atrous_oid.config
@@ -0,0 +1,146 @@
+# Faster R-CNN with Inception Resnet v2, Atrous version;
+# Configured for Open Images 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 {
+  faster_rcnn {
+    num_classes: 546
+    image_resizer {
+      keep_aspect_ratio_resizer {
+        min_dimension: 600
+        max_dimension: 1024
+      }
+    }
+    feature_extractor {
+      type: 'faster_rcnn_inception_resnet_v2'
+      first_stage_features_stride: 8
+    }
+    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: 8
+        width_stride: 8
+      }
+    }
+    first_stage_atrous_rate: 2
+    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
+            }
+          }
+        }
+      }
+    }
+    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
+  }
+}
+
+train_config: {
+  batch_size: 1
+  optimizer {
+    momentum_optimizer: {
+      learning_rate: {
+        manual_step_learning_rate {
+          initial_learning_rate: 0.00006
+          schedule {
+            step: 0
+            learning_rate: .00006
+          }
+          schedule {
+            step: 6000000
+            learning_rate: .000006
+          }
+          schedule {
+            step: 7000000
+            learning_rate: .0000006
+          }
+        }
+      }
+      momentum_optimizer_value: 0.9
+    }
+    use_moving_average: false
+  }
+  gradient_clipping_by_norm: 10.0
+  fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/model.ckpt"
+  # Note: The below line limits the training process to 800K steps, which we
+  # empirically found to be sufficient enough to train the Open Images dataset.
+  # This effectively bypasses the learning rate schedule (the learning rate will
+  # never decay). Remove the below line to train indefinitely.
+  num_steps: 8000000
+  data_augmentation_options {
+    random_horizontal_flip {
+    }
+  }
+}
+
+train_input_reader: {
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/oid_bbox_trainable_train.record"
+  }
+  label_map_path: "PATH_TO_BE_CONFIGURED/oid_bbox_trainable_label_map.pbtxt"
+}
+
+eval_config: {
+  metrics_set: "open_images_metrics"
+  num_examples: 8000
+  # Note: The below line limits the evaluation process to 10 evaluations.
+  # Remove the below line to evaluate indefinitely.
+  max_evals: 10
+}
+
+eval_input_reader: {
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/oid_bbox_trainable_val.record"
+  }
+  label_map_path: "PATH_TO_BE_CONFIGURED/oid_bbox_trainable_label_map.pbtxt"
+  shuffle: false
+  num_readers: 1
+}