naisy / train_ssd_mobilenet Goto Github PK

---
image_input: 'images'       # input image dir
movie_input: '/home/DATI/insulators/SSD_mobilenet/test_videos/route226_argentina.mp4'    # mp4 or avi. Movie file.
#camera_input: 0            # USB Webcam on PC
camera_input: 1             # USB Webcam on TX2
## Input Must be OpenCV readable
## Onboard camera on Xavier (with TX2 onboard camera)
#camera_input: "nvarguscamerasrc ! video/x-raw(memory:NVMM), width=1280, height=720,format=NV12, framerate=120/1 ! nvvidconv ! video/x-raw,format=I420 ! videoflip method=rotate-180 ! appsink"
## Onboard camera on TX2 ### (need: apt-get install libxine2)
#camera_input: "nvcamerasrc ! video/x-raw(memory:NVMM), width=(int)1280, height=(int)720, format=(string)I420, framerate=(fraction)30/1 ! nvvidconv flip-method=0 ! video/x-raw, format=(string)BGRx ! videoconvert ! video/x-raw, format=(string)BGR ! appsink"
## Onboard or external RTSP feed
#camera_input: "rtspsrc location=rtsp://127.0.0.1:8554/test latency=500 ! rtph264depay ! h264parse ! omxh264dec ! nvvidconv ! video/x-raw, width=(int)1280, height=(int)720, format=(string)BGRx ! videoconvert ! appsink"

force_gpu_compatible: False # If True with visualize False, speed up. Forces all CPU tensors to be allocated with Cuda pinned memory.
save_to_file: True         # movie or camera: ./output_movie/output_unixtime.avi. Save it in avi format to prevent compression degradation. Requires a lot of disk space.
                            # image: ./output_image/PATH_TO_FILE. Save it in image file.
visualize: True             # True: Show result image. False: Without image show.
vis_worker: False           # True: Visualization run on process. (With visuzalize:True)
max_vis_fps: 0              # >=1: Limit of show fps. 0: No limit - means try to spend full machine power for visualization. (With visualize:True.)
vis_text: True              # Display fps on result image. (With visualize:True.)
max_frames: 5000            # >=1: Quit when frames done. 0: no exit. (With visualize:False)
width: 600                  # Camera width.
height: 600                 # Camera height.
fps_interval: 5             # FPS console out interval and FPS stream length.
det_interval: 100           # interval [frames] to print detections to console
det_th: 0.5                 # detection threshold for det_intervall
worker_threads: 4           # parallel detection for Mask R-CNN.
split_model: True           # Splits Model into a GPU and CPU session for SSD/Faster R-CNN.
log_device: False           # Logs GPU / CPU device placement
allow_memory_growth: True   # limits memory allocation to the actual needs
debug_mode: False           # Show FPS spike value
split_shape: 1917           # 1917, 3000, 3309, 5118, 7326, 51150. ExpandDims_1's shape.

model_type: 'nms_v2'
model_path: '/home/DATI/insulators/SSD_mobilenet/output_models/frozen_inference_graph.pb'
label_path: '/home/davidecremona/PycharmProjects/train_ssd_mobilenet/roadsign_data/roadsign_label_map.pbtxt'
num_classes: 4

 if num_boxes != num_scores:
    raise ValueError('Incorrect scores field length: actual vs expected.')

InvalidArgumentError (see above for traceback): assertion failed: [Incorrect scores field length: actual vs expected.] [7668] [1917]
    [[node Postprocessor/BatchMultiClassNonMaxSuppression/map/while/MultiClassNonMaxSuppression/Assert/Assert (defined at /home/nvidia/Downloads/realtime_object_detection-master/lib/load_graph_nms_v1.py:197)  = Assert[T=[DT_STRING, DT_INT32, DT_INT32], summarize=3, _device="/job:localhost/replica:0/task:0/device:CPU:0"](Postprocessor/BatchMultiClassNonMaxSuppression/map/while/MultiClassNonMaxSuppression/Equal, Postprocessor/BatchMultiClassNonMaxSuppression/map/while/MultiClassNonMaxSuppression/Assert/Assert/data_0, Postprocessor/BatchMultiClassNonMaxSuppression/map/while/MultiClassNonMaxSuppression/strided_slice_1, Postprocessor/BatchMultiClassNonMaxSuppression/map/while/MultiClassNonMaxSuppression/strided_slice)]]

Traceback (most recent call last):
  File "/home/r/github/models/research/object_detection/export_inference_graph.py", line 71, in <module>
    from object_detection import exporter
ImportError: No module named object_detection

Traceback (most recent call last):
  File "/home/r/github/models/research/object_detection/export_inference_graph.py", line 71, in <module>
    import exporter
  File "/home/r/github/models/research/object_detection/exporter.py", line 28, in <module>
    from builders import model_builder
  File "/home/r/github/models/research/object_detection/builders/model_builder.py", line 25
    builders import region_similarity_calculator_builder as sim_calc
                  ^
SyntaxError: invalid syntax

# SSD with Mobilenet v1 configuration for MSCOCO 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: 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
      }
    }
    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 {
          anchorwise_output: true
        }
      }
      localization_loss {
        weighted_smooth_l1 {
          anchorwise_output: true
        }
      }
      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: 24
  optimizer {
    rms_prop_optimizer: {
      learning_rate: {
        exponential_decay_learning_rate {
          initial_learning_rate: 0.004
          decay_steps: 800720
          decay_factor: 0.95
        }
      }
      momentum_optimizer_value: 0.9
      decay: 0.9
      epsilon: 1.0
    }
  }
  fine_tune_checkpoint: "/home/davidecremona/PycharmProjects/train_ssd_mobilenet/ssd_mobilenet_v1_coco_2017_11_17/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: "/home/DATI/insulators/datasets/object-detection_0/tfrecords/train.record"
  }
  label_map_path: "/home/DATI/insulators/datasets/object-detection_0/label_map.pbtxt"
}

eval_config: {
  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: "/home/DATI/insulators/datasets/object-detection_0/tfrecords/val.record"
  }
  label_map_path: "/home/DATI/insulators/datasets/object-detection_0/label_map.pbtxt"
  shuffle: false
  num_readers: 1
  num_epochs: 1
}