UNET

            

            
tao model unet <sub_task> <args_per_subtask>
        

            

            
# Sample model config for to instantiate a resnet18 model freeze blocks 0, 1
# with all shortcuts having projection layers.

model_config {
  num_layers: 18
  all_projections: true
  arch: "resnet"
  freeze_blocks: 0
  freeze_blocks: 1
  use_batch_norm: true
  initializer: HE_UNIFORM
  training_precision {
    backend_floatx: FLOAT32
  }
  model_input_height: 320
  model_input_width: 320
  model_input_channels: 3
}
        

            

            
training_config {
  batch_size: 2
  epochs: 3
  log_summary_steps: 10
  checkpoint_interval: 1
  loss: "cross_dice_sum"
  learning_rate:0.0001
  lr_scheduler {
    cosine_decay {
      alpha : 0.01
      decay_steps: 500
    }
  }
  regularizer {
    type: L2
    weight: 3.00000002618e-09
  }
  optimizer {
    adam {
      epsilon: 9.99999993923e-09
      beta1: 0.899999976158
      beta2: 0.999000012875
    }
  }
}
        

            

            
tao model unet dataset-convert [-h] -f <path_to_coco_json_file>
                              -r <results dir to save mask images>
                              [-n <number of images>]
        

            

            
tao model unet dataset_convert -f /path/to/coco_json_file
                         -r /path/to/results_dir/images
                         -n 8
        

            

            
  dataset_config {
    dataset: "custom"
    augment: True
    resize_padding: True
    resize_method: BILINEAR
    augmentation_config {
      spatial_augmentation {
        hflip_probability : 0.5
        vflip_probability : 0.5
        crop_and_resize_prob : 0.5
      }
      brightness_augmentation {
        delta: 0.2
      }
    }

    input_image_type: "grayscale"
    train_images_path:"/workspace/tao-experiments/data/unet/isbi/images/train"
    train_masks_path:"/workspace/tao-experiments/data/unet/isbi/masks/train"
    val_images_path:"/workspace/tao-experiments/data/unet/isbi/images/val"
    val_masks_path:"/workspace/tao-experiments/data/unet/isbi/masks/val"
    test_images_path:"/workspace/tao-experiments/data/unet/isbi/images/test"
    data_class_config {
      target_classes {
      name: "foreground"
      mapping_class: "foreground"
      label_id: 0
    }
    target_classes {
      name: "background"
      mapping_class: "background"
      label_id: 1
    }
  }
}
        

            

            
dataset_config {
  dataset: "custom"
  augment: True
  augmentation_config {
    spatial_augmentation {
      hflip_probability : 0.5
      vflip_probability : 0.5
      crop_and_resize_prob : 0.5
    }
    brightness_augmentation {
      delta: 0.2
    }
  }
  input_image_type: "color"
  train_data_sources: {
    data_source: {
      image_path: "/workspace/images_train/images_source1.txt"
      masks_path: "/workspace/labels_train/labels_source1.txt"
    }
    data_source: {
      image_path: "/workspace/images_train/images_source2.txt"
      masks_path: "/workspace/labels_train/labels_source2.txt"
    }
  }
  val_data_sources: {
    data_source: {
      image_path: "/workspace/images_val/images_source1.txt"
      masks_path: "/workspace/labels_val/labels_source1.txt"
    }
    data_source: {
      image_path: "/workspace/images_val/images_source2.txt"
      masks_path: "/workspace/labels_val/labels_source2.txt"
    }
  }
  test_data_sources: {
    data_source: {
      image_path: "/workspace/images_test/images_source1.txt"
      masks_path: "/workspace/labels_test/labels_source1.txt"
    }
    data_source: {
      image_path: "/workspace/images_test/images_source2.txt"
      masks_path: "/workspace/labels_test/labels_source2.txt"
    }
  }
  data_class_config {
    target_classes {
      name: "foreground"
      mapping_class: "foreground"
      label_id: 0
    }
    target_classes {
      name: "background"
      mapping_class: "background"
      label_id: 1
    }
  }
}
        

            

            
tao model unet train [-h] -k <key>
                    -r <result directory>
                    -e <spec_file>
                    [-m <Pre-trained weights to initialize>]
                    [-n <name of the model>
                    [--gpus <num GPUs>]
                    [--gpu_index <space separate gpu indices>]
                    [--use_amp]
        

            

            
tao model unet train -e </path/to/spec/file>
               -r </path/to/experiment/output>
               -k <key_to_load_the_model>
               -n <name_string_for_the_model>
               -m <Pre-trained weights to initialize the model>
               --gpus 2
        

            

            
tao model unet prune [-h] -m <pretrained_model>
                    -e <spec_file>
                    -o <output_file>
                    -k <key>
                    [-n <normalizer>]
                    [-eq <equalization_criterion>]
                    [-pg <pruning_granularity>]
                    [-pth <pruning threshold>]`
                    [-nf <min_num_filters>]
                    [-el [<excluded_list>]
        

            

            
tao model unet prune -e </path/to/spec/file>
               -m </path/to/weights to be pruned>
               -o </path/to/pruned weights>
               -eq union
               -pth 0.7
               -k $KEY
        

            

            
tao model unet evaluate [-h] -e <experiment_spec>
                       -m <model_file>
                       -o <output folder>
                       -k <key>
                       [--gpu_index]
        

            

            
tao model unet evaluate -e </path/to/training/spec/file>
                  -m </path/to/the/model>
                  -o </path/to/evaluation/output>
                  -k <key to load the model>
        

            

            
tao model unet inference [-h] -e <experiment_spec>
                        -m <model_file>
                        -o <output folder to save inference images>
                        -k <key>
                        [--gpu_index]
        

            

            
tao model unet export [-h] -m </path/to the .tlt model file generated by tao model train>
                     -k <key>
                     -e </path/to/experiment/spec_file>
                     [-o </path/to/output/file>]
                     [-s <strict_type_constraints>]
                     [--cal_data_file </path/to/tensor/file>]
                     [--cal_image_dir </path/to/the/directory/images/to/calibrate/the/model]
                     [--cal_cache_file </path/to/output/calibration/file>]
                     [--data_type <Data type for the TensorRT backend during export>]
                     [--batches <Number of batches to calibrate over>]
                     [--max_batch_size <maximum trt batch size>]
                     [--max_workspace_size <maximum workspace size]
                     [--batch_size <batch size to TensorRT engine>]
                     [--engine_file </path/to/the/TensorRT/engine_file>]
                     [--gen_ds_config] <Flag to generate ds config and label file>]
                     [--verbose Verbosity of the logger]
        

            

            
tao model unet export
    -m $USER_EXPERIMENT_DIR/unet/model.tlt
    -o $USER_EXPERIMENT_DIR/unet/model.int8.etlt
    -e $SPECS_DIR/unet_train_spec.txt
    --key $KEY
    --cal_image_dir $USER_EXPERIMENT_DIR/data/isbi/images/val
    --data_type int8
    --batch_size 8
    --batches 10
    --cal_data_file $USER_EXPERIMENT_DIR/export/isbi_cal_data_file.txt
    --cal_cache_file $USER_EXPERIMENT_DIR/export/isbi_cal.bin
    --engine_file $USER_EXPERIMENT_DIR/export/int8.isbi.engine