Multitask Image Classification

Multitask classification expects a directory of images and two CSVs for training labels and validation labels. The image directory should contain all images for both training and validation (but it can contain additional images). Only images specified in training CSV file will be used during training and same for validation.

The data structure should look like following:

            

            
|--dataset_root:
    |--images
        |--1.jpg
        |--2.jpg
        |--3.jpg
        |--4.jpg
        |--5.jpg
        |--6.jpg
    |--train.csv
    |--val.csv
        

Training and validation CSV files contain the labels for training and validation images. Both CSVs should have same format: the first column of the CSV must be fname, standing for the filename of the image. If you have N tasks, you need additional N columns, each with the task name as column name. For each image (row entry in CSV), there must be one and only one label for each task cell. An example for train.csv with 3 classification tasks (color, type and size) is like following:

Note: currently, multitask image classification only supports RGB training. The trained model will always have 3 input channels. For inferencing on grayscale images, user should load the image as RGB with same values in all channels. This is also how the training script handles grayscale training images.

Here is an example of a specification file for multitask classification:

            

            
random_seed: 42
model_config {
  arch: "resnet"
  n_layers: 101
  use_batch_norm: True
  use_bias: False
  all_projections: False
  use_pooling: True
  use_imagenet_head: True
  resize_interpolation_method: BICUBIC
  input_image_size: "3,224,224"
}
training_config {
  batch_size_per_gpu: 16
  checkpoint_interval: 10
  num_epochs: 80
  enable_qat: false
  learning_rate {
    soft_start_annealing_schedule {
      min_learning_rate: 5e-5
      max_learning_rate: 2e-2
      soft_start: 0.15
      annealing: 0.8
    }
  }
  regularizer {
    type: L1
    weight: 3e-5
  }
  optimizer {
    adam {
      epsilon: 1e-7
      beta1: 0.9
      beta2: 0.999
      amsgrad: false
    }
  }
  pretrain_model_path: "EXPERIMENT_DIR/resnet_101.hdf5"
}
dataset_config {
  image_directory_path: "EXPERIMENT_DIR/data/images"
  train_csv_path: "EXPERIMENT_DIR/data/train.csv"
  val_csv_path: "EXPERIMENT_DIR/data/val.csv"
}
        

Model Config

The table below describes the configurable parameters in the model_config.

BatchNormalization Parameters

The parameter batch_norm_config defines parameters for BatchNormalization layers in the model (momentum and epsilon).

Activation functions

The parameter activation defines the parameters for activation functions in the model.

Training Config

The training configuration (training_config) defines the parameters needed for training, evaluation, and inference. Details are summarized in the table below.

Dataset Config

Use the tao multitask_classification train command to tune a pre-trained model:

            

            
tao multitask_classification train -e <spec file>
                                   -k <encoding key>
                                   -r <result directory>
                                   [--gpus <num GPUs>]
                                   [--gpu_index <gpu_index>]
                                   [--use_amp]
                                   [--log_file <log_file_path>]
                                   [-h]
        

Required Arguments

• -r, --results_dir: Path to a folder where the experiment outputs should be written.

• -k, --key: User specific encoding key to save or load a .tlt model.

• -e, --experiment_spec_file: Path to the experiment spec file.

Optional Arguments

• --gpus: Number of GPUs to use and processes to launch for training. The default value is 1.

• --gpu_index: The GPU indices used to run the training. We can specify the GPU indices used to run training when the machine has multiple GPUs installed.

• --use_amp: A flag to enable AMP training.

• --log_file: Path to the log file. Defaults to stdout.

• -h, --help: Print the help message.

Here’s an example of using the tao multitask_classification train command:

            

            
tao multitask_classification train -e /workspace/tlt_drive/spec/spec.cfg -r /workspace/output -k $YOUR_KEY
        

After the model has been trained, using the experiment config file, and by following the steps to train a model, the next step is to evaluate this model on a test set to measure the accuracy of the model. The TAO Toolkit includes the tao multitask_classification evaluate command to do this.

The multitask_classification app computes per-task evaluation loss and accuracy as metrics.

When training is complete, the model is stored in the output directory of your choice in $OUTPUT_DIR. Evaluate a model using the tao multitask_classification evaluate command:

            

            
tao multitask_classification evaluate -e <experiment_spec_file>
                                      -k <key>
                                      -m <model>
                                      [--gpu_index <gpu_index>]
                                      [--log_file <log_file>]
                                      [-h]
        

Required Arguments

• -e, --experiment_spec_file: Path to the experiment spec file.

• -k, --key: Provide the encryption key to decrypt the model.

• -m, --model: Provide path to the trained model.

Optional Arguments

• -h, --help: Show this help message and exit.

• --gpu_index: The GPU indices used to run the evaluation. We can specify the GPU indices used to run training when the machine has multiple GPUs installed.

• --log_file: Path to the log file. Defaults to stdout.

Inferencing models on a labeled dataset can give confusion matrices from which you can see where the model makes mistakes.

TAO offers a command to easily generate confusion matrices for all tasks:

            

            
tao multitask_classification confmat  -i <img_root>
                                      -l <target_csv>
                                      -k <key>
                                      -m <model>
                                      [--gpu_index <gpu_index>]
                                      [--log_file <log_file>]
                                      [-h]
        

Required Arguments

• -i, --img_root: Path to the image directory.

• -l, --target_csv: Path to the ground truth label CSV file.

• -k, --key: Provide the encryption key to decrypt the model.

• -m, --model: Provide path to the trained model.

Optional Arguments

• -h, --help: Show this help message and exit.

• --gpu_index: The GPU indices used to run the confmat. We can specify the GPU indices used to run training when the machine has multiple GPUs installed.

• --log_file: Path to the log file. Defaults to stdout.

The tao multitask_classification inference command runs the inference on a specified image.

Execute tao multitask_classification inference on a multitask classification model trained on TAO Toolkit.

            

            
tao multitask_classification inference -m <model> -i <image> -k <key> -cm <classmap> [--gpu_index <gpu_index>] [--log_file <log_file>] [-h]
        

Here are the arguments of the tao multitask_classification inference tool:

Required arguments

• -m, --model: Path to the pretrained model (TAO model).

• -i, --image: A single image file for inference.

• -k, --key: Key to load model.

• -cm, --class_map: The json file that specifies the class index and label mapping for each task.

Optional arguments

• -h, --help: Show this help message and exit.

• --gpu_index: The GPU indices used to run the inference. We can specify the GPU indices used to run training when the machine has multiple GPUs installed.

• --log_file: Path to the log file. Defaults to stdout.

Pruning removes parameters from the model to reduce the model size without compromising the integrity of the model itself using the tao multitask_classification prune command.

The tao multitask_classification prune command includes these parameters:

            

            
tao multitask_classification prune -m <model>
                                   -o <output_file>
                                   -k <key>
                                   [-n <normalizer>
                                   [-eq <equalization_criterion>]
                                   [-pg <pruning_granularity>]
                                   [-pth <pruning threshold>]
                                   [-nf <min_num_filters>]
                                   [-el <excluded_list>]
                                   [--gpu_index <gpu_index>]
                                   [--log_file <log_file>]
                                   [-h]
        

Required Arguments

• -m, --model: Path to pretrained model

• -o, --output_file: Path to output checkpoints

• -k, --key: Key to load a .tlt model

Optional Arguments

• -h, --help: Show this help message and exit.

• -n, –normalizer: max to normalize by dividing each norm by the maximum norm within a layer; L2 to normalize by dividing by the L2 norm of the vector comprising all kernel norms. (default: max)

• -eq, --equalization_criterion: Criteria to equalize the stats of inputs to an elementwise op layer, or depth-wise convolutional layer. This parameter is useful for ResNet and MobileNet. Options are arithmetic_mean, geometric_mean, union, and intersection. (default: union)

• -pg, -pruning_granularity: Number of filters to remove at a time (default: 8)

• -pth: Threshold to compare normalized norm against (default: 0.1)

• -nf, --min_num_filters: Minimum number of filters to keep per layer (default: 16)

• -el, --excluded_layers: List of excluded_layers. Examples: -i item1 item2 (default: [])

• --gpu_index: The GPU indices used to run the pruning. We can specify the GPU indices used to run training when the machine has multiple GPUs installed.

• --log_file: Path to the log file. Defaults to stdout.

After pruning, the model needs to be retrained. See Re-training the Pruned Model for more details.

After the model has been pruned, there might be a slight decrease in accuracy. This happens because some previously useful weights may have been removed. In order to regain the accuracy, NVIDIA recommends that you retrain this pruned model over the same dataset. To do this, use the tao multitask_classification train command as documented in Training the model, with an updated spec file that points to the newly pruned model as the pretrained model file.

Users are advised to turn off the regularizer in the training_config for classification to recover the accuracy when retraining a pruned model. You may do this by setting the regularizer type to NO_REG. All the other parameters may be retained in the spec file from the previous training.

Exporting the model decouples the training process from inference and allows conversion to TensorRT engines outside the TAO environment. TensorRT engines are specific to each hardware configuration and should be generated for each unique inference environment. The exported model may be used universally across training and deployment hardware. The exported model format is referred to as .etlt. Like .tlt, the .etlt model format is also an encrypted model format with the same key of the .tlt model that it is exported from. This key is required when deploying this model.

Exporting the Model

Here’s an example of the tao multitask_classification export command:

            

            
tao multitask_classification export
            -m <path to the .tlt model file generated by training>
            -k <key>
            -cm <classmap>
            [-o <path to output file>]
            [--gpu_index <gpu_index>]
            [--log_file <log_file_path>]
        

Required Arguments

• -m, --model: Path to the .tlt model file to be exported.

• -k, --key: Key used to save the .tlt model file.

• -cm, --class_map: The json file that specifies the class index and label mapping for each task.

Optional Arguments

• -o, --output_file: Path to save the exported model to. The default is ./<input_file>.etlt.

• --gpu_index: The index of (discrete) GPUs used for exporting the model. We can specify the GPU index to run export if the machine has multiple GPUs installed. Note that export can only run on a single GPU.

• --log_file: Path to the log file. Defaults to stdout.

• -v, --verbose: Verbose log.

For TensorRT engine generation, validation, and int8 calibration, refer to the TAO Deploy documentation.

Refer to the Integrating a Multitask Image Classification Model page for more information about deploying a classification model with DeepStream.