Deeplite Torch Zoo

The deeplite-torch-zoo package is a collection of popular CNN model architectures and benchmark datasets for PyTorch framework. The models are grouped under different datasets and different task types such as classification, object detection, and segmentation. The primary aim of this deeplite-torch-zoo is to booststrap applications by starting with the most suitable pretrained models. In addition, the pretrained models from deeplite-torch-zoo can be used as a good starting point for optimizing model architectures using our neutrino_engine

• Installation
  • Install using pip
  • Install from source
  • Install in Dev mode
• How to Use
  • Loading Datasets
    • Classification Datasets
    • Object Detection Datasets
  • Loading Models
    • Classification Models
    • Object Detection Models
• Available Models
• Available Datasets
• Benchmark Results
• Contribute a Model/Dataset to the Zoo

Installation

Install using pip

Use following command to install the package from our internal PyPI repository.

    $ pip install --upgrade pip
    $ pip install deeplite-torch-zoo

Install from source

    $ git clone https://github.com/Deeplite/deeplite-torch-zoo.git
    $ pip install .

Install in Dev mode

    $ git clone https://github.com/Deeplite/deeplite-torch-zoo.git
    $ pip install -e .
    $ pip install -r requirements-test.txt

To test the installation, one can run the basic tests using pytest command in the root folder.

Minimal Dependencies

• numpy==1.18.5
• torch==1.4.0
• torchvision==0.5.0
• opencv-python
• scipy>=1.4.1
• pycocotools
• Cython==0.28.4
• scikit-image==0.15.0
• tqdm==4.46.0
• albumentations==0.1.8
• pretrainedmodels==0.7.4
• torchfcn
• tensorboardX
• mmcv==1.2.0
• xtcocotools>=1.6
• json-tricks>=3.15.4
• black
• isort

How to Use

The deeplite-torch-zoo is collection of benchmark computer vision datasets and pretrained models. There are two primary wrapper functions to load datasets and models, get_data_splits_by_name, get_model_by_name (available in deeplite_torch_zoo.wrappers.wrapper)

Loading Datasets

The loaded datasets are available as a dictionary of the following format: {'train': train_dataloder, 'test': test_dataloader}. The train_dataloder and test_dataloader are objects of torch.utils.data.DataLoader.

Classification Datasets

    # Example: DATASET_NAME = "cifar100", BATCH_SIZE = 128
    data_splits = get_data_splits_by_name(
        dataset_name=DATASET_NAME, batch_size=BATCH_SIZE
    )

Object Detection Datasets

The following sample code loads PASCAL VOC <http://host.robots.ox.ac.uk/pascal/VOC/>_ dataset. train contains data loader for train sets for VOC2007 and/or VOC2012. If both datasets are provided it concatenates both VOC2007 and VOC2012 train sets. Otherwise, it returns the train set for the provided dataset. 'test' contains dataloader (always with batch_size=1) for test set based on VOC2007. You also need to provide the model type as well.

data_splits = get_data_splits_by_name(
        data_root=PATH_TO_VOCdevkit,
        dataset_name="voc",
        model_name="vgg16_ssd",
        batch_size=BATCH_SIZE,
    )

NOTE: As it can be observed the data_loaders are provided based on the corresponding model (model_name). Different object detection models consider inputs/outputs in different formats, and thus the our data_splits are formatted according to the needs of the model.

Loading Models

Models are provided with weights pretrained on specific datasets. Thus, one could load a model X pretrained on dataset Y, for getting the appropriate weights.

Classification Models

    model = get_model_by_name(
        model_name=MODEL_NAME, # example: "resnet18"
        dataset_name=DATASET_NAME, # example: "cifar100"
        pretrained=True, # or False, if pretrained weights are not required
        progress=False, # or True, if a progressbar is required
        device="cpu", # or "gpu"
    )

Object Detection Models

    model = get_model_by_name(
        model_name=MODEL_NAME, # example: "vgg16_ssd"
        dataset_name=DATASET_NAME, # example: "voc_20"
        pretrained=True, # or False, if pretrained weights are not required
        progress=False, # or True, if a progressbar is required
    )

To evaluate a model, the following style of code could be used,

    test_loader = data_splits["test"]
    APs = vgg16_ssd_eval_func(model, test_loader)

Available Models

There is an important utility function list_models (available in deeplite_torch_zoo.wrappers.wrapper). This utility will help in listing all available pretrained models or datasets.

For instance list_models("yolo3") will provide the following result. Similar results can be obtained using list_models("yo").

    yolo3
    yolo3_voc_1
    yolo3_voc_2
    yolo3_voc_6
    yolo3_voc_20
    yolo3_lisa_11

Available Datasets

Benchmark Results

Please refer to our documentation for the detailed performance metrics of the pretrained models available in the deeplite-torch-zoo. After downloading a model, please evaluate the model using deeplite-profiler to verify the performance metric values. However, one may see different numbers for the execution time as the target hardware and/or the load on the system may impact it.

Contribute a Model/Dataset to the Zoo

NOTE: If you looking for an SDK documentation, please head over here.

We always welcome community contributions to expand the scope of deeplite-torch-zoo and also to have additional new models and datasets. Please refer to the documentation for the detailed steps on how to add a model and dataset. In general, we follow the fork-and-pull Git workflow.

1. Fork the repo on GitHub
2. Clone the project to your own machine
3. Commit changes to your own branch
4. Push your work back up to your fork
5. Submit a Pull request so that we can review your changes

NOTE: Be sure to merge the latest from "upstream" before making a pull request!

Credit

Object Detection

• The implementation of mb-ssd models: qfgaohao/pytorch-ssd
• The implementation of resnet-ssd: Nvidia-SSD
• The implementation of yolov3: ultralytics/yolov3
• The implementation of yolov4: WongKinYiu/PyTorch_YOLOv4
• The implementation of yolov5: ultralytics/yolov5

Segmentation

• The implementation of deeplab: pytorch-deeplab-xception
• The implementation of unet_scse: nyoki-mtl/pytorch-segmentation
• The implementation of fcn: wkentaro/pytorch-fcn
• The implementation of Unet: milesial/Pytorch-UNet

Classification

• The implementation of models on CIFAR100 dataset: kuangliu/pytorch-cifar
• The implementation of Mobilenetv1 model on VWW dataset: qfgaohao/pytorch-ssd
• The implementation of Mobilenetv3 model on VWW dataset: d-li14/mobilenetv3.pytorch
• The implementation of models on Imagenet dataset: pytorch/vision