Supervisely/ Model Zoo/ SSD Inception v2 (COCO)

Neural Network Plugin: TF Object Detection Created 7 months ago Free
Speed (ms): 42; COCO mAP[^1]: 24
Free Signup

Tensorflow Object Detection

The TensorFlow Object Detection API is an open source framework built on top of TensorFlow that makes it easy to construct, train and deploy object detection models.


Train configuration

Default train configuration available in model presets.

Also you can read common training configurations documentation.

  • lr - Learning rate.
  • epochs - the count of training epochs.
  • val_every - validation peroid by epoch (value 0.5 mean 2 validations per epoch).
  • batch_size - batch sizes for training (train) and validation (val) stages.
  • gpu_devices - list of selected GPU devices indexes.
  • data_workers - how many subprocesses to use for data loading.
  • dataset_tags - mapping for split data to train (train) and validation (val) parts by images tags. Images must be tagged by train or val tags.
  • special_classes - objects with specified classes will be interpreted in a specific way. Default class name for background is bg, default class name for neutral is neutral. All pixels from neutral objects will be ignored in loss function.
  • weights_init_type - can be in one of 2 modes. In transfer_learning mode all possible weights will be transfered except last layer. In continue_training mode all weights will be transfered and validation for classes number and classes names order will be performed.

Full training configuration example:

  "lr": 0.001,
  "epochs": 2,
  "val_every": 0.5,
  "batch_size": {
    "val": 6,
    "train": 12
  "input_size": {
    "width": 256,
    "height": 256
  "gpu_devices": [
  "dataset_tags": {
    "val": "val",
    "train": "train"
  "special_classes": {
    "neutral": "neutral",
    "background": "bg"
  "weights_init_type": "continue_training"

Inference configuration

For full explanation see documentation.

model - group contains unique settings for each model:

  • gpu_device - device to use for inference. Right now we support only single GPU.

  • confidence_tag_name - name of confidence tag for predicted bound boxes.

mode - group contains all mode settings:

  • name - mode name defines how to apply NN to image (e.g. full_image - apply NN to full image)

  • model_classes - which classes will be used, e.g. NN produces 80 classes and you are going to use only few and ignore other. In that case you should set save_classes field with the list of interested class names. add_suffix string will be added to new class to prevent similar class names with exisiting classes in project. If you are going to use all model classes just set "save_classes": "__all__".

Full image inference configuration example:

  "model": {
    "gpu_device": 0,
    "confidence_tag_name": "confidence",
  "mode": {
    "name": "full_image",
    "model_classes": {
      "save_classes": "__all__",
      "add_suffix": "_tf"

Docker Image


More Info

Plugin ID
Plugin Version
First released
7 months ago
Last updated
5 months ago