Model Zoo
ImageNet classification
These modes are trained to perform classification using ImageNet ILSVRC challenge data. The goal of the competition is to build a model that classifies image into one of the 1,000 categories. Categories include animals, objects, transports and so on.
| Name | Number of parameters | Pre-trained model | Code example |
|---|---|---|---|
| ResNet50 | ~25.5 millions | resnet50.hdf5 | resnet50.py |
| SqueezeNet | ~1.2 million | squeezenet.hdf5 | squeezenet.py |
| VGG16 | ~138 million | vgg16.hdf5 | vgg16.py |
| VGG19 | ~143 million | vgg19.hdf5 | vgg19.py |
Value Iteration Network (VIN)
VINs can learn to plan, and are suitable for predicting outcomes that involve planning-based reasoning, such as policies for reinforcement learning. NeuPy has 3 models pre-trained for the path-searching task in artificially created environments with different grid sizes.
| Grid size | Pre-trained parameters |
|---|---|
| 8x8 | pretrained-VIN-8.hdf5 |
| 16x16 | pretrained-VIN-16.hdf5 |
| 28x28 | pretrained-VIN-28.hdf5 |
Project that include everything related to VIN is available on Github: examples/reinforcement_learning/vin