sdemyanov / tensorflow-worklab
This set of files is an example of how to use Tensorflow for importing and retraining an existing model, such as ResNet. The goal of this example is to separate all functionality on several classes, so it is easy to modify the parameters and run the models, while still having all code not too deep inside.
☆24Updated 7 years ago
Related projects ⓘ
Alternatives and complementary repositories for tensorflow-worklab
- Dynamic Capacity Networks using Tensorflow☆53Updated 7 years ago
- An attempt to implement the recurrent attention model (RAM) from "Recurrent Models of Visual Attention" (Mnih+ 2014)☆44Updated 4 years ago
- visualizing what ConvNets learn with camera☆89Updated 9 years ago
- Implementation of state-of-art models in Torch☆54Updated 8 years ago
- Architecture learning for CNN's☆37Updated 7 years ago
- 2016 ActivityNet action recognition challenge. CNN + LSTM approach. Multi-threaded loading.☆54Updated 8 years ago
- DNI(Decoupled Neural Interfaces using Synthetic Gradients) implementation with Torch☆29Updated 8 years ago
- Implementation of Adversarial Autoencoder with Theano☆40Updated 8 years ago
- Code for Attentive Recurrent Comparators☆57Updated 7 years ago
- Reproduction of some of the results from 'Identity Mappings in Deep Residual Networks'☆72Updated 8 years ago
- An implementation of Highway Networks in Caffe☆96Updated 9 years ago
- an updated version of fb.resnet.torch with many changes.☆37Updated 7 years ago
- Recurrent Models of Visual Attention (RAM) with Chainer☆44Updated 7 years ago
- Implementation of Deep Neural Decision Forest based on MSR paper☆29Updated 8 years ago
- Attend Refine Repeat: Active Box Proposal Generation via In-Out Localization☆62Updated 5 years ago
- Code for SDS☆59Updated 9 years ago
- The inception-resnet-v2 models re-trained from scratch via torch☆52Updated 6 years ago
- Implementation of GoogLeNet with lasagne and theano☆28Updated 9 years ago
- Structured Receptive Fields in Convolutional Neural Networks☆47Updated 6 years ago
- Python wrapper to extract CNN embeddings with Oxford VGG models using caffe.☆27Updated 9 years ago
- ☆11Updated 8 years ago
- ☆9Updated 8 years ago
- Batch-Normalized LSTM (Recurrent Batch Normalization) implementation in Torch.☆92Updated 8 years ago
- A Siamese network implementation in torch (simple example on MNIST to embed to 2D space)☆24Updated 9 years ago
- Torch implementation of PixelCNN for MNIST☆29Updated 7 years ago
- Playing with an LSTM neural network.☆32Updated 7 years ago
- A loss function based on the distances between anchor, positive and negative embeddings used in FaceNet☆21Updated 8 years ago
- Distilling knowledge to specialist ConvNets for clustered classification☆21Updated 8 years ago