Leonid Keselman leonidk
leonidk
/ pytorch_finetune.py
Created
June 15, 2017 03:14
— forked from jcjohnson/pytorch_finetune.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import argparse | |
| import torch | |
| import torch.nn as nn | |
| from torch.autograd import Variable | |
| from torch.utils.data import DataLoader | |
| import torchvision | |
| import torchvision.transforms as T | |
| from torchvision.datasets import ImageFolder |
leonidk
/ tensorflow_finetune.py
Created
June 15, 2017 03:14
— forked from omoindrot/tensorflow_finetune.py
Example TensorFlow script for fine-tuning a VGG model (uses tf.contrib.data)
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| """ | |
| Example TensorFlow script for finetuning a VGG model on your own data. | |
| Uses tf.contrib.data module which is in release candidate 1.2.0rc0 | |
| Based on: | |
| - PyTorch example from Justin Johnson: | |
| https://gist.github.com/jcjohnson/6e41e8512c17eae5da50aebef3378a4c | |
| Required packages: tensorflow (v1.2) | |
| You can install the release candidate 1.2.0rc0 here: | |
| https://www.tensorflow.org/versions/r1.2/install/ | |
| Download the weights trained on ImageNet for VGG: |
leonidk
/ tf_lstm.py
Created
December 22, 2016 09:08
— forked from siemanko/tf_lstm.py
Simple implementation of LSTM in Tensorflow in 50 lines (+ 130 lines of data generation and comments)
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| """Short and sweet LSTM implementation in Tensorflow. | |
| Motivation: | |
| When Tensorflow was released, adding RNNs was a bit of a hack - it required | |
| building separate graphs for every number of timesteps and was a bit obscure | |
| to use. Since then TF devs added things like `dynamic_rnn`, `scan` and `map_fn`. | |
| Currently the APIs are decent, but all the tutorials that I am aware of are not | |
| making the best use of the new APIs. | |
| Advantages of this implementation: |