##VGG19 model for Keras
This is the Keras model of the 19-layer network used by the VGG team in the ILSVRC-2014 competition.
It has been obtained by directly converting the Caffe model provived by the authors.
Details about the network architecture can be found in the following arXiv paper:
Very Deep Convolutional Networks for Large-Scale Image Recognition
K. Simonyan, A. Zisserman
| import torch | |
| import torch.nn as nn | |
| from torch.autograd import Variable | |
| from torch.nn import functional as F | |
| """ | |
| Blog post: | |
| Taming LSTMs: Variable-sized mini-batches and why PyTorch is good for your health: | |
| https://medium.com/@_willfalcon/taming-lstms-variable-sized-mini-batches-and-why-pytorch-is-good-for-your-health-61d35642972e | |
| """ |
| import torch | |
| import torch.nn as nn | |
| from torch.autograd import Variable | |
| from torch.nn import functional as F | |
| """ | |
| Blog post: | |
| Taming LSTMs: Variable-sized mini-batches and why PyTorch is good for your health: | |
| https://medium.com/@_willfalcon/taming-lstms-variable-sized-mini-batches-and-why-pytorch-is-good-for-your-health-61d35642972e | |
| """ |
| """ | |
| Blog post: | |
| Taming LSTMs: Variable-sized mini-batches and why PyTorch is good for your health: | |
| https://medium.com/@_willfalcon/taming-lstms-variable-sized-mini-batches-and-why-pytorch-is-good-for-your-health-61d35642972e | |
| """ | |
| def forward(self, X, X_lengths): | |
| # reset the LSTM hidden state. Must be done before you run a new batch. Otherwise the LSTM will treat | |
| # a new batch as a continuation of a sequence | |
| self.hidden = self.init_hidden() |
| """ | |
| Blog post: | |
| Taming LSTMs: Variable-sized mini-batches and why PyTorch is good for your health: | |
| https://medium.com/@_willfalcon/taming-lstms-variable-sized-mini-batches-and-why-pytorch-is-good-for-your-health-61d35642972e | |
| """ | |
| def loss(self, Y_hat, Y, X_lengths): | |
| # TRICK 3 ******************************** | |
| # before we calculate the negative log likelihood, we need to mask out the activations | |
| # this means we don't want to take into account padded items in the output vector |
| import os | |
| import torch | |
| from torch.nn import functional as F | |
| from torch.utils.data import DataLoader | |
| from torchvision.datasets import MNIST | |
| import torchvision.transforms as transforms | |
| import pytorch_lightning as ptl | |
| class CoolModel(ptl.LightningModule): |
| from pytorch_lightning import Trainer | |
| from test_tube import Experiment | |
| model = CoolModel() | |
| exp = Experiment(save_dir=os.getcwd()) | |
| # train on cpu using only 10% of the data (for demo purposes) | |
| trainer = Trainer(experiment=exp, max_nb_epochs=1, train_percent_check=0.1) | |
| # train on 4 gpus |
| from pytorch_lightning import Trainer | |
| model = LightningModule(…) | |
| trainer = Trainer() | |
| trainer.fit(model) |
| dataset = MNIST(root=self.hparams.data_root, train=train, download=True) | |
| loader = DataLoader(dataset, batch_size=32, shuffle=True) | |
| for batch in loader: | |
| x, y = batch | |
| model.training_step(x, y) | |
| ... |
| # slow | |
| loader = DataLoader(dataset, batch_size=32, shuffle=True) | |
| # fast (use 10 workers) | |
| loader = DataLoader(dataset, batch_size=32, shuffle=True, num_workers=10) |