| from keras.models import Sequential | |
| from keras.layers.core import Dense, Dropout, Activation, Flatten | |
| from keras.layers.convolutional import Convolution2D, MaxPooling2D | |
| from keras.layers.normalization import BatchNormalization | |
| #AlexNet with batch normalization in Keras | |
| #input image is 224x224 | |
| model = Sequential() | |
| model.add(Convolution2D(64, 3, 11, 11, border_mode='full')) |
| """ | |
| A deep neural network with or w/o dropout in one file. | |
| License: Do What The Fuck You Want to Public License http://www.wtfpl.net/ | |
| """ | |
| import numpy, theano, sys, math | |
| from theano import tensor as T | |
| from theano import shared | |
| from theano.tensor.shared_randomstreams import RandomStreams |
Trained by me using https://github.com/soumith/imagenet-multiGPU.torch, achieves 56.7% top1 center crop accuracy on ImageNet validation set. Tested here: https://github.com/szagoruyko/imagenet-validation.torch
Download link: https://yadi.sk/d/uX6id_yZoU8FC (247 MB)
Load as:
| # -*- coding: utf-8 -*- | |
| """ | |
| Preliminary implementation of batch normalization for Lasagne. | |
| Does not include a way to properly compute the normalization factors over the | |
| full training set for testing, but can be used as a drop-in for training and | |
| validation. | |
| Author: Jan Schlüter | |
| """ |
sudo tar -xf Franz-linux-x64-0.9.10.tgz -C /opt/franzwget "https://cdn-images-1.medium.com/max/360/1*v86tTomtFZIdqzMNpvwIZw.png" -O franz-icon.png then sudo cp franz-icon.png /opt/franzsudo touch /usr/share/applications/franz.desktop then sudo vim /usr/share/applications/franz.desktoppaste the following lines into the file, then save the file:
[Desktop Entry]
Name=Franz
Comment=
| INFO:root:Namespace(aug_level=2, batch_size=256, bn_mom=0.9, data_dir='data/imagenet', data_type='imagenet', depth=101, frequent=50, gpus='0,1,2,3,4,5,6,7', kv_store='device', list_dir='./', lr=0.1, memonger=False, model_load_epoch=0, mom=0.9, num_classes=1000, num_examples=1281167, retrain=False, wd=0.0001, workspace=512) | |
| [00:03:29] src/io/iter_image_recordio.cc:221: ImageRecordIOParser: data/imagenet/train_480_q90.rec, use 4 threads for decoding.. | |
| [00:03:32] src/io/iter_image_recordio.cc:221: ImageRecordIOParser: data/imagenet/val_256_q90.rec, use 4 threads for decoding.. | |
| INFO:root:Start training with [gpu(0), gpu(1), gpu(2), gpu(3), gpu(4), gpu(5), gpu(6), gpu(7)] | |
| INFO:root:Epoch[0] Batch [50] Speed: 136.63 samples/sec Train-accuracy=0.001328 | |
| INFO:root:Epoch[0] Batch [50] Speed: 136.63 samples/sec Train-top_k_accuracy_5=0.006406 | |
| INFO:root:Epoch[0] Batch [100] Speed: 132.44 samples/sec Train-accuracy=0.001328 | |
| INFO:root:Epoch[0] Batch [100] Speed: 132.44 samples/sec Train-top_k_accuracy_5=0.005625 |
| import torch | |
| from torch.autograd import Variable | |
| import torch.nn as nn | |
| import numpy as np | |
| import torch.optim as optim | |
| import torch.nn.functional as F | |
| import time | |
| from torchvision.models import vgg | |
| # Initialize network |
| from tf_logger import TFLogger | |
| """ Example of using TFLogger to save train & dev statistics. To visualize | |
| in tensorboard simply do: | |
| tensorboard --logdir /path/to/summaries | |
| This code does depend on Tensorflow, but does not require that your model | |
| is built using Tensorflow. For instance, could build a model in Chainer, then |