import torch
torch.manual_seed(1)
from util import adjust_learning_rate, AverageMeter, accuracy
from tensorflow.python.platform import flags
import torch.nn as nn
import sys
import torch.optim as optim
import tensorboard_logger as tb_logger
import torchvision.models as models
import torchvision.models as models
FLAGS = flags.FLAGS
flags.DEFINE_bool('places_full', False, 'use all of places')
flags.DEFINE_float('learning_rate', 0.1, 'learning rate')
flags.DEFINE_list('lr_decay_epochs', [30, 40, 50],
'epochs to decay learning rate')
flags.DEFINE_string('mode', 'crl', 'type of model to load')
flags.DEFINE_bool('policy', False, 'whether to use model or policy')
class PlacesLinear(nn.Module):
def __init__(self, classes):
super(PlacesLinear, self).__init__()
self.fc = nn.Linear(2048, classes)
def forward(self, inp):
logits = self.fc(inp)
return logits
flags.DEFINE_string('real_data_shape', default='asus', help='')
flags.DEFINE_string('checkpoint',
default='checkpoint',
help='checkpoint directory')
flags.DEFINE_string(
'manual_checkpoint',
default=None,
help='instead of tacking on extra terms, use their exact path')
flags.DEFINE_string('logpath', default='./logs', help='log directory')
flags.DEFINE_bool('serve',
default=False,
help='export the model to allow for tensorflow serving')
flags.DEFINE_integer('num_files', default=None, help='')
flags.DEFINE_integer('shuffle_files', default=0, help='')
flags.DEFINE_integer('num_epochs', default=None, help='')
flags.DEFINE_list('filenames', default=None, help='')
flags.DEFINE_bool('notify', default=False, help='notify on end')
flags.DEFINE_bool('more_notify', default=False, help='notify on epoch')
flags.DEFINE_bool('plot_preds', default=True, help='plot pred plots')
flags.DEFINE_bool('random_noise', default=True, help='random noise to output')
flags.DEFINE_float('maxval', default=0.1, help='random noise to output')
flags.DEFINE_float('minval', default=0.0, help='random noise to output')
flags.DEFINE_float('noise_std', default=0.02, help='random noise to output')
# Architecture
flags.DEFINE_string('arch', default='vgg', help='')
flags.DEFINE_string('output', default='binned', help='')
flags.DEFINE_integer('coarse_bin', default=64, help='')
#flags.DEFINE_string('loss/output', default='vgg', help='')
flags.DEFINE_bool('coord_all', default=False, help='always use coord convs')
flags.DEFINE_bool('batch_norm', default=False, help='')
batch_size=FLAGS.batch_size,
learning_rate=FLAGS.learning_rate,
clean_train=FLAGS.clean_train,
backprop_through_attack=FLAGS.backprop_through_attack,
nb_filters=FLAGS.nb_filters)
if __name__ == '__main__':
flags.DEFINE_float('label_smooth', 0.1,
("Amount to subtract from correct label "
"and distribute among other labels"))
flags.DEFINE_list('attack_type', ['fgsm', 'pgd'],
("Attack type: 'fgsm'->'fast gradient sign method', "
"'pgd'->'projected gradient descent', "
"'bim'->'basic iterative method',"
"'cwl2'->'Carlini & Wagner L2',"
"'jsma'->'jsma method'"))
flags.DEFINE_string('dataset', 'mnist',
("dataset: 'mnist'->'mnist dataset', "
"'fmnist'->'fashion mnist dataset', "
"'cifar10'->'cifar-10 dataset'"))
flags.DEFINE_string(
'attack_model', 'mnist_model',
("defence_model: 'basic_model'->'a cnn model for mnist', "
"'all_cnn'->'a cnn model for cifar10', "
"'cifar10_model'->'model for cifar10', "
"'mnist_model'->'model for mnist'"))
flags.DEFINE_integer('nb_filters', NB_FILTERS, 'Model size multiplier')
flags.DEFINE_integer('nb_epochs', NB_EPOCHS,
'Number of epochs to train model')
import os
import tensorflow as tf
from tensorflow.python.platform import flags
from a02_textcnn.model import Model
from utils.preprocess import build_corpus
FLAGS = flags.FLAGS
flags.DEFINE_integer('batch_size', 256, 'count of each batch for train')
flags.DEFINE_integer('embed_size', 100, 'dims of word embedding')
flags.DEFINE_integer('class_num', 2, 'class num')
flags.DEFINE_list('filters', [2, 3, 4], 'filters')
flags.DEFINE_integer('filter_num', 10, 'filter_num')
flags.DEFINE_integer('channel_size', 1, 'channel_size')
flags.DEFINE_float('keep_prob', 0.9, 'keep_prob')
flags.DEFINE_float('learning_rate', 0.9, 'learning rate')
flags.DEFINE_integer('decay_step', 100, 'decay learning rate every decay_step')
flags.DEFINE_float('decay_rate', 0.9, 'decay learning rate with decay_rate')
flags.DEFINE_integer('epoch_num', 500, 'the number of epoch')
flags.DEFINE_integer('epoch_val', 50, 'the freq for test val')
flags.DEFINE_string('check_point', 'checkpoint/', 'checkpoint path')
def main(_):
train, test, _, sentence_size, vocab_size = build_corpus()
train_x, train_y = train
test_x, test_y = test
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
with tf.Session(config=config) as sess:
model = Model(sentence_size, FLAGS.class_num, vocab_size,
## Dataset/method options
flags.DEFINE_integer(
'num_classes', 2,
'number of classes used in classification (e.g. 5-way classification).')
flags.DEFINE_string('training_data_path',
'input/feature_extraction_train_updated.csv',
'path to training data')
flags.DEFINE_string('testing_data_path',
'input/feature_extraction_test_updated.csv',
'path to testing data')
flags.DEFINE_string('target_variable', 'label',
'name of the target variable column')
flags.DEFINE_list('cols_drop', [
'article_title', 'article_content', 'source', 'source_category', 'unit_id'
], 'list of column to drop from data, if any')
flags.DEFINE_string('special_encoding', 'latin-1',
'special encoding needed to read the data, if any')
flags.DEFINE_string('scaling', 'z-score',
'scaling done to the dataset, if any')
flags.DEFINE_integer('pretrain_iterations', 0,
'number of pre-training iterations.')
flags.DEFINE_integer('metatrain_iterations', 1000,
'number of metatraining iterations.')
flags.DEFINE_integer('meta_batch_size', 32,
'number of tasks sampled per meta-update')
flags.DEFINE_float('meta_lr', 0.1, 'the base learning rate of the generator')
flags.DEFINE_integer(
import os
import tensorflow as tf
from tensorflow.python.platform import flags
from a04_dcnn.model import Model
from utils.preprocess import build_corpus
FLAGS = flags.FLAGS
flags.DEFINE_integer('batch_size', 256, 'count of each batch for train')
flags.DEFINE_integer('embed_size', 100, 'dims of word embedding')
flags.DEFINE_integer('class_num', 2, 'class num')
flags.DEFINE_list('filters', [2, 3, 4], 'filters')
flags.DEFINE_list('filter_num', [5, 10], 'filter_num')
flags.DEFINE_integer('channel_size', 1, 'channel_size')
flags.DEFINE_float('keep_prob', 0.5, 'keep_prob')
flags.DEFINE_float('learning_rate', 0.01, 'learning rate')
flags.DEFINE_integer('decay_step', 100, 'decay learning rate every decay_step')
flags.DEFINE_float('decay_rate', 0.9, 'decay learning rate with decay_rate')
flags.DEFINE_integer('epoch_num', 500, 'the number of epoch')
flags.DEFINE_integer('epoch_val', 50, 'the freq for test val')
flags.DEFINE_integer('k1', 20, 'the freq for test val')
flags.DEFINE_integer('k_top', 4, 'the freq for test val')
flags.DEFINE_string('check_point', 'checkpoint/', 'checkpoint path')
def main(_):
train, test, _, sentence_size, vocab_size = build_corpus()
train_x, train_y = train
test_x, test_y = test
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
def getFlag(model_name):
use_time = False
if use_time:
exp_name = datetime.datetime.now().strftime("%I:%M%p-%Y-%B-%d")
else:
exp_name = 'test'
FLAGS = flags.FLAGS
# Dataset Options:
flags.DEFINE_integer('batch_size', 8, 'Size of a batch')
# Base Model class Mandatory:
flags.DEFINE_bool('train', True, 'whether to train or test')
flags.DEFINE_bool('verbose', True,
'whether to show print information or not')
flags.DEFINE_integer('epoch', 30, 'Number of Epochs to train on')
flags.DEFINE_string('exp', exp_name, 'name of experiments')
flags.DEFINE_integer('log_interval', 1, 'log outputs every so many epoch')
flags.DEFINE_integer('val_interval', 3, 'validate every so many epoch')
flags.DEFINE_integer(
'patience', 3,
'number of non-improving validation iterations before early stop')
flags.DEFINE_integer('save_interval', 10,
'save outputs every so many iterations')
## Saver load or options:
flags.DEFINE_integer('max_to_keep', 10, 'maximum number of models to keep')
flags.DEFINE_integer('keep_checkpoint_every_n_hours', 3,
'check point intervals')
flags.DEFINE_integer(
'resume_iter', -1,
'iteration to resume training from, -1 means not resuming')
flags.DEFINE_string('ckptdir', global_macros.CKPT_ROOT + "/" + model_name,
'location where models will be stored')
flags.DEFINE_string('logdir', global_macros.LOGGER_ROOT + "/" + model_name,
'location where log of experiments will be stored')
## Plot option:
flags.DEFINE_bool('plot', True, 'plot after training')
flags.DEFINE_bool('crop', False, 'crop regions')
flags.DEFINE_bool('crop_stack', True, 'crop stack/ random crop')
# learning rate
flags.DEFINE_bool('L1_loss', False, 'Use L1 or L2 loss')
flags.DEFINE_bool('weight_decay', False, 'Turn on weight decay or not')
flags.DEFINE_float('lr', 1e-4, 'Learning rate for training')
flags.DEFINE_float('lr_decay_val', 10, 'Learning rate decay ratio')
flags.DEFINE_bool('recompute', False, 'use recomputation')
# Model specific:
flags.DEFINE_bool('temp_only', False,
'only use temperature channel or not')
flags.DEFINE_bool('ssim', False, 'use ssim loss or not')
# Unet specific:
flags.DEFINE_bool('is_pad', True, 'Use padding for convolution or not')
flags.DEFINE_integer('nfilters', 8, 'The number of base filters for unet')
flags.DEFINE_integer('unet_levels', 3, 'Levels of Unet')
flags.DEFINE_bool('img_emb', False, 'Use image embedding or not')
# LCN specific:
flags.DEFINE_list('lcn_kernel', [1, 3, 3], 'Kernel list for lcn model')
flags.DEFINE_bool('regularize', False, 'Turn on regularizer for LCN')
flags.DEFINE_float('alpha', 1e5, 'Regularizer value')
# tile conv LCN
flags.DEFINE_bool('use_LCN', False,
'use LCN as the last layer, tile conv LCN only')
return FLAGS
# Training Options
flags.DEFINE_integer('iterations', 500000,
'The number of training iterations.')
flags.DEFINE_integer(
'batch_size', 64,
'The number of tasks sampled per batch (aka batch size).')
flags.DEFINE_float('lr', 0.0001, 'The learning rate.')
flags.DEFINE_integer('support', 5,
'The number of support examples per task (aka k-shot).')
flags.DEFINE_integer('query', 5, 'The number of query examples per task.')
flags.DEFINE_integer('embedding', 20, 'The embedding size.')
# Model Options
flags.DEFINE_string('activation', 'relu', 'One of relu, elu, or leaky_relu.')
flags.DEFINE_bool('max_pool', False, 'Use max pool rather than strides.')
flags.DEFINE_list('filters', [32, 64],
'List of filters per convolution layer.')
flags.DEFINE_list('kernels', [3, 3],
'List of kernel sizes per convolution layer.')
flags.DEFINE_list(
'strides', [2, 2], 'List of strides per convolution layer. '
'Can be None if using max pooling.')
flags.DEFINE_list('fc_layers', [64, 64],
'List of fully connected nodes per layer.')
flags.DEFINE_float('drop_rate', 0.0, 'Dropout probability. 0 for no dropout.')
flags.DEFINE_string('norm', None, 'One of layer, batch, or None')
# Loss Options
flags.DEFINE_float('lambda_embedding', 1.0, 'Lambda for the embedding loss.')
flags.DEFINE_float('lambda_support', 1.0,
'Lambda for the support control loss.')
flags.DEFINE_float('lambda_query', 1.0, 'Lambda for the query control loss.')