def generate_features(self, out_file, feat_extractor, transform_type):
data = self.train_data+self.val_data+self.test_data
transform = data_utils.imagenet_transform('test', transform_type)
if feat_extractor is None:
feat_extractor = torchvision.models.resnet18(pretrained=True)
feat_extractor.fc = torch.nn.Sequential()
feat_extractor.eval().cuda()
image_feats = []
image_files = []
for chunk in tqdm.tqdm(data_utils.chunks(data, 512), total=len(data)//512):
files = zip(*chunk)[0]
imgs = list(map(self.loader, files))
imgs = list(map(transform, imgs))
feats = feat_extractor(torch.stack(imgs, 0).cuda())
image_feats.append(feats.data.cpu())
image_files += files
image_feats = torch.cat(image_feats, 0)
print ('features for %d images generated'%(len(image_files)))
torch.save({'features': image_feats, 'files': image_files}, out_file)
def train(self,
pivot_ids,
target_ids,
doc_ids,
num_epochs,
idx_to_word,
switch_loss_epoch=5,
save_every=1,
report_every=1,
print_topics_every=5):
data_size = len(pivot_ids)
temp_fraction = self.batch_size * 1.0 / data_size
self.sesh.run(tf.assign(self.fraction, temp_fraction))
iters_per_epoch = int(data_size / self.batch_size) + np.ceil(
data_size % self.batch_size)
switch_loss_step = iters_per_epoch * switch_loss_epoch
self.sesh.run(tf.assign(self.switch_loss, switch_loss_step))
if self.save_graph:
saver = tf.train.Saver()
writer = tf.summary.FileWriter(self.logdir + '/',
graph=self.sesh.graph)
for epoch in range(num_epochs):
print('\nEPOCH:', epoch + 1)
for pivot, target, doc in chunks(self.batch_size, pivot_ids,
target_ids, doc_ids):
feed_dict = {self.x: pivot, self.y: target, self.docs: doc}
fetches = [
self.merged, self.optimizer, self.loss, self.loss_word2vec,
self.loss_lda, self.step
]
summary, _, l, lw2v, llda, step = self.sesh.run(
fetches, feed_dict=feed_dict)
if (epoch + 1) % report_every == 0:
print('Loss: ', l, 'Word2Vec Loss: ', lw2v, 'LDA loss: ', llda)
if (epoch + 1) % save_every == 0 and self.save_graph:
writer.add_summary(summary, step)
writer.flush()
writer.close()
save_path = saver.save(self.sesh, self.logdir + '/model.ckpt')
writer = tf.summary.FileWriter(self.logdir + '/',
graph=self.sesh.graph)
if epoch > 0 and (epoch + 1) % print_topics_every == 0:
idxs = np.arange(self.num_topics)
words, sims = self.get_k_closest(idxs,
idx_to_word=idx_to_word,
k=10)
if self.save_graph and (epoch + 1) % save_every != 0:
writer.add_summary(summary, step)
writer.flush()
writer.close()
save_path = saver.save(self.sesh, self.logdir + '/model.ckpt')