def load_data_wiki(batch_size, max_len):
num_workers = d2l.get_dataloader_workers()
data_dir = d2l.download_extract('wikitext-2', 'wikitext-2')
paragraphs = _read_wiki(data_dir)
train_set = _WikiTextDataset(paragraphs, max_len)
train_iter = gluon.data.DataLoader(train_set,
batch_size,
shuffle=True,
num_workers=num_workers)
return train_iter, train_set.vocab
def load_data_snli(batch_size, num_steps=50):
"""Download the SNLI dataset and return data iterators and vocabulary."""
num_workers = d2l.get_dataloader_workers()
data_dir = 'E:\AI\projects\Text Inference with Attention Mechanisms\snli_1.0'
train_data = read_snli(data_dir, True)
test_data = read_snli(data_dir, False)
train_set = SNLIDataset(train_data, num_steps)
test_set = SNLIDataset(test_data, num_steps, train_set.vocab)
train_iter = gluon.data.DataLoader(train_set, batch_size, shuffle=True,
num_workers=num_workers)
test_iter = gluon.data.DataLoader(test_set, batch_size, shuffle=False,
num_workers=num_workers)
return train_iter, test_iter, train_set.vocab
np.sum(np.sign(test_data)))
return float(rmse)
#%%
devices = d2l.try_all_gpus()
df, num_users, num_items = d2l.read_data_ml100k()
train_data, test_data = d2l.split_data_ml100k(df, num_users, num_items)
_, _, _, train_inter_mat = d2l.load_data_ml100k(train_data, num_users,
num_items)
_, _, _, test_inter_mat = d2l.load_data_ml100k(test_data, num_users, num_items)
train_iter = gluon.data.DataLoader(train_inter_mat,
shuffle=True,
last_batch='rollover',
batch_size=256,
num_workers=d2l.get_dataloader_workers())
test_iter = gluon.data.DataLoader(np.array(train_inter_mat),
shuffle=False,
last_batch="keep",
batch_size=1024,
num_workers=d2l.get_dataloader_workers())
net = AutoRec(500, num_users)
net.initialize(ctx=devices, force_reinit=True, init=mx.init.Normal(0.01))
lr, num_epochs, wd, optimizer = 0.002, 25, 1e-5, 'adam'
loss = gluon.loss.L2Loss()
trainer = gluon.Trainer(net.collect_params(), optimizer, {
"learning_rate": lr,
'wd': wd
})
d2l.train_recsys_rating(net,
train_iter,