def train():
print("Loading data...")
SRC, TGT, train, val, test = generate_dataloaders()
devices = [0, 1, 2, 3]
pad_idx = TGT.vocab.stoi["<blank>"]
print("Making model...")
model = make_model(len(SRC.vocab), len(TGT.vocab), N=6)
model.cuda()
criterion = LabelSmoothing(
size=len(TGT.vocab), padding_idx=pad_idx, smoothing=0.1)
criterion.cuda()
BATCH_SIZE = 12000
train_iter = BatchIterator(train, batch_size=BATCH_SIZE, device=torch.device(0),
repeat=False, sort_key=lambda x: (len(x.src), len(x.trg)),
batch_size_fn=batch_size_fn, train=True)
valid_iter = BatchIterator(val, batch_size=BATCH_SIZE, device=torch.device(0),
repeat=False, sort_key=lambda x: (len(x.src), len(x.trg)),
batch_size_fn=batch_size_fn, train=False)
model_par = nn.DataParallel(model, device_ids=devices)
model_opt = NoamOpt(model.src_embed[0].d_model, 1, 2000,
torch.optim.Adam(model.parameters(), lr=0, betas=(0.9, 0.98), eps=1e-9))
folder = get_unique_folder("./models/", "model")
if not(os.path.exists(folder)):
os.mkdir(folder)
for epoch in tqdm(range(10)):
model_par.train()
run_epoch((rebatch(pad_idx, b) for b in train_iter),
model_par,
MultiGPULossCompute(model.generator, criterion,
devices=devices, opt=model_opt))
model_par.eval()
loss = run_epoch((rebatch(pad_idx, b) for b in valid_iter),
model_par,
MultiGPULossCompute(model.generator, criterion,
devices=devices, opt=None))
torch.save(model.state_dict, os.path.join(folder, "model.bin." + str(epoch)))
print(loss)
for i, batch in enumerate(valid_iter):
src = batch.src.transpose(0, 1)[:1]
src_mask = (src != SRC.vocab.stoi["<blank>"]).unsqueeze(-2)
out = greedy_decode(model, src, src_mask,
max_len=60, start_symbol=TGT.vocab.stoi["<s>"])
print("Translation:", end="\t")
for i in range(1, out.size(1)):
sym = TGT.vocab.itos[out[0, i]]
if sym == "</s>":
break
print(sym, end=" ")
print()
print("Target:", end="\t")
for i in range(1, batch.trg.size(0)):
sym = TGT.vocab.itos[batch.trg.data[i, 0]]
if sym == "</s>":
break
print(sym, end=" ")
print()
break
def rebatch(pad_idx, batch):
"Fix order in torchtext to match ours"
src, trg = batch.src.transpose(0, 1), batch.trg.transpose(0, 1)
return Batch(src, trg, pad_idx)
# GPUs to use
devices = [0, 1, 2, 3]
if True:
pad_idx = TGT.vocab.stoi["<blank>"]
model = make_model(len(SRC.vocab), len(TGT.vocab), N=6)
model.cuda()
criterion = LabelSmoothing(size=len(TGT.vocab), padding_idx=pad_idx, smoothing=0.1)
criterion.cuda()
BATCH_SIZE = 12000
train_iter = MyIterator(train, batch_size=BATCH_SIZE, device=0,
repeat=False, sort_key=lambda x: (len(x.src), len(x.trg)),
batch_size_fn=batch_size_fn, train=True)
valid_iter = MyIterator(val, batch_size=BATCH_SIZE, device=0,
repeat=False, sort_key=lambda x: (len(x.src), len(x.trg)),
batch_size_fn=batch_size_fn, train=False)
model_par = nn.DataParallel(model, device_ids=devices)
None
if False:
model_opt = NoamOpt(model.src_embed[0].d_model, 1, 2000,
torch.optim.Adam(model.parameters(), lr=0, betas=(0.9, 0.98), eps=1e-9))
for epoch in range(10):