def test_console_log_callback(self):
total_instances = 1000
batch_size = 25
reader = FakeDatasetReader(total_instances, batch_size)
data_loader = SimpleDataLoader.from_dataset_reader(
reader, "fake_path", batch_size=batch_size)
instances = list(data_loader.iter_instances())
vocab = Vocabulary.from_instances(instances)
data_loader.index_with(vocab)
model = FakeModel(vocab)
optimizer = torch.optim.SGD(model.parameters(), 0.01, momentum=0.9)
trainer = GradientDescentTrainer(
model,
optimizer,
data_loader,
num_epochs=3,
serialization_dir=self.TEST_DIR,
callbacks=[
ConsoleLoggerCallback.from_params(
Params({"should_log_inputs": True}),
serialization_dir=self.TEST_DIR,
)
],
)
trainer.train()
def test_trainer_can_log_batch_inputs(self):
total_instances = 1000
batch_size = 25
reader = FakeDatasetReader(total_instances, batch_size)
data_loader = SimpleDataLoader.from_dataset_reader(
reader, "fake_path", batch_size=batch_size)
instances = list(data_loader.iter_instances())
vocab = Vocabulary.from_instances(instances)
data_loader.index_with(vocab)
model = FakeModel(vocab)
optimizer = torch.optim.SGD(model.parameters(), 0.01, momentum=0.9)
trainer = GradientDescentTrainer(
model,
optimizer,
data_loader,
num_epochs=2,
serialization_dir=self.TEST_DIR,
callbacks=[
TensorBoardCallback(
serialization_dir=self.TEST_DIR,
distribution_interval=2,
)
],
)
trainer.train()
vocab=vocab)
tgt_char_encoder = TokenCharactersEncoder(embedding=tgt_char_embedding,
encoder=GruSeq2VecEncoder(input_size=args.emb_dim,
hidden_size=args.hid_dim))
src_embedders = BasicTextFieldEmbedder({
"tokens": src_embedding,
"character_tokens": src_char_encoder
})
tgt_embedders = BasicTextFieldEmbedder({
"tokens": tgt_embedding,
"character_tokens": tgt_char_encoder
})
train_loader = SimpleDataLoader.from_dataset_reader(
reader=dataset_reader,
data_path=args.train_file,
batch_size=args.bs,
shuffle=True)
train_loader.index_with(vocab)
val_loader = SimpleDataLoader.from_dataset_reader(reader=dataset_reader,
data_path=args.valid_file,
batch_size=args.bs)
val_loader.index_with(vocab)
model = create_seq2seqmodel(vocab, src_embedders=src_embedders, tgt_embedders=tgt_embedders, hidden_dim=args.hid_dim,
max_decoding_steps=args.maxlen, device=device)
def count_parameters(model):
return sum(p.numel() for p in model.parameters() if p.requires_grad)
print(f"The model has {count_parameters(model)} parameters.")
save_dir = None
if args.save: