def main():
dataloader = CorpusReader("./data/wili-2018/x_train_sub.txt",
"./data/wili-2018/y_train_sub.txt")
char_to_idx, idx_to_char, char_frequency = dataloader.get_mappings()
model = SkipGram(12300, 256, char_frequency)
with open("./models/skipgram/5.pt", 'rb') as f:
state_dict = torch.load(f)
model.load_state_dict(state_dict)
print("Model Loaded")
save_embeddings = True
if save_embeddings:
central_embeddings = model.central_embedding.weight
torch.save(central_embeddings, './models/character_embeddings.pt')
print("{} Embedding Weights Saved".format(central_embeddings.shape))
model = model.to(device)
model.eval()
similarities = model.vocabulary_similarities()
show_chars = [
't', 'b', 'a', 'e', 'x', ',', '.', '@', '%', '4', '9', "բ", "Հ", "ñ",
"名", "Θ"
]
show_results(show_chars, similarities, char_to_idx, idx_to_char)
def train_skipgram(vocab, sg_loader):
losses = []
loss_fn = nn.L1Loss()
model = SkipGram(len(vocab), embed_size, simple)
print(model)
if load_prev:
try:
model.load_state_dict(torch.load(model_file))
except:
print('Could not load file')
optimizer = optim.SGD(model.parameters(), lr=learning_rate)
for epoch in range(n_epoch):
total_loss = 0.0
for i, sample_batched in enumerate(sg_loader):
sample_batched = sample_batched[0]
in_w_var = Variable(sample_batched[:, 0])
ctx_w_var = Variable(sample_batched[:, 1])
# print(in_w_var.shape)
model.zero_grad()
log_probs = model(in_w_var, ctx_w_var)
loss = loss_fn(log_probs, Variable(sample_batched[:, 2].float()))
loss.backward()
optimizer.step()
total_loss += loss.data
losses.append(total_loss.item())
print('Epoch:', epoch, 'Loss:', total_loss.item())
save_params(vocab, model, losses)
return model, losses
