61 lines
2.0 KiB
Python
61 lines
2.0 KiB
Python
import numpy as np
|
|
import torch
|
|
from gensim import downloader
|
|
import gensim
|
|
|
|
with open(r"C:\Users\Kacper Dudzic\Desktop\paranormal-or-skeptic\train\in.tsv", "r", encoding="utf-8") as f:
|
|
X_train = [line.strip() for line in f.readlines()]
|
|
with open(r"C:\Users\Kacper Dudzic\Desktop\paranormal-or-skeptic\train\expected.tsv", "r", encoding="utf-8") as f:
|
|
Y_train = np.array([int(line.strip()) for line in f.readlines()])
|
|
|
|
glove_vectors = downloader.load("glove-wiki-gigaword-100")
|
|
X_train = [np.mean([glove_vectors[tk] for tk in gensim.utils.tokenize(text, lowercase=True) if tk in glove_vectors] or
|
|
[np.zeros(100)], axis=0) for text in X_train]
|
|
|
|
|
|
class NeuralNetworkModel(torch.nn.Module):
|
|
|
|
def __init__(self):
|
|
super(NeuralNetworkModel, self).__init__()
|
|
self.fc1 = torch.nn.Linear(100, 500)
|
|
self.fc2 = torch.nn.Linear(500, 1)
|
|
|
|
def forward(self, x):
|
|
x = self.fc1(x)
|
|
x = torch.relu(x)
|
|
x = self.fc2(x)
|
|
x = torch.sigmoid(x)
|
|
return x
|
|
|
|
|
|
nn_model = NeuralNetworkModel()
|
|
criterion = torch.nn.BCELoss()
|
|
optimizer = torch.optim.Adam(nn_model.parameters())
|
|
|
|
BATCH_SIZE = 5
|
|
for epoch in range(5):
|
|
loss_score = 0
|
|
acc_score = 0
|
|
items_total = 0
|
|
nn_model.train()
|
|
for i in range(0, Y_train.shape[0], BATCH_SIZE):
|
|
X = X_train[i:i + BATCH_SIZE]
|
|
X = torch.tensor(np.array(X).astype(np.float32))
|
|
Y = Y_train[i:i + BATCH_SIZE]
|
|
Y = torch.tensor(Y.astype(np.float32)).reshape(-1, 1)
|
|
Y_predictions = nn_model(X)
|
|
acc_score += torch.sum((Y_predictions > 0.5) == Y).item()
|
|
items_total += Y.shape[0]
|
|
optimizer.zero_grad()
|
|
loss = criterion(Y_predictions, Y)
|
|
loss.backward()
|
|
optimizer.step()
|
|
|
|
loss_score += loss.item() * Y.shape[0]
|
|
|
|
print(epoch)
|
|
print((loss_score / items_total), (acc_score / items_total))
|
|
|
|
PATH = "new_model_full.pt"
|
|
torch.save(nn_model, PATH)
|