def main():
dataset_train = tf.data.TFRecordDataset(train_file)
dataset_val = tf.data.TFRecordDataset(val_file)
dataset_train = dataset_train.map(parsing_record)
dataset_val = dataset_val.map(parsing_record)
deepFM = DeepFM(config.data_size["feature_size"],
config.data_size["field_size"], config.model_conf)
deepFM.train(dataset_train,
dataset_val=dataset_val,
epochs=500,
batch_size=128)
num_contns= num_contns,
k= k,
hidden_dims= hidden_dims,
dropout= p,
n_class= n_class,
sparse= sparse).to(device)
optimizer = torch.optim.Adam(model.parameters(), lr= lr)
criterion= nn.BCEWithLogitsLoss(pos_weight=torch.tensor(pos_weight, device= device))
print('model created.')
# lr_scheduler = torch.optim.lr_scheduler.StepLR(optimizer, step_size=step_size, gamma= 0.3, verbose= True)
'''training phase'''
for epoch in range(n_epoch):
model.train()
train_loss= 0
train_score= 0
val_score= 0
train_preds, train_gts = [], []
val_preds, val_gts = [], []
'''train'''
for i, (X_cat, X_dense, y) in enumerate(tqdm(train_loader)):
optimizer.zero_grad()
output= model(X_cat.to(device), X_dense.to(device))
loss= criterion(output, y.unsqueeze(dim= 1).to(device))
loss.backward()
optimizer.step()
train_loss += loss.item()
output_boolean = nn.Sigmoid()(output.squeeze(dim= 1))>=threshold