ium_426206/dlgssdpytorch.py
2021-06-12 17:19:51 +02:00

132 lines
4.8 KiB
Python

import torch
import numpy as np
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import Dataset, TensorDataset, DataLoader
import argparse
from sacred import Experiment
from sacred.observers import MongoObserver, FileStorageObserver
ex = Experiment("426206", interactive=False, save_git_info=False)
ex.observers.append(FileStorageObserver('my_runs'))
ex.observers.append(MongoObserver(url='mongodb://mongo_user:mongo_password_IUM_2021@172.17.0.1:27017', db_name='sacred'))
class LayerLinearRegression(nn.Module):
def __init__(self):
super().__init__()
# Instead of our custom parameters, we use a Linear layer with single input and single output
self.linear = nn.Linear(1, 1)
def forward(self, x):
# Now it only takes a call to the layer to make predictions
return self.linear(x)
# parser = argparse.ArgumentParser(description='Program do uczenia modelu')
# parser.add_argument('-l', '--lr', type=float, default=1e-3, help="Współczynik uczenia (lr)", required=False)
# parser.add_argument('-e', '--epochs', type=int, default=100, help="Liczba epok", required=False)
# args = parser.parse_args()
#python3 dlgssdpytorch.py with lr=0.01 n_epochs=10
@ex.config
def my_config():
lr = 1e-3
n_epochs = 20
@ex.capture
def train(lr, n_epochs, _run):
train_dataset = torch.load('train_dataset.pt')
#val_dataset = torch.load('val_dataset.pt')
train_loader = DataLoader(dataset=train_dataset)
#val_loader = DataLoader(dataset=val_dataset)
model = LayerLinearRegression()
# Checks model's parameters
#print(model.state_dict())
loss_fn = nn.MSELoss(reduction='mean')
optimizer = optim.SGD(model.parameters(), lr=lr)
def make_train_step(model, loss_fn, optimizer):
# Builds function that performs a step in the train loop
def train_step(x, y):
# Sets model to TRAIN mode
model.train()
# Makes predictions
yhat = model(x)
# Computes loss
loss = loss_fn(y, yhat)
# Computes gradients
loss.backward()
# Updates parameters and zeroes gradients
optimizer.step()
optimizer.zero_grad()
# Returns the loss
return loss.item()
# Returns the function that will be called inside the train loop
return train_step
# Creates the train_step function for our model, loss function and optimizer
train_step = make_train_step(model, loss_fn, optimizer)
training_losses = []
validation_losses = []
#print(model.state_dict())
# For each epoch...
for epoch in range(n_epochs):
_run.log_scalar("Epoch", str(epoch))
losses = []
# Uses loader to fetch one mini-batch for training
for x_batch, y_batch in train_loader:
# NOW, sends the mini-batch data to the device
# so it matches location of the MODEL
# x_batch = x_batch.to(device)
# y_batch = y_batch.to(device)
# One stpe of training
loss = train_step(x_batch, y_batch)
losses.append(loss)
training_loss = np.mean(losses)
training_losses.append(training_loss)
_run.log_scalar("MSE", str(training_loss))
# After finishing training steps for all mini-batches,
# it is time for evaluation!
# Ewaluacja jest już tutaj nie potrzebna bo odbywa sie w evaluation.py. Można jednak włączyć podgląd ewaluacji dla poszczególnych epok.
# # We tell PyTorch to NOT use autograd...
# # Do you remember why?
# with torch.no_grad():
# val_losses = []
# # Uses loader to fetch one mini-batch for validation
# for x_val, y_val in val_loader:
# # Again, sends data to same device as model
# # x_val = x_val.to(device)
# # y_val = y_val.to(device)
# model.eval()
# # Makes predictions
# yhat = model(x_val)
# # Computes validation loss
# val_loss = loss_fn(y_val, yhat)
# val_losses.append(val_loss.item())
# validation_loss = np.mean(val_losses)
# validation_losses.append(validation_loss)
# print(f"[{epoch+1}] Training loss: {training_loss:.3f}\t Validation loss: {validation_loss:.3f}")
print(f"[{epoch+1}] Training loss: {training_loss:.3f}\t")
torch.save({
'model_state_dict': model.state_dict(),
'optimizer_state_dict': optimizer.state_dict(),
'loss': lr,
}, 'model.pt')
@ex.automain
def my_main(lr, n_epochs, _run):
train(lr, n_epochs, _run)
ex.run()
ex.add_artifact('model.pt')