I am new to Pytorch. I was trying to model a binary classifier on the Kepler dataset. The following was my dataset class.
class KeplerDataset(Dataset):
def __init__(self, test=False):
self.dataframe_orig = pd.read_csv(koi_cumm_path)
if (test == False):
self.data = df_numeric[( df_numeric.koi_disposition == 1 ) | ( df_numeric.koi_disposition == 0 )].values
else:
self.data = df_numeric[~(( df_numeric.koi_disposition == 1 ) | ( df_numeric.koi_disposition == 0 ))].values
self.X_data = torch.FloatTensor(self.data[:, 1:])
self.y_data = torch.FloatTensor(self.data[:, 0])
def __len__(self):
return len(self.data)
def __getitem__(self, index):
return self.X_data[index], self.y_data[index]
Here, I created a custom classifier class with one hidden layer and a single output unit that produces sigmoidal probability of being in class 1 (planet).
class KOIClassifier(nn.Module):
def __init__(self, input_dim, out_dim):
super(KOIClassifier, self).__init__()
self.linear1 = nn.Linear(input_dim, 32)
self.linear2 = nn.Linear(32, 32)
self.linear3 = nn.Linear(32, out_dim)
def forward(self, xb):
out = self.linear1(xb)
out = F.relu(out)
out = self.linear2(out)
out = F.relu(out)
out = self.linear3(out)
out = torch.sigmoid(out)
return out
I then created a train_model function to optimize the loss using SGD.
def train_model(X, y):
criterion = nn.BCELoss()
optim = torch.optim.SGD(model.parameters(), lr=0.001)
n_epochs = 100
losses = []
for epoch in range(n_epochs):
y_pred = model.forward(X)
loss = criterion(y_pred, y)
losses.append(loss.item())
optim.zero_grad()
loss.backward()
optim.step()
losses = []
for X, y in train_loader:
losses.append(train_model(X, y))
But after performing the optimization over the train_loader, When I try predicting on the trainn_loader itself, the prediction values are so much worse.
for features, y in train_loader:
y_pred = model.predict(features)
break
y_pred
> tensor([[4.5436e-02],
[1.5024e-02],
[2.2579e-01],
[4.2279e-01],
[6.0811e-02],
.....
Why is my model not working properly? Is it the problem with the dataset or am I doing something wrong with implementing the Neural net? I will link my Kaggle notebook because more context might be helpful. Please help.
You are optimizing many times (100 steps) on the first batch (first samples), then moving to the next samples. It means that your model will overfit your few samples before going to the next batch. Then, your training will be very non smooth, diverge and go far from your global optimum.
Usually, in a training loop you should:
go over all samples (this is one epoch)
shuffle your dataset in order to visit your samples in a different order (set your pytorch training loader accordingly)
go back to 1. until you reach the max number of epochs
Also you should not define your optimizer each time (nor your criterion).
Your training loop should look like this:
criterion = nn.BCELoss()
optim = torch.optim.SGD(model.parameters(), lr=0.001)
n_epochs = 100
def train_model():
for X, y in train_loader:
optim.zero_grad()
y_pred = model.forward(X)
loss = criterion(y_pred, y)
loss.backward()
optim.step()
for epoch in range(n_epochs):
train_model()
Related
I am training a neural network using pytorch. here is the code for my model and training loop.
class AccidentModel(nn.Module):
def __init__(self):
super().__init__()
self.fc1 = nn.Linear(89, 1600)
self.act1 = nn.ReLU()
self.fc2 = nn.Linear(1600, 800)
self.act2 = nn.ReLU()
self.dropout = nn.Dropout(p=0.5)
self.act3 = nn.Softmax()
self.fc3 = nn.Linear(800, 2)
def forward(self, x):
x = self.fc1(x)
x = self.act1()
x = self.fc2(x)
x = self.act2()
x = self.dropout(x)
x = self.act3()
x = self.fc3(X)
return x
def train(train_dl, model, epochs, losses, accuracies):
loss_function = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.0001)
for epoch in range(epochs):
with tqdm.tqdm(train_dl, unit="batch") as tepoch:
for (features, target) in tepoch:
tepoch.set_description(f"Epoch {epoch}")
optimizer.zero_grad()
features, target = features.to(get_device()), target.to(get_device())
output = model(features.float())
target = target.view(-1)
loss = loss_function(output, target)
loss.backward()
optimizer.step()
output = torch.argmax(output, dim=1)
correct = (output == target).float().sum()
accuracy = correct / features.shape[0]
losses.append(loss)
accuracies.append(accuracy)
tepoch.set_postfix(loss=loss.item(), accuracy=accuracy.item())
and here is the evolution of the accuracy (orange) and the loss (blue) function:
My question is if my model is really learning or not? anf how to interpret this graph?
thanks,
No it's not learning, your loss is not decreasing in this case of classification.
What type of datas are you using ? text ? images ? It might be good to begin with a "classical" architecture according to the task.
You may have to delete your third activation which is not necessary and/or wrongly placed.
There are a lot of guides for beginners online ...
I am learning pytorch, that to do a basic linear regression on this data created this way here:
from sklearn.datasets import make_regression
x, y = make_regression(n_samples=100, n_features=1, noise=15, random_state=42)
y = y.reshape(-1, 1)
print(x.shape, y.shape)
plt.scatter(x, y)
I know that using tensorflow this code can solve:
model = tf.keras.models.Sequential()
model.add(tf.keras.layers.Dense(units=1, activation='linear', input_shape=(x.shape[1], )))
model.compile(optimizer=tf.keras.optimizers.SGD(lr=0.05), loss='mse')
hist = model.fit(x, y, epochs=15, verbose=0)
but I need to know what the pytorch equivalent would be like, what I tried to do was this:
# Model Class
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.linear = nn.Linear(1,1)
def forward(self, x):
x = self.linear(x)
return x
def predict(self, x):
return self.forward(x)
model = Net()
loss_fn = F.mse_loss
opt = torch.optim.SGD(modelo.parameters(), lr=0.05)
# Funcao para treinar
def fit(num_epochs, model, loss_fn, opt, train_dl):
# Repeat for given number of epochs
for epoch in range(num_epochs):
# Train with batches of data
for xb, yb in train_dl:
# 1. Generate predictions
pred = model(xb)
# 2. Calculate Loss
loss = loss_fn(pred, yb)
# 3. Campute gradients
loss.backward()
# 4. Update parameters using gradients
opt.step()
# 5. Reset the gradients to zero
opt.zero_grad()
# Print the progress
if (epoch+1) % 10 == 0:
print('Epoch [{}/{}], Loss: {:.4f}'.format(epoch+1, num_epochs, loss.item()))
# Training
fit(200, model, loss_fn, opt, data_loader)
But the model doesn't learn anything, I don't know what I can do anymore.
The input/output dimensions is (1/1)
Dataset
First of all, you should define torch.utils.data.Dataset
import torch
from sklearn.datasets import make_regression
class RegressionDataset(torch.utils.data.Dataset):
def __init__(self):
data = make_regression(n_samples=100, n_features=1, noise=0.1, random_state=42)
self.x = torch.from_numpy(data[0]).float()
self.y = torch.from_numpy(data[1]).float()
def __len__(self):
return len(self.x)
def __getitem__(self, index):
return self.x[index], self.y[index]
It converts numpy data to PyTorch's tensor inside __init__ and converts data to float (numpy has double by default while PyTorch's default is float in order to use less memory).
Apart from that it will simply return tuple of features and respective regression targets.
Fit
Almost there, but you have to flatten output from the model (described below). torch.nn.Linear will return tensors of shape (batch, 1) while your targets are of shape (batch,). flatten() will remove unnecessary 1 dimension.
# 2. Calculate Loss
loss = criterion(pred.flatten(), yb)
Model
That is all you need actually:
model = torch.nn.Linear(1, 1)
Any layer can be called directly, no need for forward and inheritance for simple models.
Calling
The rest is almost okay, you just have to create torch.utils.data.DataLoader and pass instance of our dataset. What DataLoader does is it issues __getitem__ of dataset multiple times and creates a batch of specified size (there is some other funny business, but that's the idea):
dataset = RegressionDataset()
dataloader = torch.utils.data.DataLoader(dataset, batch_size=32)
model = torch.nn.Linear(1, 1)
criterion = torch.nn.MSELoss()
optimizer = torch.optim.SGD(model.parameters(), lr=3e-4)
fit(5000, model, criterion, optimizer, dataloader)
Also notice I've used torch.nn.MSELoss(), as we are passing object it looks better than function in this case.
Whole code
To make it easier:
import torch
from sklearn.datasets import make_regression
class RegressionDataset(torch.utils.data.Dataset):
def __init__(self):
data = make_regression(n_samples=100, n_features=1, noise=0.1, random_state=42)
self.x = torch.from_numpy(data[0]).float()
self.y = torch.from_numpy(data[1]).float()
def __len__(self):
return len(self.x)
def __getitem__(self, index):
return self.x[index], self.y[index]
# Funcao para treinar
def fit(num_epochs, model, criterion, optimizer, train_dl):
# Repeat for given number of epochs
for epoch in range(num_epochs):
# Train with batches of data
for xb, yb in train_dl:
# 1. Generate predictions
pred = model(xb)
# 2. Calculate Loss
loss = criterion(pred.flatten(), yb)
# 3. Compute gradients
loss.backward()
# 4. Update parameters using gradients
optimizer.step()
# 5. Reset the gradients to zero
optimizer.zero_grad()
# Print the progress
if (epoch + 1) % 10 == 0:
print(
"Epoch [{}/{}], Loss: {:.4f}".format(epoch + 1, num_epochs, loss.item())
)
dataset = RegressionDataset()
dataloader = torch.utils.data.DataLoader(dataset, batch_size=32)
model = torch.nn.Linear(1, 1)
criterion = torch.nn.MSELoss()
optimizer = torch.optim.SGD(model.parameters(), lr=3e-4)
fit(5000, model, criterion, optimizer, dataloader)
You should get around 0.053 loss or so, vary noise or other params for harder/easier regression task.
from dataset import get_strange_symbol_loader, get_strange_symbols_test_data
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
class Net(nn.Module):
def __init__(self):
super().__init__()
self.fc1 = nn.Linear(28*28, 512)
self.fc2 = nn.Linear(512, 256)
self.fc3 = nn.Linear(256, 15)
def forward(self,x):
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
x = self.fc3(x)
return F.softmax(x, dim=1)
if __name__ == '__main__':
net = Net()
train, test = get_strange_symbol_loader(batch_size=128)
loss_function = nn.CrossEntropyLoss()
optimizer = optim.Adam(net.parameters(), lr=1e-3)
Accuracy = []
for epoch in range(30):
print("epoch",epoch)
#Train
for data in train:
img, label = data
net.zero_grad()
output = net(img.view(-1,28*28))
loss = F.nll_loss(output, label)
loss.backward()
optimizer.step()
#Test
correct, total = 0, 0
with torch.no_grad():
for data in test:
img, label = data
output = net(img.view(-1,784))
for idx, i in enumerate(output):
if torch.argmax(i) == label[idx]:
correct += 1
total += 1
Accuracy.append(round(correct/total, 3))
print("Accuracy: ",Accuracy)
Here is my neural network made with PyTorch based on the one by Sentdex. I'm using a dataset given to me by my university course administrators imported by the function get_strange_symbol_loader(batch_size=128).
When I run this code it tells me that accuracy in every epoch is supposed to be 1.0. However, running the #Test block after the iteration of the for loop containing epoch gives somewhat more realistic results. Why does this happen?
My goal here is to plot testing accuracy against the number of epochs to find the optimal number of epochs for the model before it starts to overfit.
You are incrementing both correct and total in the block
if torch.argmax(i) == label[idx]:
correct += 1
total += 1
therefore both have always the same value and one divided by the other gives 1.0
Check your intends, I think removing a tab from total +=1 should do it.
EDIT: I assume that by "after running the #test block after..." you mean you run another snippet which might be different (is correctly intended perhaps)
I am trying to solve the very simple non-linear problem. It is XOR gate.
I my school knowledge. XOR can be solve by using 2 input nodes, 2 hidden layer nodes. And 1 output. It is binary classification problem.
I generate the 1000 of random integer number it is 0 or 1 and then do backpropagation. But for some unknown reason my network has not learned anything. The training accuracy is constant at 50.
# coding: utf-8
import matplotlib
import torch
import torch.nn as nn
from torch.autograd import Variable
matplotlib.use('TkAgg') # My buggy OSX 10.13.6 requires this
import matplotlib.pyplot as plt
from torch.utils.data import Dataset
from tqdm import tqdm
import random
N = 1000
batch_size = 10
epochs = 40
hidden_size = 2
output_size = 1
lr = 0.1
def return_xor(N):
tmp_x = []
tmp_y = []
for i in range(N):
a = (random.randint(0, 1) == 1)
b = (random.randint(0, 1) == 1)
if (a and not b) or (not a and b):
q = True
else:
q = False
input_features = (a, b)
output_class = q
tmp_x.append(input_features)
tmp_y.append(output_class)
return tmp_x, tmp_y
# In[495]:
# Training set
x, y = return_xor(N)
x = torch.tensor(x, dtype=torch.float, requires_grad=True)
y = torch.tensor(y, dtype=torch.float, requires_grad=True)
# Test dataset
x_test, y_test = return_xor(100)
x_test = torch.tensor(x_test)
y_test = torch.tensor(y_test)
class MyDataset(Dataset):
"""Define my own `Dataset` in order to use `Variable` with `autograd`"""
def __init__(self, x, y):
self.x = x
self.y = y
def __getitem__(self, index):
return self.x[index], self.y[index]
def __len__(self):
return len(self.x)
dataset = MyDataset(x, y)
test_dataset = MyDataset(x_test, y_test)
print(dataset.x.shape)
print(dataset.y.shape)
# Make data iterable by loading to a loader. Shuffle, batch_size kwargs put them here in order to remind I myself
train_loader = torch.utils.data.DataLoader(dataset=dataset, batch_size=batch_size, shuffle=True)
test_loader = torch.utils.data.DataLoader(dataset=test_dataset, batch_size=batch_size, shuffle=False)
print(f"They are {len(train_loader)} batches in the dataset")
shown = 0
for (x, y) in train_loader:
if shown == 1:
break
print(f"{x.shape} {x.dtype}")
print(f"{y.shape} {y.dtype}")
shown += 1
class MyModel(nn.Module):
"""
Binary classification
2 input nodes
2 hidden nodes
1 output node
"""
def __init__(self, input_size, hidden_size, output_size):
super().__init__()
self.fc1 = torch.nn.Linear(input_size, hidden_size)
self.fc2 = torch.nn.Linear(hidden_size, output_size)
self.sigmoid = torch.nn.Sigmoid()
def forward(self, out):
out = self.fc1(out)
out = self.fc2(out)
out = self.sigmoid(out)
return out
# Create my network
net = MyModel(dataset.x.shape[1], hidden_size, output_size)
CUDA = torch.cuda.is_available()
if CUDA:
net = net.cuda()
criterion = torch.nn.BCELoss(reduction='elementwise_mean')
optimizer = torch.optim.SGD(net.parameters(), lr=lr)
# Train the network
correct_train = 0
total_train = 0
for epoch in range(epochs):
for i, (batches, labels) in enumerate(train_loader):
batcesh = Variable(batches.float())
labels = Variable(labels.float())
output = net(batches) # Forward pass
optimizer.zero_grad()
loss = criterion(output, labels.view(10, 1))
loss.backward()
optimizer.step()
total_train += labels.size(0)
correct_train += (predicted == labels.long()).sum()
if (i + 1) % 10 == 0:
print(f"""
Epoch {epoch+1}/{epochs},
Iteration {i+1}/{len(dataset)//batch_size},
Training Loss: {loss.item()},
Training Accuracy: {100*correct_train/total_train}
""")
Solution:
I did initialized weight, Adaptive learning rate
https://github.com/elcolie/nnbootcamp/blob/master/Study-XOR.ipynb
I am not sure what results you are getting, as the code you have posted in the question doesn't work (It gives errors with pytorch 0.4.1 like predicted not defined etc). But syntax issues apart, there are other problems.
Your model is not actually two layer as it does not use non-linearity after the first output. Effectively this is one layer network and to fix that you can modify your model's forward as follows:
def forward(self, out):
out = torch.nn.functional.relu(self.fc1(out))
out = self.fc2(out)
out = self.sigmoid(out)
return out
You can try sigmoid or tanh non-linearity as well... but the non-linearity is a must. This should fix the problem.
I also see that you are using only 2 hidden units. This might be restrictive and you might want to increase that to something like 5 or 10.
I'm trying a basic averaging example, but the validation and loss don't match and the network fails to converge if I increase the training time. I'm training a network with 2 hidden layers, each 500 units wide on three integers from the range [0,9] with a learning rate of 1e-1, Adam, batch size of 1, and dropout for 3000 iterations and validate every 100 iterations. If the absolute difference between the label and the hypothesis is less than a threshold, here I set the threshold to 1, I consider that correct. Could someone let me know if this is an issue with the choice of loss function, something wrong with Pytorch, or something I'm doing. Below are some plots:
val_diff = 1
acc_diff = torch.FloatTensor([val_diff]).expand(self.batch_size)
Loop 100 times to during validation:
num_correct += torch.sum(torch.abs(val_h - val_y) < acc_diff)
Append after each validation phase:
validate.append(num_correct / total_val)
Here are some examples of the (hypothesis, and labels):
[...(-0.7043088674545288, 6.0), (-0.15691305696964264, 2.6666667461395264),
(0.2827358841896057, 3.3333332538604736)]
I tried six of the loss functions in the API that are typically used for regression:
torch.nn.L1Loss(size_average=False)
torch.nn.L1Loss()
torch.nn.MSELoss(size_average=False)
torch.nn.MSELoss()
torch.nn.SmoothL1Loss(size_average=False)
torch.nn.SmoothL1Loss()
Thanks.
Network code:
class Feedforward(nn.Module):
def __init__(self, topology):
super(Feedforward, self).__init__()
self.input_dim = topology['features']
self.num_hidden = topology['hidden_layers']
self.hidden_dim = topology['hidden_dim']
self.output_dim = topology['output_dim']
self.input_layer = nn.Linear(self.input_dim, self.hidden_dim)
self.hidden_layer = nn.Linear(self.hidden_dim, self.hidden_dim)
self.output_layer = nn.Linear(self.hidden_dim, self.output_dim)
self.dropout_layer = nn.Dropout(p=0.2)
def forward(self, x):
batch_size = x.size()[0]
feat_size = x.size()[1]
input_size = batch_size * feat_size
self.input_layer = nn.Linear(input_size, self.hidden_dim).cuda()
hidden = self.input_layer(x.view(1, input_size)).clamp(min=0)
for _ in range(self.num_hidden):
hidden = self.dropout_layer(F.relu(self.hidden_layer(hidden)))
output_size = batch_size * self.output_dim
self.output_layer = nn.Linear(self.hidden_dim, output_size).cuda()
return self.output_layer(hidden).view(output_size)
Training code:
def train(self):
if self.cuda:
self.network.cuda()
dh = DataHandler(self.data)
# loss_fn = nn.L1Loss(size_average=False)
# loss_fn = nn.L1Loss()
# loss_fn = nn.SmoothL1Loss(size_average=False)
# loss_fn = nn.SmoothL1Loss()
# loss_fn = nn.MSELoss(size_average=False)
loss_fn = torch.nn.MSELoss()
losses = []
validate = []
hypos = []
labels = []
val_size = 100
val_diff = 1
total_val = float(val_size * self.batch_size)
for i in range(self.iterations):
x, y = dh.get_batch(self.batch_size)
x = self.tensor_to_Variable(x)
y = self.tensor_to_Variable(y)
self.optimizer.zero_grad()
loss = loss_fn(self.network(x), y)
loss.backward()
self.optimizer.step()
It looks like you've misunderstood how layers in pytorch works, here are a few tips:
In your forward when you do nn.Linear(...) you are definining new layers instead of using those you pre-defined in your network __init__. Therefore, it cannot learn anything as weights are constantly reinitalized.
You shouldn't need to call .cuda() inside net.forward(...) since you've already copied the network on gpu in your train by calling self.network.cuda()
Ideally the net.forward(...) input should directly have the shape of the first layer so you won't have to modify it. Here you should have x.size() <=> Linear -- > (Batch_size, Features).
Your forward should look close to this:
def forward(self, x):
x = F.relu(self.input_layer(x))
x = F.dropout(F.relu(self.hidden_layer(x)),training=self.training)
x = self.output_layer(x)
return x