Pytorch:Network not learning at all + Weights are too low - deep-learning

Question

About the input. Sorry for the bad formatting. The for each two rows first row is the key and second row is the value. 18~20_ride is the label and is not included in the input. Below is one input. And train set consists of 400000 of these.
bus_route_id station_code latitude longitude 6~7_ride
0 4270000 344 33.48990 126.49373
7~8_ride 8~9_ride 9~10_ride 10~11_ride 11~12_ride 6~7_takeoff
0.0 1.0 2.0 5.0 2.0 6.0
7~8_takeoff 8~9_takeoff 9~10_takeoff 10~11_takeoff 11~12_takeoff
0.0 0.0 0.0 0.0 0.0
18~20_ride weekday dis_jejusi dis_seoquipo
0.0 6 2.954920 26.256744
Example weights: Captured at 4th epoch. After 20 epochs of training I got much smaller values (ex. -7e-44 or 1e-55)
2.3937e-11, -2.6920e-12, -1.0445e-11, ..., -1.0754e-11, 1.1128e-11, -1.4814e-11
The model's prediction and target
#Target
[2.],
[0.],
[0.]
#Prediction
[1.4187],
[1.4187],
[1.4187]
MyDataset.py
from torch.utils.data import Dataset, DataLoader
import numpy as np
import pandas as pd
import torch
import os
class MyDataset(Dataset):
def __init__(self, csv_filename):
self.dataset = pd.read_csv(csv_filename, index_col=0)
self.labels = self.dataset.pop("18~20_ride")
self.dataset = self.dataset.values
self.labels = np.reshape(self.labels.values,(-1,1))
def __len__(self):
return len(self.dataset)
def __getitem__(self, idx):
return self.dataset[idx], self.labels[idx]
Model
class Network(nn.Module):
def __init__(self, input_num):
super(Network, self).__init__()
self.fc1 = nn.Sequential(
nn.Linear(input_num, 64),
nn.BatchNorm1d(64),
GELU()
)
self.fc2 = nn.Sequential(
nn.Linear(64, 64),
nn.BatchNorm1d(64),
GELU()
)
self.fc3 = nn.Sequential(
nn.Linear(64, 64),
nn.BatchNorm1d(64),
GELU()
)
self.fc4 = nn.Sequential(
nn.Linear(64, 64),
nn.BatchNorm1d(64),
GELU()
)
self.fc5 = nn.Sequential(
nn.Linear(64, 64),
nn.BatchNorm1d(64),
GELU()
)
self.fc6 = nn.Sequential(
nn.Linear(64, 64),
nn.BatchNorm1d(64),
GELU)
)
self.fc7 = nn.Sequential(
nn.Linear(64, 64),
nn.BatchNorm1d(64),
GELU()
)
self.fc8 = nn.Sequential(
nn.Linear(64, 64),
nn.BatchNorm1d(64),
GELU())
)
self.fc9 = nn.Linear(64, 1)
The training and validation
def train(model, device, train_loader, optimizer, loss_fn, log_interval, epoch):
print("Training")
model.train()
for batch_idx, (data, target) in enumerate(train_loader):
data, target = data.float().to(device), target.float().to(device)
optimizer.zero_grad()
output = model(data)
loss = loss_fn(output, target)
loss.backward()
optimizer.step()
if batch_idx % log_interval == 0:
print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
epoch, (batch_idx+1) * len(data), len(train_loader.dataset),
100. * batch_idx / len(train_loader), loss.item()))
def validate(model, device, loader, loss_fn):
print("\nValidating")
model.eval()
test_loss = 0
correct = 0
with torch.no_grad():
for batch_idx, (data, target) in enumerate(loader):
data, target = data.float().to(device), target.float().to(device)
output = model(data)
test_loss += loss_fn(output, target).item() # sum up batch loss
test_loss /= len(loader)
print('Validation average loss: {:.4f}\n'.format(
test_loss))
return test_loss
Entire process of training and validation
from MyDataset import MyDataset
from torch.utils.data import DataLoader
from torch.optim.lr_scheduler import StepLR
from datetime import datetime
train_dataset_path = "/content/drive/My Drive/root/bus/dataset/train.csv"
val_dataset_path = "/content/drive/My Drive/root/bus/dataset/val.csv"
model_base_path = "/content/drive/My Drive/root/bus/models/"
model_file = "/content/drive/My Drive/root/bus/models/checkpoints/1574427776.202017.pt"
"""
Training Config
"""
epochs = 10
batch_size = 32
learning_rate = 0.5
check_interval = 4
log_interval = int(40000/batch_size)
gamma = 0.1
load_model = False
save_model = True
make_checkpoint = True
"""
End of config
"""
# Read test set
train_set = MyDataset(train_dataset_path)
train_loader = DataLoader(train_set, batch_size=batch_size, shuffle=True)
val_set = MyDataset(val_dataset_path)
val_loader = DataLoader(val_set, batch_size=1)
print("Data READY")
device = torch.device("cuda")
net = Network(19).float().to(device)
if load_model:
net.load_state_dict(torch.load(model_file))
loss_fn = torch.nn.MSELoss()
optimizer = optim.AdamW(net.parameters(), lr=learning_rate)
best_loss = float('inf')
isAbort = False
for epoch in range(1, epochs+1):
train(net, device, train_loader, optimizer, loss_fn, log_interval, epoch)
val_loss = validate(net, device, val_loader, loss_fn)
if epoch%check_interval==0:
if make_checkpoint:
print("Saving new checkpoint")
torch.save(net.state_dict(), model_base_path+"checkpoints/"+str(datetime.today().timestamp())+".pt")
"""
if val_loss < best_loss and epoch%check_interval==0:
best_loss = val_loss
if make_checkpoint:
print("Saving new checkpoint")
torch.save(net.state_dict(), model_base_path+"checkpoints/"+str(datetime.today().timestamp())+".pt")
else:
print("Model overfit detected. Aborting training")
isAbort = True
break
"""
if save_model and not isAbort:
torch.save(net.state_dict(), model_base_path+"finals/"+str(datetime.today().timestamp())+".pt")
So I tried to train a fully connected model for a regression problem, with google colab. But it did not get trained well; The loss absolutely did not decrease. So I dug down and found out that the weights were really small. Any idea why this is happening and how I could avoid this? Thank you
I used MSE for loss and used ADaW optimizer. Below are the things I have tried
Tried other architectures (Changing number of layers sizes, Changed activation function ReLU, GELU)but the loss did not decrease
Tried changing the learning rate from 3e-1~1e-3, even tried 1
Tried other pre-processing(Used day/month/year instead of weekday) for the data
Given the label in the input data but loss did not decrease
Tried different batch_sizes(4, 10, 32, 64)
Removed batch_normalization
Other kinds of optimizer such as SGD, Adam
Training 20 epochs but loss did not decrease at all
The weights do change at loss.backward()

Answer 1

TL;DR: Invalid input data!! Check for NaN or NULL
Well it has been sometime since the question. Tried almost everything and though maybe messed up the project setup. So I deleted the project and tried it again: same. Delete again and migrate to TF2: THE SAME RESULT! So I found out that there wasn't any problem with the setup. So I searched other places. In the end I did find the reason. The input columns were actually modified by myself. (To remove some highly correlated features). It was not original. During the modification I messed up some float values and it ended up having NaN values. So check if you're dataset contains invalid values.