Related
I am currently building an LSTM model in Pytorch to predict the next word of a given input.
My model:
class LSTM(nn.Module):
def __init__(self, vocab_size, embedding_dim, hidden_dim, num_layers, dropout_rate, tie_weights):
super().__init__()
self.num_layers = num_layers
self.hidden_dim = hidden_dim
self.embedding_dim = embedding_dim
self.embedding = nn.Embedding(vocab_size, embedding_dim)
self.lstm = nn.LSTM(embedding_dim, hidden_dim, num_layers=num_layers,
dropout=dropout_rate, batch_first=True)
self.dropout = nn.Dropout(dropout_rate)
self.linear = nn.Linear(hidden_dim, vocab_size)
if tie_weights:
#Embedding and hidden layer need to be same size for weight tieing
assert embedding_dim == hidden_dim, 'cannot tie, check dims'
self.linear.weight = self.embedding.weight
self.init_weights()
def forward(self, x):
# x is a batch of input sequences
x = self.embedding(x)
x, _ = self.lstm(x)
x = self.linear(x)
return x
def init_weights(self):
init_range_emb = 0.1
init_range_other = 1/math.sqrt(self.hidden_dim)
self.embedding.weight.data.uniform_(-init_range_emb, init_range_emb)
self.linear.weight.data.uniform_(-init_range_other, init_range_other)
self.linear.bias.data.zero_()
for i in range(self.num_layers):
self.lstm.all_weights[i][0] = torch.FloatTensor(self.embedding_dim,
self.hidden_dim).uniform_(-init_range_other, init_range_other)
self.lstm.all_weights[i][1] = torch.FloatTensor(self.hidden_dim,
self.hidden_dim).uniform_(-init_range_other, init_range_other)
vocab_size = len(vocab)
embedding_dim = 100
hidden_dim = 100
num_layers = 2
dropout_rate = 0.4
tie_weights = True
model = LSTM(vocab_size, embedding_dim, hidden_dim, num_layers, dropout_rate, tie_weights)
model.to(device)
Training and evaluation funciton:
import copy
import time
criterion = nn.CrossEntropyLoss()
lr = 20.0 # learning rate
optimizer = torch.optim.SGD(model.parameters(), lr=lr)
scheduler = torch.optim.lr_scheduler.StepLR(optimizer, 1.0, gamma=0.95)
def train(model: nn.Module) -> None:
model.train() # turn on train mode
total_loss = 0.
log_interval = 200
start_time = time.time()
num_batches = len(train_data) // bptt
for batch, i in enumerate(range(0, train_data.size(0) - 1, bptt)):
data, targets = get_batch(train_data, i)
seq_len = data.size(0)
output = model(data)
loss = criterion(output.view(-1, vocab_size), targets)
optimizer.zero_grad()
loss.backward()
torch.nn.utils.clip_grad_norm_(model.parameters(), 0.5)
optimizer.step()
total_loss += loss.item()
if batch % log_interval == 0 and batch > 0:
lr = scheduler.get_last_lr()[0]
ms_per_batch = (time.time() - start_time) * 1000 / log_interval
cur_loss = total_loss / log_interval
ppl = math.exp(cur_loss)
print(f'| epoch {epoch:3d} | {batch:5d}/{num_batches:5d} batches | '
f'lr {lr:02.2f} | ms/batch {ms_per_batch:5.2f} | '
f'loss {cur_loss:5.2f} | ppl {ppl:8.2f}')
total_loss = 0
start_time = time.time()
def evaluate(model: nn.Module, eval_data: Tensor) -> float:
model.eval() # turn on evaluation mode
total_loss = 0.
with torch.no_grad():
for i in range(0, eval_data.size(0) - 1, bptt):
data, targets = get_batch(eval_data, i)
seq_len = data.size(0)
output = model(data)
output_flat = output.view(-1, vocab_size)
total_loss += seq_len * criterion(output_flat, targets).item()
return total_loss / (len(eval_data) - 1)
Training loop
best_val_loss = float('inf')
epochs = 50
best_model = None
for epoch in range(1, epochs + 1):
epoch_start_time = time.time()
train(model)
val_loss = evaluate(model, val_data)
val_ppl = math.exp(val_loss)
elapsed = time.time() - epoch_start_time
print('-' * 89)
print(f'| end of epoch {epoch:3d} | time: {elapsed:5.2f}s | '
f'valid loss {val_loss:5.2f} | valid ppl {val_ppl:8.2f}')
print('-' * 89)
if val_loss < best_val_loss:
best_val_loss = val_loss
best_model = copy.deepcopy(model)
scheduler.step()
My problem is I have no idea how to go about this. I've seen some implementations of character based LSTM text generators but I'm looking for it to be word based. For example I want to pass an input like "How are you" and the output will included the next predicted word, like for example "How are you today"
Any help appreciated.
I would suggest to try the example in the attached link(https://www.kaggle.com/code/ysthehurricane/next-word-prediction-bi-lstm-tutorial-easy-way).
You can download the dataset from the attached link below.
(https://www.kaggle.com/datasets/dorianlazar/medium-articles-dataset)
It tries to predict the next word using Bi-directional LSTM architecture. I think that this example mostly suits to your needs, which will give you an idea to proceed further.
You can follow the instruction provided in the first link.
I'm trying to reconstruct this paper about hierarchical autoencoder for paragraphs.
The idea is: Break a paragraph into sentences, then encode each sentence using an LSTM, and then using these encoding as an input for another LSTM that encode the entire paragraph.
Then, using a mirror decoder, decode the encoded paragraph using an LSTM into multiple sentences, and then use another LSTM to decode each word, with a linear layer on top and predicts the word.
The objective is to try to predict the original paragraph.
I've done some preprocessing, and right now I save each paragraph as a tensor of (maxSentence,maxWordsPerSentence,VocabSize), using one hot encoding.
My problem is, there model is not learning. The loss stays exactly the same and it doesn't seem as anything is happening.. I wasn't sure on how to calculate the loss (I've ran a batch all together and decoded it into multiple paragraphs, and then calculated the loss against the entire batch predictions, my train function is added below. I don't know if that is the problem (maybe I should calculate loss sentence by sentence instead the entire paragraph?) or maybe I have a problem in my model.
Encoder code:
class Encoder(nn.Module):
def __init__(self, input_dim, emb_dim, enc_hid_dim, dec_hid_dim, dropout):
super().__init__()
#self.embedding = nn.Embedding(input_dim, emb_dim)
self.rnn_sent = nn.GRU(input_dim, enc_hid_dim, bidirectional = True)
self.rnn_par = nn.GRU(enc_hid_dim*2, dec_hid_dim, bidirectional = True)
def forward(self, src):
outputs, hidden = self.rnn_sent(src[:,0,0])
total_out = outputs.unsqueeze(0).permute(1,0,2)
for i in range(1,src.shape[1]):
for j in range(src.shape[2]):
outputs, hidden = self.rnn_sent(src[:,i,j],hidden)
total_out = torch.cat((total_out,outputs.unsqueeze(0).permute(1,0,2)),dim=1)
outputs_par, hidden_par = self.rnn_par(total_out[:,0])
for i in range(total_out.shape[1]):
outputs_par, hidden_par = self.rnn_par(total_out[:,i],hidden_par)
return outputs_par, hidden_par
Decoder code:
class Decoder(nn.Module):
def __init__(self, output_dim, emb_dim, enc_hid_dim, dec_hid_dim, dropout, attention):
super().__init__()
self.output_dim = output_dim
self.attention = attention
#self.embedding = nn.Embedding(output_dim, emb_dim)
self.rnn_par = nn.GRU((enc_hid_dim * 2), dec_hid_dim*2)
self.rnn_sen = nn.GRU(output_dim, dec_hid_dim*2)
self.fc_out = nn.Linear(dec_hid_dim*2, output_dim)
self.dropout = nn.Dropout(dropout)
def forward(self, input, hidden, encoder_outputs):
output, hidden = self.rnn_par(encoder_outputs)
all_par = output.unsqueeze(0).permute(1,0,2)
for i in range(1,max_par_len):
output,hidden = self.rnn_par(output,hidden)
all_par = torch.cat((all_par,output.unsqueeze(0).permute(1,0,2)),dim=1)
for i in range(max_par_len):
output_arg = self.fc_out(all_par[:,i])
#output_argmax = F.one_hot(output_arg.argmax(dim = 1), self.output_dim).to(torch.float)
output_argmax = torch.softmax(output_arg,dim=1)
output_sen, hidden_sen = self.rnn_sen(output_argmax)
all_par_sen = output_argmax.unsqueeze(0).permute(1,0,2)
for j in range(max_sen_len - 1):
output_sen,hidden_sen = self.rnn_sen(output_argmax,hidden_sen)
output_arg = self.fc_out(output_sen)
output_argmax = torch.softmax(output_arg,dim=1)
all_par_sen = torch.cat((all_par_sen,output_argmax.unsqueeze(0).permute(1,0,2)),dim=1)
if i == 0:
all_doc = all_par_sen.unsqueeze(0).permute(1,0,2,3)
else:
all_doc = torch.cat((all_doc,all_par_sen.unsqueeze(0).permute(1,0,2,3)),dim=1)
i+=1
return all_doc ,hidden_sen
And my train function:
def train(model, iterator, optimizer, criterion, clip, epoch):
model.train()
epoch_loss = 0
data = tqdm(iterator)
for i, batch in enumerate(data):
src = batch[0].to(device)#.to(torch.long)#.reshape(batch[0].shape[0],-1)
trg = batch[0].to(device)#.to(torch.long)#.reshape(batch[0].shape[0],-1)
target = torch.argmax(trg,dim=3).view(-1)
print(target)
optimizer.zero_grad()
output = model(src, trg).view(-1,OUTPUT_DIM)
loss = criterion(output, target)
loss.backward()
torch.nn.utils.clip_grad_norm_(model.parameters(), clip)
optimizer.step()
epoch_loss += loss.item()
N_EPOCHS = 20
CLIP = 1
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)
criterion = nn.CrossEntropyLoss(ignore_index = vocabulary['<pad>'])
best_valid_loss = float('inf')
for epoch in range(N_EPOCHS):
start_time = time.time()
train_loader, valid_loader = data_loaders['train_loader'], data_loaders['test_loader']
train_loss = train(model, train_loader, optimizer, criterion, CLIP,f'{epoch+1}/{N_EPOCHS}')
#valid_loss = evaluate(model, valid_loader, criterion)
end_time = time.time()
epoch_mins, epoch_secs = epoch_time(start_time, end_time)
print(f'Epoch: {epoch+1:02} | Time: {epoch_mins}m {epoch_secs}s')
print(f'\tTrain Loss: {train_loss:.3f} | Train PPL: {math.exp(train_loss):7.3f}')
I've built a CNN using Pytorch and am attempting to train it to classify dog and cat images from this Kaggle dataset.
The training loss starts at ~9 after the first epoch and then gets stuck at ~0.69 from the second epoch onwards. The testing loss and the accuracy are stack at ~0.69 and ~50% throughout the training.
At the moment my parameters are as follows:
batch_size = 128
num_epochs = 10
learning_rate = 0.1
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adamax(model.parameters(), lr=learning_rate)
I've tried changing the batch size, the optimizer and the learning rate. I've attached my code for creating the dataset and the CNN, and the training loop below.
Definition of dataset class and transforms for augmentations
class CatDogDataset(Dataset):
def __init__(self, images_list, mode="train", transform=None):
self.images_list = images_list
self.mode = mode
self.transform = transform
# dataset length
def __len__(self):
self.dataset_len = len(self.images_list)
return self.dataset_len
# load an image
def __getitem__(self, idx):
image_name = self.images_list[idx]
image = Image.open(image_name)
image = image.resize((224,224)) # this is important when feeding into a pretrained model
transformed_image = self.transform(image)
image_category = image_name.split("/")[-1].split(".")[0]
if self.mode == "train" or self.mode == "val":
if image_category == "cat":
label = 0
else:
label = 1
return transformed_image, label
else:
return transformed_image
train_transforms = transforms.Compose([
transforms.RandomHorizontalFlip(p=0.5),
transforms.RandomRotation(15),
transforms.RandomResizedCrop(224, scale=(0.8,1.0),ratio=(1.0,1.0)),
transforms.ToTensor(),
transforms.Normalize((0, 0, 0),(1, 1, 1))
])
val_transforms = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0, 0, 0),(1, 1, 1))
])
CNN class definition
class CNN(nn.Module):
def __init__(self):
super().__init__()
self.cnn_layers = nn.Sequential(
# convolutional layer 1
nn.Conv2d(in_channels=3, out_channels=16, kernel_size=5, padding=0, stride=1),
nn.BatchNorm2d(16),
nn.ReLU(),
nn.MaxPool2d(kernel_size=2),
# convolutional layer 2
nn.Conv2d(in_channels=16, out_channels=32, kernel_size=5, padding=0, stride=1),
nn.BatchNorm2d(32),
nn.ReLU(),
nn.MaxPool2d(kernel_size=2),
# convolutional layer 3
nn.Conv2d(in_channels=32, out_channels=64, kernel_size=5, padding=0, stride=1),
nn.BatchNorm2d(64),
nn.ReLU(),
nn.MaxPool2d(kernel_size=2)
)
self.linear_layers = nn.Sequential(
nn.Linear(in_features=64 * 24 * 24, out_features=10),
nn.ReLU(),
nn.Dropout(0.3),
nn.Linear(in_features=10, out_features=2)
)
def forward(self, x):
out = self.cnn_layers(x)
#print(out.shape)
out = out.view(-1, 64 * 24 * 24) # flatten
out = self.linear_layers(out)
return out
Model training and validation
from tqdm import tqdm
train_losses = []
val_losses = []
accuracy_list = []
for epoch in range(num_epochs):
# perform training on train set
model.train()
running_loss = 0
for images, labels in tqdm(train_dataloader):
# load to gpu
images = images.to(device)
labels = labels.to(device)
# forward pass
outputs = model(images)
loss = criterion(outputs, labels)
running_loss += loss.item()
# backprop and update model params
optimizer.zero_grad()
loss.backward()
optimizer.step()
# calculate training loss for the epoch
train_losses.append(running_loss / len(train_dataloader))
# calculate loss accuracy on validation set
model.eval()
running_loss = 0
num_correct = 0
num_predictions = 0
with torch.no_grad():
for images, labels in tqdm(val_dataloader):
# load to gpu
images = images.to(device)
labels = labels.to(device)
# forward pass
outputs = model(images)
loss = criterion(outputs, labels)
running_loss += loss.item()
# calculate accuracy for batch
_, predicted = torch.max(outputs.data, 1)
num_correct += (predicted == labels).sum().item()
num_predictions += labels.size(0)
# calculate val loss for epoch
val_losses.append(running_loss / len(val_dataloader))
# calculate accuracy for epoch
accuracy = num_correct / num_predictions * 100
accuracy_list.append(accuracy)
print("[Epoch: %d / %d], [Train loss: %.4f], [Test loss: %.4f], [Acc: %.2f]" \
%(epoch+1, num_epochs, train_losses[-1], val_losses[-1], accuracy))
I'm new to Neural Networks and I'm trying to train a CNN model on a custom dataset (cats and dogs images in a single directory). So I guess I do the very usual stuff here which is in the most tutorials, but just in case I will give here my full code.
First I generate .csv file to be processed:
import os
import torch
device = ("cuda" if torch.cuda.is_available() else "cpu")
train_df = pd.DataFrame(columns=["img_name","label"])
train_df["img_name"] = os.listdir("train/")
for idx, i in enumerate(os.listdir("train/")):
if "cat" in i:
train_df["label"][idx] = 0
if "dog" in i:
train_df["label"][idx] = 1
train_df.to_csv (r'train_csv.csv', index = False, header=True)
Then I prepare the dataset:
from torch.utils.data import Dataset
import pandas as pd
import os
from PIL import Image
import torch
class CatsAndDogsDataset(Dataset):
def __init__(self, root_dir, annotation_file, transform=None):
self.root_dir = root_dir
self.annotations = pd.read_csv(annotation_file)
self.transform = transform
def __len__(self):
return len(self.annotations)
def __getitem__(self, index):
img_id = self.annotations.iloc[index, 0]
img = Image.open(os.path.join(self.root_dir, img_id)).convert("RGB")
y_label = torch.tensor(float(self.annotations.iloc[index, 1]))
if self.transform is not None:
img = self.transform(img)
return (img, y_label)
This is my model:
import torch.nn as nn
import torchvision.models as models
class CNN(nn.Module):
def __init__(self, train_CNN=False, num_classes=1):
super(CNN, self).__init__()
self.train_CNN = train_CNN
self.inception = models.inception_v3(pretrained=True, aux_logits=False)
self.inception.fc = nn.Linear(self.inception.fc.in_features, num_classes)
self.relu = nn.ReLU()
self.dropout = nn.Dropout(0.5)
self.sigmoid = nn.Sigmoid()
def forward(self, images):
features = self.inception(images)
return self.sigmoid(self.dropout(self.relu(features))).squeeze(1)
This is my hyper-params, transformations and dataloaders:
from torch.utils.data import DataLoader
import torchvision.transforms as transforms
num_epochs = 10
learning_rate = 0.00001
train_CNN = False
batch_size = 32
shuffle = True
pin_memory = True
num_workers = 0
transform = transforms.Compose(
[
transforms.Resize((356, 356)),
transforms.RandomCrop((299, 299)),
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5)),
]
)
dataset = CatsAndDogsDataset("train","train_csv.csv",transform=transform)
print(len(dataset))
train_set, validation_set = torch.utils.data.random_split(dataset,[162,40])
train_loader = DataLoader(dataset=train_set, shuffle=shuffle, batch_size=batch_size,num_workers=num_workers,pin_memory=pin_memory)
validation_loader = DataLoader(dataset=validation_set, shuffle=shuffle, batch_size=batch_size,num_workers=num_workers, pin_memory=pin_memory)
model = CNN().to(device)
criterion = nn.BCELoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
for name, param in model.inception.named_parameters():
if "fc.weight" in name or "fc.bias" in name:
param.requires_grad = True
else:
param.requires_grad = train_CNN
and accuracy check:
def check_accuracy(loader, model):
if loader == train_loader:
print("Checking accuracy on training data")
else:
print("Checking accuracy on validation data")
num_correct = 0
num_samples = 0
model.eval()
with torch.no_grad():
for x, y in loader:
x = x.to(device=device)
y = y.to(device=device)
scores = model(x)
predictions = torch.tensor([1.0 if i >= 0.5 else 0.0 for i in scores]).to(device)
num_correct += (predictions == y).sum()
num_samples += predictions.size(0)
print(
f"Got {num_correct} / {num_samples} with accuracy {float(num_correct)/float(num_samples)*100:.2f}"
)
model.train()
return f"{float(num_correct)/float(num_samples)*100:.2f}"
And this is my training function:
from tqdm import tqdm
def train():
model.train()
for epoch in range(num_epochs):
loop = tqdm(train_loader, total = len(train_loader), leave = True)
if epoch % 2 == 0:
loop.set_postfix(val_acc = check_accuracy(validation_loader, model))
for imgs, labels in loop:
imgs = imgs.to(device)
labels = labels.to(device)
outputs = model(imgs)
loss = criterion(outputs, labels)
optimizer.zero_grad()
loss.backward()
optimizer.step()
loop.set_description(f"Epoch [{epoch}/{num_epochs}]")
loop.set_postfix(loss = loss.item())
if __name__ == "__main__":
train()
0%| | 0/6 [00:00<?, ?it/s]Checking accuracy on validation data
0%| | 0/6 [01:13<?, ?it/s, val_acc=60.00]Got 24 / 40 with accuracy 60.00
Epoch [0/10]: 100%|██████████| 6/6 [06:02<00:00, 60.39s/it, loss=0.693]
Epoch [1/10]: 100%|██████████| 6/6 [04:49<00:00, 48.23s/it, loss=0.693]
...
Epoch [8/10]: 100%|██████████| 6/6 [06:07<00:00, 61.29s/it, loss=0.693]
Epoch [9/10]: 100%|██████████| 6/6 [04:55<00:00, 49.19s/it, loss=0.781]
The model gets trained fine but when I try to use it for prediction I get different results each time I run this last piece in my Jupyter Notebooks:
model.eval()
img = Image.open('train/cat.22.png').convert("RGB")
img_t = transform(img)
batch_t = torch.unsqueeze(img_t, 0)
out = model(batch_t)
print(out)
tensor([0.5276], grad_fn=)
tensor([0.5000], grad_fn=)
tensor([0.5064], grad_fn=)
etc. Each time different result for the same image. Is this normal? Why this is happening?
I don't see you loading your trained model. This means every time you initialize the CNN module, the inception.fc layer will get initialized with random weights, this is most probably the reason why you are getting different results on each inference.
Edit: You have a random transform in your transformation pipeline, namely RandomCrop.
According to this answer on the use of model.eval(), I believe you might want to ensure that you have the lower half of the code cell wrapped in a with torch.no_grad(): context. I think it may still be learning/updating parameters unless inside that context.
I'm simply trying to train a ResNet18 model using PyTorch library. The training dataset consists of 25,000 images. Therefore, it is taking a lot of time for even the first epoch to complete. Therefore, I want to save the progress after a certain no. of batch iteration is completed. But I can't figure out how to modify my code and how to use the torch.save() and torch.load() functions in my code to save the periodic progress.
My code is given below:
# BUILD THE NETWORK
import torch
import torch.nn as nn
import torch.optim as optim
import torch.utils.data
import torch.nn.functional as F
import torchvision
import torchvision.models as models
from torchvision import transforms
from PIL import Image
import matplotlib.pyplot as plt
# DOWNLOAD PRETRAINED MODELS ON ImageNet
model_resnet18 = torch.hub.load('pytorch/vision', 'resnet18', pretrained = True)
model_resnet34 = torch.hub.load('pytorch/vision', 'resnet34', pretrained = True)
for name, param in model_resnet18.named_parameters():
if('bn' not in name):
param.requires_grad = False
for name, param in model_resnet34.named_parameters():
if('bn' not in name):
param.requires_grad = False
num_classes = 2
model_resnet18.fc = nn.Sequential(nn.Linear(model_resnet18.fc.in_features, 512),
nn.ReLU(),
nn.Dropout(),
nn.Linear(512, num_classes))
model_resnet34.fc = nn.Sequential(nn.Linear(model_resnet34.fc.in_features, 512),
nn.ReLU(),
nn.Dropout(),
nn.Linear(512, num_classes))
# FUNCTIONS FOR TRAINING AND LOADING DATA
def train(model, optimizer, loss_fn, train_loader, val_loader, epochs = 5, device = "cuda"):
print("Inside Train Function\n")
for epoch in range(epochs):
print("Epoch : {} running".format(epoch))
training_loss = 0.0
valid_loss = 0.0
model.train()
k = 0
for batch in train_loader:
optimizer.zero_grad()
inputs, targets = batch
inputs = inputs.to(device)
output = model(inputs)
loss = loss_fn(output, targets)
loss.backward()
optimizer.step()
training_loss += loss.data.item() * inputs.size(0)
print("End of batch loop iteration {} \n".format(k))
k = k + 1
training_loss /= len(train_loader.dataset)
model.eval()
num_correct = 0
num_examples = 0
for batch in val_loader:
inputs, targets = batch
inputs.to(device)
output = model(inputs)
targets = targets.to(device)
loss = loss_fn(output, targets)
valid_loss += loss.data.item() * inputs.size(0)
correct = torch.eq(torch.max(F.softmax(output, dim = 1), dim = 1)[1], targets).view(-1)
num_correct += torch.sum(correct).item()
num_examples += correct.shape[0]
valid_loss /= len(val_loader.dataset)
print('Epoch: {}, Training Loss: {:.4f}, Validation Loss: {:.4f}, accuracy = {:.4f}'.format(epoch, training_loss, valid_loss, num_correct / num_examples))
batch_size = 32
img_dimensions = 224
img_transforms = transforms.Compose([ transforms.Resize((img_dimensions, img_dimensions)),
transforms.ToTensor(),
transforms.Normalize(mean = [0.485, 0.456, 0.406], std = [0.229, 0.224, 0.225])
])
img_test_transforms = transforms.Compose([ transforms.Resize((img_dimensions, img_dimensions)),
transforms.ToTensor(),
transforms.Normalize(mean = [0.485, 0.456, 0.406], std = [0.229, 0.224, 0.225])
])
def check_image(path):
try:
im = Image.open(path)
return True
except:
return False
train_data_path = "E:\Image Recognition\dogsandcats\\train\\"
train_data = torchvision.datasets.ImageFolder(root=train_data_path,transform=img_transforms, is_valid_file=check_image)
validation_data_path = "E:\\Image Recognition\\dogsandcats\\validation\\"
validation_data = torchvision.datasets.ImageFolder(root=validation_data_path,transform=img_test_transforms, is_valid_file=check_image)
test_data_path = "E:\\Image Recognition\\dogsandcats\\test\\"
test_data = torchvision.datasets.ImageFolder(root=test_data_path,transform=img_test_transforms, is_valid_file=check_image)
num_workers = 6
train_data_loader = torch.utils.data.DataLoader(train_data, batch_size=batch_size, shuffle=True, num_workers=num_workers)
validation_data_loader = torch.utils.data.DataLoader(validation_data, batch_size=batch_size, shuffle=False, num_workers=num_workers)
test_data_loader = torch.utils.data.DataLoader(test_data, batch_size=batch_size, shuffle=False, num_workers=num_workers)
print(torch.cuda.is_available(), "\n")
if torch.cuda.is_available():
device = torch.device("cuda")
else:
device = torch.device("cpu")
print(f'Num training images: {len(train_data_loader.dataset)}')
print(f'Num validation images: {len(validation_data_loader.dataset)}')
print(f'Num test images: {len(test_data_loader.dataset)}')
def test_model(model):
print("Inside Test Model Function\n")
correct = 0
total = 0
with torch.no_grad():
for data in test_data_loader:
images, labels = data[0].to(device), data[1].to(device)
outputs = model(images)
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum().item()
print('correct: {:d} total: {:d}'.format(correct, total))
print('accuracy = {:f}'.format(correct / total))
model_resnet18.to(device)
optimizer = optim.Adam(model_resnet18.parameters(), lr=0.001)
if __name__ == "__main__":
train(model_resnet18, optimizer, torch.nn.CrossEntropyLoss(), train_data_loader, validation_data_loader, epochs=2, device=device)
test_model(model_resnet18)
model_resnet34.to(device)
optimizer = optim.Adam(model_resnet34.parameters(), lr=0.001)
if __name__ == "__main__":
train(model_resnet34, optimizer, torch.nn.CrossEntropyLoss(), train_data_loader, validation_data_loader, epochs=2, device=device)
test_model(model_resnet34)
import os
def find_classes(dir):
classes = os.listdir(dir)
classes.sort()
class_to_idx = {classes[i]: i for i in range(len(classes))}
return classes, class_to_idx
def make_prediction(model, filename):
labels, _ = find_classes('E:\\Image Recognition\\dogsandcats\\test\\test')
img = Image.open(filename)
img = img_test_transforms(img)
img = img.unsqueeze(0)
prediction = model(img.to(device))
prediction = prediction.argmax()
print(labels[prediction])
make_prediction(model_resnet34, 'E:\\Image Recognition\\dogsandcats\\test\\test\\3.jpg') #dog
make_prediction(model_resnet34, 'E:\\Image Recognition\\dogsandcats\\test\\test\\5.jpg') #cat
torch.save(model_resnet18.state_dict(), "./model_resnet18.pth")
torch.save(model_resnet34.state_dict(), "./model_resnet34.pth")
# Remember that you must call model.eval() to set dropout and batch normalization layers to
# evaluation mode before running inference. Failing to do this will yield inconsistent inference results.
resnet18 = torch.hub.load('pytorch/vision', 'resnet18')
resnet18.fc = nn.Sequential(nn.Linear(resnet18.fc.in_features,512),nn.ReLU(), nn.Dropout(), nn.Linear(512, num_classes))
resnet18.load_state_dict(torch.load('./model_resnet18.pth'))
resnet18.eval()
resnet34 = torch.hub.load('pytorch/vision', 'resnet34')
resnet34.fc = nn.Sequential(nn.Linear(resnet34.fc.in_features,512),nn.ReLU(), nn.Dropout(), nn.Linear(512, num_classes))
resnet34.load_state_dict(torch.load('./model_resnet34.pth'))
resnet34.eval()
# Test against the average of each prediction from the two models
models_ensemble = [resnet18.to(device), resnet34.to(device)]
correct = 0
total = 0
if __name__ == '__main__':
with torch.no_grad():
for data in test_data_loader:
images, labels = data[0].to(device), data[1].to(device)
predictions = [i(images).data for i in models_ensemble]
avg_predictions = torch.mean(torch.stack(predictions), dim=0)
_, predicted = torch.max(avg_predictions, 1)
total += labels.size(0)
correct += (predicted == labels).sum().item()
if total != 0:
print('accuracy = {:f}'.format(correct / total))
print('correct: {:d} total: {:d}'.format(correct, total))
To be very precise, I want to save my progress at the end of for batch in train_loader: loop, for say k = 1500.
If anyone can guide me about modifying my code so that I can save my progress and resume it later, then it will be a great and highly appreciated.
Whenever you want to save your training progress, you need to save two things:
Your model's state dict
Your optimizer's state dict
This can be done in the following way:
def save_checkpoint(model, optimizer, save_path, epoch):
torch.save({
'model_state_dict': model.state_dict(),
'optimizer_state_dict': optimizer.state_dict(),
'epoch': epoch
}, save_path)
To resume training, you can restore your model and optimizer's state dict.
def load_checkpoint(model, optimizer, load_path):
checkpoint = torch.load(load_path)
model.load_state_dict(checkpoint['model_state_dict'])
optimizer.load_state_dict(checkpoint['optimizer_state_dict'])
epoch = checkpoint['epoch']
return model, optimizer, epoch
You can save your model at any point in training, wherever you need to. However, it should be ideal to save after finishing an epoch.