Basically following the guide and made some minor adjustments.
I want to load in RGB images paired with binary masks.
If anyone could point me to some good examples of this. (Ones that don’t use .csv or other ‘label’-oriented files.)
Error:
Traceback (most recent call last):
File "densenet/PyTorchAttempt2.py", line 340, in <module>
model_ft, hist = train_model(model_ft, loaders, criterion, optimizer_ft, num_epochs=num_epochs, is_inception=(model_name=="inception"))
File "densenet/PyTorchAttempt2.py", line 188, in train_model
loss = criterion(outputs, labels)
File "venv/lib/python3.6/site-packages/torch/nn/modules/module.py", line 489, in __call__
result = self.forward(*input, **kwargs)
File "venv/lib/python3.6/site-packages/torch/nn/modules/loss.py", line 904, in forward
ignore_index=self.ignore_index, reduction=self.reduction)
File "venv/lib/python3.6/site-packages/torch/nn/functional.py", line 1970, in cross_entropy
return nll_loss(log_softmax(input, 1), target, weight, None, ignore_index, None, reduction)
File "/venv/lib/python3.6/site-packages/torch/nn/functional.py", line 1790, in nll_loss
ret = torch._C._nn.nll_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index)
RuntimeError: Expected object of scalar type Long but got scalar type Float for argument #2 'target'
Code:
from __future__ import print_function, division
import os
import torch
from skimage import io, transform
import numpy as np
import matplotlib.pyplot as plt
from torch.utils.data import Dataset, DataLoader
from torchvision import transforms, utils, models
from common import dataset as qc_ds
from PIL import Image
import time
import os
import copy
import torch.nn as nn
import torch.optim as optim
print("PyTorch Version: ",torch.__version__)
# Ignore warnings
import warnings
warnings.filterwarnings("ignore")
plt.ion() # interactive mode
# Models to choose from [resnet, alexnet, vgg, squeezenet, densenet, inception]
model_name = "densenet"
# Number of classes in the dataset
num_classes = 1
# Batch size for training (change depending on how much memory you have)
batch_size = 8
# Number of epochs to train for
num_epochs = 15
# Flag for feature extracting. When False, we finetune the whole model,
# when True we only update the reshaped layer params
feature_extract = True
class QCDataset(Dataset):
def __init__(self, paths, transform=None):
self.paths = paths
self.transform = transform
ds = qc_ds.Dataset(0, 0, 0, 0)
(frontImages, frontMasks, sideImages, sideMasks) = ds.get_file_names(paths)
self.frontImages = frontImages
self.frontMasks = frontMasks
def __len__(self):
return len(self.frontImages)
def __getitem__(self, idx):
print('Getting ', idx, ' image')
print(self.frontImages[idx])
print(self.frontMasks[idx])
# image = io.imread(self.frontImages[idx])
# mask = io.imread(self.frontMasks[idx])
image = Image.open(self.frontImages[idx]).convert('RGB')
mask = Image.open(self.frontMasks[idx]).convert('L')
image = self.transform(image)
mask = self.transform(mask)
print(image.shape)
print(mask.shape)
return (image, mask)
def show_ds(dataset):
print('Plotting figure')
plt.figure(figsize=(10, 20))
for i in range(4):
(image, mask) = dataset[i]
plt.tight_layout()
plt.axis('on')
plt.subplot(5, 5, 1 * i + 1)
plt.imshow(image)
plt.title("Image")
plt.subplot(5, 5, 2 * i + 2)
plt.imshow(mask)
plt.title("Actual Mask")
plt.pause(2) # pause a bit so that plots are updated
if i == 4:
plt.ioff()
plt.show()
break
plt.show()
def getValDS():
validationPath = '/Users/...'
myPath4 = '/Users/....'
valids = [myPath4, validationPath]
data_transform = transforms.Compose([
transforms.RandomSizedCrop(input_size),
# transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
# transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
])
val_ds = QCDataset(paths=valids, transform=data_transform)
return val_ds
def getDS():
myPath1 = '/Users/...'
myPath2 ='/Users/...'
myPath3 = '/Users/...'
myPath4 = '/Users/...'
validationPath = '/Users/...'
allPaths = [myPath1, myPath2, myPath3]
valids = [myPath4]
data_transform = transforms.Compose([
transforms.RandomSizedCrop(input_size),
# transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
# transforms.Normalize(mean=[0.485, 0.456, 0.406],std=[0.229, 0.224, 0.225])
])
tds = QCDataset(paths=allPaths, transform=data_transform)
return tds
def set_parameter_requires_grad(model, feature_extracting):
if feature_extracting:
for param in model.parameters():
param.requires_grad = False
def train_model(model, dataloaders, criterion, optimizer, num_epochs=25, is_inception=False):
since = time.time()
val_acc_history = []
best_model_wts = copy.deepcopy(model.state_dict())
best_acc = 0.0
for epoch in range(num_epochs):
print('Epoch {}/{}'.format(epoch, num_epochs - 1))
print('-' * 10)
# Each epoch has a training and validation phase
for phase in ['train', 'val']:
if phase == 'train':
model.train() # Set model to training mode
else:
model.eval() # Set model to evaluate mode
running_loss = 0.0
running_corrects = 0
# Iterate over data.
for inputs, labels in dataloaders[phase]:
inputs = inputs.to(device)
labels = labels.to(device)
# zero the parameter gradients
optimizer.zero_grad()
# forward
# track history if only in train
with torch.set_grad_enabled(phase == 'train'):
# Get model outputs and calculate loss
# Special case for inception because in training it has an auxiliary output. In train
# mode we calculate the loss by summing the final output and the auxiliary output
# but in testing we only consider the final output.
if is_inception and phase == 'train':
# From https://discuss.pytorch.org/t/how-to-optimize-inception-model-with-auxiliary-classifiers/7958
outputs, aux_outputs = model(inputs)
loss1 = criterion(outputs, labels)
loss2 = criterion(aux_outputs, labels)
loss = loss1 + 0.4*loss2
else:
outputs = model(inputs)
#outputs = outputs.float()
print(outputs)
loss = criterion(outputs, labels)
_, preds = torch.max(outputs, 1)
# backward + optimize only if in training phase
if phase == 'train':
loss.backward()
optimizer.step()
# statistics
running_loss += loss.item() * inputs.size(0)
running_corrects += torch.sum(preds == labels.data)
epoch_loss = running_loss / len(dataloaders[phase].dataset)
epoch_acc = running_corrects.double() / len(dataloaders[phase].dataset)
print('{} Loss: {:.4f} Acc: {:.4f}'.format(phase, epoch_loss, epoch_acc))
# deep copy the model
if phase == 'val' and epoch_acc > best_acc:
best_acc = epoch_acc
best_model_wts = copy.deepcopy(model.state_dict())
if phase == 'val':
val_acc_history.append(epoch_acc)
print()
time_elapsed = time.time() - since
print('Training complete in {:.0f}m {:.0f}s'.format(time_elapsed // 60, time_elapsed % 60))
print('Best val Acc: {:4f}'.format(best_acc))
# load best model weights
model.load_state_dict(best_model_wts)
return model, val_acc_history
def initialize_model(model_name, num_classes, feature_extract, use_pretrained=True):
# Initialize these variables which will be set in this if statement. Each of these
# variables is model specific.
model_ft = None
input_size = 0
if model_name == "resnet":
""" Resnet18
"""
model_ft = models.resnet18(pretrained=use_pretrained)
set_parameter_requires_grad(model_ft, feature_extract)
num_ftrs = model_ft.fc.in_features
model_ft.fc = nn.Linear(num_ftrs, num_classes)
input_size = 224
elif model_name == "alexnet":
""" Alexnet
"""
model_ft = models.alexnet(pretrained=use_pretrained)
set_parameter_requires_grad(model_ft, feature_extract)
num_ftrs = model_ft.classifier[6].in_features
model_ft.classifier[6] = nn.Linear(num_ftrs,num_classes)
input_size = 224
elif model_name == "vgg":
""" VGG11_bn
"""
model_ft = models.vgg11_bn(pretrained=use_pretrained)
set_parameter_requires_grad(model_ft, feature_extract)
num_ftrs = model_ft.classifier[6].in_features
model_ft.classifier[6] = nn.Linear(num_ftrs,num_classes)
input_size = 224
elif model_name == "squeezenet":
""" Squeezenet
"""
model_ft = models.squeezenet1_0(pretrained=use_pretrained)
set_parameter_requires_grad(model_ft, feature_extract)
model_ft.classifier[1] = nn.Conv2d(512, num_classes, kernel_size=(1,1), stride=(1,1))
model_ft.num_classes = num_classes
input_size = 224
elif model_name == "densenet":
""" Densenet
"""
model_ft = models.densenet121(pretrained=use_pretrained)
set_parameter_requires_grad(model_ft, feature_extract)
num_ftrs = model_ft.classifier.in_features
model_ft.classifier = nn.Linear(num_ftrs, num_classes)
input_size = 224
elif model_name == "inception":
""" Inception v3
Be careful, expects (299,299) sized images and has auxiliary output
"""
model_ft = models.inception_v3(pretrained=use_pretrained)
set_parameter_requires_grad(model_ft, feature_extract)
# Handle the auxilary net
num_ftrs = model_ft.AuxLogits.fc.in_features
model_ft.AuxLogits.fc = nn.Linear(num_ftrs, num_classes)
# Handle the primary net
num_ftrs = model_ft.fc.in_features
model_ft.fc = nn.Linear(num_ftrs,num_classes)
input_size = 299
else:
print("Invalid model name, exiting...")
exit()
return model_ft, input_size
# Initialize the model for this run
model_ft, input_size = initialize_model(model_name, num_classes, feature_extract, use_pretrained=True)
# Print the model we just instantiated
print(model_ft)
tds = getDS()
valds = getValDS()
tds_loader = DataLoader(tds, batch_size=batch_size, shuffle=True, num_workers=4)
valds_loader = DataLoader(valds, batch_size=batch_size, shuffle=True, num_workers=4)
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
# Send the model to GPU
model_ft = model_ft.to(device)
# Gather the parameters to be optimized/updated in this run. If we are
# finetuning we will be updating all parameters. However, if we are
# doing feature extract method, we will only update the parameters
# that we have just initialized, i.e. the parameters with requires_grad
# is True.
params_to_update = model_ft.parameters()
print("Params to learn:")
if feature_extract:
params_to_update = []
for name,param in model_ft.named_parameters():
if param.requires_grad == True:
params_to_update.append(param)
print("\t",name)
else:
for name,param in model_ft.named_parameters():
if param.requires_grad == True:
print("\t",name)
# Observe that all parameters are being optimized
optimizer_ft = optim.SGD(params_to_update, lr=0.001, momentum=0.9)
# Setup the loss fxn
criterion = nn.CrossEntropyLoss()
loaders = {}
loaders['train'] = tds_loader
loaders['val'] = valds_loader
# Train and evaluate
model_ft, hist = train_model(model_ft, loaders, criterion, optimizer_ft, num_epochs=num_epochs, is_inception=(model_name=="inception"))