Hello all.
I training a PyTorch model and try to find error. The error occurs because of changing input image jpg file(448,448,3) to png file(1080, 1920, 3)
error :RuntimeError: Sizes of tensors must match except in dimension 2. Got 67 and 66 (The offending index is 0)
main code :
import torch
from torch import nn
from unet.unet_transfer import UNet16, UNetResNet
from pathlib import Path
import torchvision.transforms as transforms
from torch.utils.data import DataLoader, Dataset, random_split
import torch.nn.functional as F
from torch.autograd import Variable
import shutil
from data_loader import ImgDataSet
import os
import argparse
import tqdm
import numpy as np
import scipy.ndimage as ndimage
class AverageMeter(object):
"""Computes and stores the average and current value"""
def __init__(self):
self.reset()
def reset(self):
self.val = 0
self.avg = 0
self.sum = 0
self.count = 0
def update(self, val, n=1):
self.val = val
self.sum += val * n
self.count += n
self.avg = self.sum / self.count
def create_model(device, type ='vgg16'):
if type == 'vgg16':
print('create vgg16 model')
model = UNet16(pretrained=True)
elif type == 'resnet101':
encoder_depth = 101
num_classes = 1
print('create resnet101 model')
model = UNetResNet(encoder_depth=encoder_depth, num_classes=num_classes, pretrained=True)
elif type == 'resnet34':
encoder_depth = 34
num_classes = 1
print('create resnet34 model')
model = UNetResNet(encoder_depth=encoder_depth, num_classes=num_classes, pretrained=True)
else:
assert False
model.eval()
return model.to(device)
def adjust_learning_rate(optimizer, epoch, lr):
"""Sets the learning rate to the initial LR decayed by 10 every 30 epochs"""
lr = lr * (0.1 ** (epoch // 30))
for param_group in optimizer.param_groups:
param_group['lr'] = lr
def find_latest_model_path(dir):
model_paths = []
epochs = []
for path in Path(dir).glob('*.pt'):
if 'epoch' not in path.stem:
continue
model_paths.append(path)
parts = path.stem.split('_')
epoch = int(parts[-1])
epochs.append(epoch)
if len(epochs) > 0:
epochs = np.array(epochs)
max_idx = np.argmax(epochs)
return model_paths[max_idx]
else:
return None
def train(train_loader, model, criterion, optimizer, validation, args):
latest_model_path = find_latest_model_path(args.model_dir)
best_model_path = os.path.join(*[args.model_dir, 'model_best.pt'])
if latest_model_path is not None:
state = torch.load(latest_model_path)
epoch = state['epoch']
model.load_state_dict(state['model'])
epoch = epoch
#if latest model path does exist, best_model_path should exists as well
assert Path(best_model_path).exists() == True, f'best model path {best_model_path} does not exist'
#load the min loss so far
best_state = torch.load(latest_model_path)
min_val_los = best_state['valid_loss']
print(f'Restored model at epoch {epoch}. Min validation loss so far is : {min_val_los}')
epoch += 1
print(f'Started training model from epoch {epoch}')
else:
print('Started training model from epoch 0')
epoch = 0
min_val_los = 9999
valid_losses = []
for epoch in range(epoch, args.n_epoch + 1):
adjust_learning_rate(optimizer, epoch, args.lr)
tq = tqdm.tqdm(total=(len(train_loader) * args.batch_size))
tq.set_description(f'Epoch {epoch}')
losses = AverageMeter()
model.train()
for i, (input, target) in enumerate(train_loader):
input_var = Variable(input).cuda()
target_var = Variable(target).cuda()
masks_pred = model(input_var)
masks_probs_flat = masks_pred.view(-1)
true_masks_flat = target_var.view(-1)
loss = criterion(masks_probs_flat, true_masks_flat)
losses.update(loss)
tq.set_postfix(loss='{:.5f}'.format(losses.avg))
tq.update(args.batch_size)
# compute gradient and do SGD step
optimizer.zero_grad()
loss.backward()
optimizer.step()
valid_metrics = validation(model, valid_loader, criterion)
valid_loss = valid_metrics['valid_loss']
valid_losses.append(valid_loss)
print(f'\tvalid_loss = {valid_loss:.5f}')
tq.close()
#save the model of the current epoch
epoch_model_path = os.path.join(*[args.model_dir, f'model_epoch_{epoch}.pt'])
torch.save({
'model': model.state_dict(),
'epoch': epoch,
'valid_loss': valid_loss,
'train_loss': losses.avg
}, epoch_model_path)
if valid_loss < min_val_los:
min_val_los = valid_loss
torch.save({
'model': model.state_dict(),
'epoch': epoch,
'valid_loss': valid_loss,
'train_loss': losses.avg
}, best_model_path)
def validate(model, val_loader, criterion):
losses = AverageMeter()
model.eval()
with torch.no_grad():
for i, (input, target) in enumerate(val_loader):
input_var = Variable(input).cuda()
target_var = Variable(target).cuda()
output = model(input_var)
loss = criterion(output, target_var)
losses.update(loss.item(), input_var.size(0))
return {'valid_loss': losses.avg}
def save_check_point(state, is_best, file_name = 'checkpoint.pth.tar'):
torch.save(state, file_name)
if is_best:
shutil.copy(file_name, 'model_best.pth.tar')
def calc_crack_pixel_weight(mask_dir):
avg_w = 0.0
n_files = 0
for path in Path(mask_dir).glob('*.*'):
n_files += 1
m = ndimage.imread(path)
ncrack = np.sum((m > 0)[:])
w = float(ncrack)/(m.shape[0]*m.shape[1])
avg_w = avg_w + (1-w)
avg_w /= float(n_files)
return avg_w / (1.0 - avg_w)
if __name__ == '__main__':
parser = argparse.ArgumentParser(description='PyTorch ImageNet Training')
parser.add_argument('-n_epoch', default=10, type=int, metavar='N', help='number of total epochs to run')
parser.add_argument('-lr', default=0.001, type=float, metavar='LR', help='initial learning rate')
parser.add_argument('-momentum', default=0.9, type=float, metavar='M', help='momentum')
parser.add_argument('-print_freq', default=20, type=int, metavar='N', help='print frequency (default: 10)')
parser.add_argument('-weight_decay', default=1e-4, type=float, metavar='W', help='weight decay (default: 1e-4)')
parser.add_argument('-batch_size', default=4, type=int, help='weight decay (default: 1e-4)')
parser.add_argument('-num_workers', default=4, type=int, help='output dataset directory')
parser.add_argument('-data_dir',type=str, help='input dataset directory')
parser.add_argument('-model_dir', type=str, help='output dataset directory')
parser.add_argument('-model_type', type=str, required=False, default='resnet101', choices=['vgg16', 'resnet101', 'resnet34'])
args = parser.parse_args()
os.makedirs(args.model_dir, exist_ok=True)
DIR_IMG = os.path.join(args.data_dir, 'images')
DIR_MASK = os.path.join(args.data_dir, 'masks')
img_names = [path.name for path in Path(DIR_IMG).glob('*.png')]
mask_names = [path.name for path in Path(DIR_MASK).glob('*.png')]
print(f'total images = {len(img_names)}')
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model = create_model(device, args.model_type)
optimizer = torch.optim.SGD(model.parameters(), args.lr,
momentum=args.momentum,
weight_decay=args.weight_decay)
#crack_weight = 0.4*calc_crack_pixel_weight(DIR_MASK)
#print(f'positive weight: {crack_weight}')
#criterion = nn.BCEWithLogitsLoss(pos_weight=torch.Tensor([crack_weight]).to('cuda'))
criterion = nn.BCEWithLogitsLoss().to('cuda')
channel_means = [0.485, 0.456, 0.406]
channel_stds = [0.229, 0.224, 0.225]
train_tfms = transforms.Compose([transforms.ToTensor(),
transforms.Normalize(channel_means, channel_stds)])
val_tfms = transforms.Compose([transforms.ToTensor(),
transforms.Normalize(channel_means, channel_stds)])
mask_tfms = transforms.Compose([transforms.ToTensor()])
dataset = ImgDataSet(img_dir=DIR_IMG, img_fnames=img_names, img_transform=train_tfms, mask_dir=DIR_MASK, mask_fnames=mask_names, mask_transform=mask_tfms)
train_size = int(0.85*len(dataset))
valid_size = len(dataset) - train_size
train_dataset, valid_dataset = random_split(dataset, [train_size, valid_size])
train_loader = DataLoader(train_dataset, args.batch_size, shuffle=False, pin_memory=torch.cuda.is_available(), num_workers=args.num_workers)
valid_loader = DataLoader(valid_dataset, args.batch_size, shuffle=False, pin_memory=torch.cuda.is_available(), num_workers=args.num_workers)
model.cuda()
train(train_loader, model, criterion, optimizer, validate, args)
dataloader code :
import os
import numpy as np
from torch.utils.data import DataLoader, Dataset
import random
from PIL import Image
import matplotlib.pyplot as plt
class ImgDataSet(Dataset):
def __init__(self, img_dir, img_fnames, img_transform, mask_dir, mask_fnames, mask_transform):
self.img_dir = img_dir
self.img_fnames = img_fnames
self.img_transform = img_transform
self.mask_dir = mask_dir
self.mask_fnames = mask_fnames
self.mask_transform = mask_transform
self.seed = np.random.randint(2147483647)
def __getitem__(self, i):
fname = self.img_fnames[i]
fpath = os.path.join(self.img_dir, fname)
img = Image.open(fpath)
if self.img_transform is not None:
random.seed(self.seed)
img = self.img_transform(img)
#print('image shape', img.shape)
mname = self.mask_fnames[i]
mpath = os.path.join(self.mask_dir, mname)
mask = Image.open(mpath)
#print('khanh1', np.min(test[:]), np.max(test[:]))
if self.mask_transform is not None:
mask = self.mask_transform(mask)
#print('mask shape', mask.shape)
#print('khanh2', np.min(test[:]), np.max(test[:]))
return img, mask #torch.from_numpy(np.array(mask, dtype=np.int64))
def __len__(self):
return len(self.img_fnames)
class ImgDataSetJoint(Dataset):
def __init__(self, img_dir, img_fnames, joint_transform, mask_dir, mask_fnames, img_transform = None, mask_transform = None):
self.joint_transform = joint_transform
self.img_dir = img_dir
self.img_fnames = img_fnames
self.img_transform = img_transform
self.mask_dir = mask_dir
self.mask_fnames = mask_fnames
self.mask_transform = mask_transform
self.seed = np.random.randint(2147483647)
def __getitem__(self, i):
fname = self.img_fnames[i]
fpath = os.path.join(self.img_dir, fname)
img = Image.open(fpath)
mname = self.mask_fnames[i]
mpath = os.path.join(self.mask_dir, mname)
mask = Image.open(mpath)
if self.joint_transform is not None:
img, mask = self.joint_transform([img, mask])
#debug
# img = np.asarray(img)
# mask = np.asarray(mask)
# plt.subplot(121)
# plt.imshow(img)
# plt.subplot(122)
# plt.imshow(img)
# plt.imshow(mask, alpha=0.4)
# plt.show()
if self.img_transform is not None:
img = self.img_transform(img)
if self.mask_transform is not None:
mask = self.mask_transform(mask)
return img, mask #torch.from_numpy(np.array(mask, dtype=np.int64))
def __len__(self):
return len(self.img_fnames)
model code :
from torch import nn
from torch.nn import functional as F
import torch
from torchvision import models
import torchvision
input_size = (448, 448)
class Interpolate(nn.Module):
def __init__(self, size=None, scale_factor=None, mode='nearest', align_corners=False):
super(Interpolate, self).__init__()
self.interp = nn.functional.interpolate
self.size = size
self.mode = mode
self.scale_factor = scale_factor
self.align_corners = align_corners
def forward(self, x):
x = self.interp(x, size=self.size, scale_factor=self.scale_factor,
mode=self.mode, align_corners=self.align_corners)
return x
def conv3x3(in_, out):
return nn.Conv2d(in_, out, 3, padding=1)
class ConvRelu(nn.Module):
def __init__(self, in_, out):
super().__init__()
self.conv = conv3x3(in_, out)
self.activation = nn.ReLU(inplace=True)
def forward(self, x):
x = self.conv(x)
x = self.activation(x)
return x
class DecoderBlockV2(nn.Module):
def __init__(self, in_channels, middle_channels, out_channels, is_deconv=True):
super(DecoderBlockV2, self).__init__()
self.in_channels = in_channels
if is_deconv:
"""
Paramaters for Deconvolution were chosen to avoid artifacts, following
link https://distill.pub/2016/deconv-checkerboard/
"""
self.block = nn.Sequential(
ConvRelu(in_channels, middle_channels),
nn.ConvTranspose2d(middle_channels, out_channels, kernel_size=4, stride=2,
padding=1),
nn.ReLU(inplace=True)
)
else:
self.block = nn.Sequential(
Interpolate(scale_factor=2, mode='bilinear'),
ConvRelu(in_channels, middle_channels),
ConvRelu(middle_channels, out_channels),
)
def forward(self, x):
return self.block(x)
class UNet16(nn.Module):
def __init__(self, num_classes=1, num_filters=32, pretrained=False, is_deconv=False):
"""
:param num_classes:
:param num_filters:
:param pretrained:
False - no pre-trained network used
True - encoder pre-trained with VGG16
:is_deconv:
False: bilinear interpolation is used in decoder
True: deconvolution is used in decoder
"""
super().__init__()
self.num_classes = num_classes
self.pool = nn.MaxPool2d(2, 2)
#print(torchvision.models.vgg16(pretrained=pretrained))
self.encoder = torchvision.models.vgg16(pretrained=pretrained).features
self.relu = nn.ReLU(inplace=True)
self.conv1 = nn.Sequential(self.encoder[0],
self.relu,
self.encoder[2],
self.relu)
self.conv2 = nn.Sequential(self.encoder[5],
self.relu,
self.encoder[7],
self.relu)
self.conv3 = nn.Sequential(self.encoder[10],
self.relu,
self.encoder[12],
self.relu,
self.encoder[14],
self.relu)
self.conv4 = nn.Sequential(self.encoder[17],
self.relu,
self.encoder[19],
self.relu,
self.encoder[21],
self.relu)
self.conv5 = nn.Sequential(self.encoder[24],
self.relu,
self.encoder[26],
self.relu,
self.encoder[28],
self.relu)
self.center = DecoderBlockV2(512, num_filters * 8 * 2, num_filters * 8, is_deconv)
self.dec5 = DecoderBlockV2(512 + num_filters * 8, num_filters * 8 * 2, num_filters * 8, is_deconv)
self.dec4 = DecoderBlockV2(512 + num_filters * 8, num_filters * 8 * 2, num_filters * 8, is_deconv)
self.dec3 = DecoderBlockV2(256 + num_filters * 8, num_filters * 4 * 2, num_filters * 2, is_deconv)
self.dec2 = DecoderBlockV2(128 + num_filters * 2, num_filters * 2 * 2, num_filters, is_deconv)
self.dec1 = ConvRelu(64 + num_filters, num_filters)
self.final = nn.Conv2d(num_filters, num_classes, kernel_size=1)
def forward(self, x):
conv1 = self.conv1(x)
conv2 = self.conv2(self.pool(conv1))
conv3 = self.conv3(self.pool(conv2))
conv4 = self.conv4(self.pool(conv3))
conv5 = self.conv5(self.pool(conv4))
center = self.center(self.pool(conv5))
dec5 = self.dec5(torch.cat([center, conv5], 1))
dec4 = self.dec4(torch.cat([dec5, conv4], 1))
dec3 = self.dec3(torch.cat([dec4, conv3], 1))
dec2 = self.dec2(torch.cat([dec3, conv2], 1))
dec1 = self.dec1(torch.cat([dec2, conv1], 1))
if self.num_classes > 1:
x_out = F.log_softmax(self.final(dec1), dim=1)
else:
x_out = self.final(dec1)
#x_out = F.sigmoid(x_out)
return x_out