def main():
# Define network
net = Net()
print(net)
data_transform = transforms.Compose(
[Rescale(250), Normalize(), RandomCrop(224)])
train_dataset = FacialKeypointsDataset(
csv_file='data/training_frames_keypoints.csv',
root_dir='data/training/',
transform=data_transform)
# iterate through the transformed dataset and print some stats about the first few samples
for i in range(4):
sample = train_dataset[i]
print(i, sample['image'].size, sample['keypoints'].size)
train_loader = DataLoader(train_dataset,
batch_size=10,
shuffle=True,
num_workers=4)
test_dataset = FacialKeypointsDataset(
csv_file='data/test_frames_keypoints.csv',
root_dir='data/test/',
transform=data_transform)
test_loader = DataLoader(test_dataset,
batch_size=1,
shuffle=True,
num_workers=4)
test_images, test_outputs, gt_pts = net_sample_output(net, test_loader)
# print out the dimensions of the data to see if they make sense
print(test_images.data.size())
print(test_outputs.data.size())
print(gt_pts.size())
# call it
visualize_output(test_images, test_outputs, gt_pts, 1)
criterion = nn.MSELoss()
optimizer = optim.Adam(net.parameters(),
lr=0.001,
betas=(0.9, 0.999),
eps=1e-8)
n_epochs = 2
train_net(net, criterion, optimizer, train_loader, n_epochs)
# get a sample of test data again
test_images, test_outputs, gt_pts = net_sample_output(net, test_loader)
print(test_images.data.size())
print(test_outputs.data.size())
print(gt_pts.size())
model_dir = 'saved_models/'
model_name = 'keypoints_model_1.pt'
# after training, save your model parameters in the dir 'saved_models'
torch.save(net.state_dict(), model_dir + model_name)
weights1 = net.conv1.weight.data
w = weights1.numpy()
filter_index = 0
print(w[filter_index][0])
print(w[filter_index][0].shape)
# display the filter weights
plt.imshow(w[filter_index][0], cmap='gray')
from torchvision import transforms, utils
from torch.utils.data import Dataset, DataLoader
from models import Net
import torch.nn.functional as F
import torch.nn as nn
import torch
import torchsnooper
import matplotlib.pyplot as plt
import numpy as np
device = torch.device('cuda')
net = Net()
data_transform = transforms.Compose(
[Rescale(256),
RandomCrop(224),
Normalize(),
ToTensor()]
)
train_dataset = FacialKeypointsDataset(
"./data/training_frames_keypoints.csv",
"./data/training",
data_transform
)
test_dataset = FacialKeypointsDataset(
"./data/test_frames_keypoints.csv",
"./data/test",
data_transform
)
running_loss += loss.item()
if batch_i % 10 == 9: # print every 10 batches
print('Epoch: {}, Batch: {}, Avg. Loss: {}'.format(
epoch + 1, batch_i + 1, running_loss / 10))
running_loss = 0.0
print('Finished Training')
if __name__ == "__main__":
net = Net()
# print(net)
data_transform = transforms.Compose(
[Rescale(225), RandomCrop(224),
Normalize(), ToTensor()])
# create the transformed dataset
transformed_dataset = FacialKeypointsDataset(
csv_file='data/training_frames_keypoints.csv',
root_dir='data/training/',
transform=data_transform)
print('Number of images: ', len(transformed_dataset))
# iterate through the transformed dataset and print some stats about the first few samples
for i in range(4):
sample = transformed_dataset[i]
print(i, sample['image'].size(), sample['keypoints'].size())
# In[24]:
from torch.utils.data import Dataset, DataLoader
from torchvision import transforms, utils
# the dataset we created in Notebook 1 is copied in the helper file `data_load.py`
from data_load import FacialKeypointsDataset
# the transforms we defined in Notebook 1 are ien the helper file `data_load.py`
from data_load import Rescale, RandomCrop, Normalize, ToTensor
## define the data_transform using transforms.Compose([all tx's, . , .])
# order matters! i.e. rescaling should come before a smaller crop
data_transform = None
rescale = Rescale(100)
crop = RandomCrop(50)
data_transform = transforms.Compose(
[Rescale(250), RandomCrop(224),
Normalize(), ToTensor()])
# testing that you've defined a transform
assert (data_transform is not None), 'Define a data_transform'
# In[25]:
# create the transformed dataset
transformed_dataset = FacialKeypointsDataset(
csv_file='/data/training_frames_keypoints.csv',
root_dir='/data/training/',
transform=data_transform)
print('Number of images: ', len(transformed_dataset))
def run_epochs(config, checkpoint_path):
print("CUDA is available: {}".format(torch.cuda.is_available()))
# Define data loader: data preprocessing and augmentation
# I use same procedures for all models that consumes imagenet-2012 dataset for simplicity
imagenet_train_transform = transforms.Compose([
Rescale(256),
RandomHorizontalFlip(0.5),
RandomCrop(224),
ColorJitter(brightness=0.2, contrast=0.2, saturation=0.2, hue=0),
ToTensor(),
# https://github.com/pytorch/examples/blob/master/imagenet/main.py#L195
# this is pre-calculated mean and std of imagenet dataset
Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
])
imagenet_val_transform = transforms.Compose([
Rescale(256),
CenterCrop(224),
ToTensor(),
Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
])
train_loader = initialize_train_loader(imagenet_train_transform, config)
val_loader = initialize_val_loader(imagenet_val_transform, config)
# Define the neural network.
Model = config.get('model')
model_params = config.get('model_params')
if model_params is not None:
net = Model(**model_params)
else:
net = Model()
# transfer variables to GPU if present
net.to(device=device)
# Print the network structure given 3x32x32 input
# need to put this before DataParallel to avoid "Expected more than 1 value per channel when training" error
# https://github.com/pytorch/pytorch/issues/4534
summary(net, (3, 224, 224))
# Wrap it with DataParallel to train with multiple GPUs
if torch.cuda.device_count() > 1:
print("Using", torch.cuda.device_count(), "GPUs!")
net = nn.DataParallel(net)
# Define the loss function. CrossEntrophyLoss is the most common one for classification task.
criterion = nn.CrossEntropyLoss()
# Define the optimizer
Optim = config.get('optimizer')
optimizer = Optim(
net.parameters(),
**config.get('optimizer_params'),
)
# Define the scheduler
Sched = config.get('scheduler')
scheduler = Sched(
optimizer,
**config.get('scheduler_params'),
)
loggers = initialize_loggers()
model_id = time.strftime("%Y-%m-%dT%H:%M:%S", time.localtime())
model_name = config.get('name')
start_epoch = 1
if checkpoint_path is not None:
net, optimizer, scheduler, loggers, start_epoch = load_checkpoint(
checkpoint_path,
net,
optimizer,
scheduler,
loggers,
)
validate(val_loader, net, criterion, 0, loggers)
for epoch in range(start_epoch, config.get('total_epochs') + 1):
train(
train_loader,
net,
criterion,
optimizer,
epoch,
loggers,
)
val_loss, top1_acc, top5_acc = validate(
val_loader,
net,
criterion,
epoch,
loggers,
)
# for ReduceLROnPlateau scheduler, we need to use top1_acc as metric
if isinstance(scheduler, optim.lr_scheduler.ReduceLROnPlateau):
scheduler.step(top1_acc)
else:
scheduler.step()
checkpoint_file = '{}-{}-epoch-{}.pt'.format(
model_name,
model_id,
epoch,
)
torch.save(
{
'epoch': epoch,
'model': net.state_dict(),
'optimizer': optimizer.state_dict(),
'scheduler': scheduler.state_dict(),
'loggers': loggers,
}, model_dir + checkpoint_file)
# As a note, should you want to perform data augmentation (which is optional in this project), and randomly rotate or shift these images, a square image size will be useful; rotating a 224x224 image by 90 degrees will result in the same shape of output.
# In[4]:
from torch.utils.data import Dataset, DataLoader
from torchvision import transforms, utils
# the dataset we created in Notebook 1 is copied in the helper file `data_load.py`
from data_load import FacialKeypointsDataset
# the transforms we defined in Notebook 1 are in the helper file `data_load.py`
from data_load import Rescale, RandomCrop, Normalize, ToTensor
## TODO: define the data_transform using transforms.Compose([all tx's, . , .])
# order matters! i.e. rescaling should come before a smaller crop
data_transform = transforms.Compose(
[Rescale(250), RandomCrop(224),
Normalize(), ToTensor()])
# testing that you've defined a transform
assert (data_transform is not None), 'Define a data_transform'
# In[5]:
# create the transformed dataset
transformed_dataset = FacialKeypointsDataset(
csv_file='/data/training_frames_keypoints.csv',
root_dir='/data/training/',
transform=data_transform)
print('Number of images: ', len(transformed_dataset))
net = Net().to(device)
print(net)
from torch.utils.data import Dataset, DataLoader
from torchvision import transforms, utils
# the dataset we created in Notebook 1 is copied in the helper file `data_load.py`
#from data_load import FacialKeypointsDataset
# the transforms we defined in Notebook 1 are in the helper file `data_load.py`
from data_load import Rescale, RandomCrop, Normalize, ToTensor
## TODO: define the data_transform using transforms.Compose([all tx's, . , .])
# order matters! i.e. rescaling should come before a smaller crop
data_transform = transforms.Compose(
[Rescale(250), RandomCrop(200),
Normalize(), ToTensor()])
# testing that you've defined a transform
assert (data_transform is not None), 'Define a data_transform'
# create the transformed dataset
transformed_dataset = FacialKeypointsDataset(
csv_file='./data/training_frames_keypoints.csv',
root_dir='./data/training/',
transform=data_transform)
print('Number of images: ', len(transformed_dataset))
# iterate through the transformed dataset and print some stats about the first few samples
for i in range(4):
# In[133]:
from torch.utils.data import Dataset, DataLoader
from torchvision import transforms, utils
# the dataset we created in Notebook 1 is copied in the helper file `data_load.py`
from data_load import FacialKeypointsDataset
# the transforms we defined in Notebook 1 are in the helper file `data_load.py`
from data_load import Rescale, RandomCrop, Normalize, ToTensor
crop = 224
data_transform = transforms.Compose([Rescale(250),
RandomCrop(crop),
Normalize(crop),
ToTensor()])
# testing that you've defined a transform
assert(data_transform is not None), 'Define a data_transform'
# In[134]:
# create the transformed dataset
transformed_dataset = FacialKeypointsDataset(csv_file='training_frames_keypoints.csv',
root_dir='/home/tianbai/P1_Facial_Keypoints/data/training/',
transform=data_transform)
