def debug_me():
# Define network
net = Net()
print(net)
data_transform = transforms.Compose(
[Rescale(250), RandomCrop(224),
Normalize()])
aww_dataset = FacialKeypointsDataset(
csv_file='data/aww_frames_keypoints.csv',
root_dir='data/aww/',
transform=data_transform)
sample = aww_dataset[0]
print(sample['image'].shape, sample['keypoints'].shape)
print(np.max(sample['keypoints']))
aww_loader = DataLoader(aww_dataset,
batch_size=10,
shuffle=True,
num_workers=4)
aww_images, aww_outputs, gt_pts = net_sample_output(net, aww_loader)
visualize_output(aww_images, aww_outputs, gt_pts, 1)
'''
def predict(imagePath, modelPath=None):
# load trained model
if (modelPath == None):
predict_model = model
else:
checkpoint = torch.load(modelPath,
map_location=lambda storage, loc: storage)
predict_model = Net().double()
if args.cuda:
predict_model = predict_model.cuda()
predict_model.load_state_dict(checkpoint['state_dict'])
# load image
image = io.imread(imagePath)
transform = transforms.Compose([CropSquare(), Rescale(256), ToTensor()])
image = transform(image)
data = image.unsqueeze(0)
data = Variable(data)
output = predict_model(data)
# get the index of the max log-probability
pred = output.data.max(1, keepdim=True)[1]
print(pred.item())
return pred.item()
def run():
print("CUDA is available: {}".format(torch.cuda.is_available()))
data_transform = transforms.Compose(
[Rescale(250), CenterCrop(224),
Normalize(), ToTensor()])
# loader will split datatests into batches witht size defined by batch_size
train_loader = initialize_train_loader(data_transform)
test_loader = initialize_test_loader(data_transform)
model_id = time.strftime("%Y-%m-%dT%H:%M:%S", time.localtime())
# instantiate the neural network
net = Net()
net.to(device=device)
summary(net, (1, 224, 224))
# define the loss function using SmoothL1Loss
criterion = nn.SmoothL1Loss()
# define the params updating function using Adam
optimizer = optim.Adam(net.parameters(), lr=0.001)
loss_logger = []
for i in range(1, epochs + 1):
model_name = 'model-{}-epoch-{}.pt'.format(model_id, i)
# train all data for one epoch
train(net, criterion, optimizer, i, train_loader, model_id,
loss_logger)
# evaludate the accuracy after each epoch
evaluate(net, criterion, i, test_loader)
# save model after every 5 epochs
# https://discuss.pytorch.org/t/loading-a-saved-model-for-continue-training/17244/3
# https://github.com/pytorch/pytorch/issues/2830
# https://pytorch.org/tutorials/beginner/saving_loading_models.html
if i % 5 == 1:
torch.save(
{
'epoch': i,
'model': net.state_dict(),
'optimizer': optimizer.state_dict(),
'loss_logger': loss_logger,
}, model_dir + model_name)
print("Finished training!")
model_name = 'model-{}-final.pt'.format(model_id)
torch.save(
{
'epoch': epochs,
'model': net.state_dict(),
'optimizer': optimizer.state_dict(),
'loss_logger': loss_logger,
}, model_dir + model_name)
def show_transformed(self, index):
# test out some of these transforms
rescale = Rescale(100)
crop = RandomCrop(50)
composed = transforms.Compose([Rescale(250), RandomCrop(224)])
# apply the transforms to a sample image
test_num = 500
sample = face_dataset[test_num]
fig = plt.figure()
for i, tx in enumerate([rescale, crop, composed]):
transformed_sample = tx(sample)
ax = plt.subplot(1, 3, i + 1)
plt.tight_layout()
ax.set_title(type(tx).__name__)
show_keypoints(transformed_sample['image'],
transformed_sample['keypoints'])
plt.show()
def main():
hyp_batch_size = 20
net = Net2()
model_dir = '../saved_models/'
model_name = 'keypoints_model_2.pt'
data_transform = transforms.Compose([
Rescale(256),
RandomCrop(224),
Normalize(),
ToTensor()
])
# retreive the saved model
net_state_dict = torch.load(model_dir+model_name)
net.load_state_dict(net_state_dict)
# load the test data
test_dataset = FacialKeypointsDataset(csv_file='../files/test_frames_keypoints.csv',
root_dir='../files/test/',
transform=data_transform)
# load test data in batches
batch_size = hyp_batch_size
test_loader = DataLoader(test_dataset,
batch_size=batch_size,
shuffle=True,
num_workers=0)
test_images, test_outputs, gt_pts = net_sample_output(test_loader, net)
print(test_images.data.size())
print(test_outputs.data.size())
print(gt_pts.size())
# Get the weights in the first conv layer, "conv1"
# if necessary, change this to reflect the name of your first conv layer
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')
#plt.show()
##TODO: load in and display any image from the transformed test dataset
i = 1
show_image(test_images, w, i)
def __init__(self, root_dir=None):
self.data_root_dir = root_dir or './data/'
self.training_csv = os.path.join(self.data_root_dir,
'training_frames_keypoints.csv')
self.training_data_dir = os.path.join(self.data_root_dir, 'training/')
self.test_csv = os.path.join(self.data_root_dir,
'test_frames_keypoints.csv')
self.test_data_dir = os.path.join(self.data_root_dir, 'test/')
self.key_pts_frame = pd.read_csv(self.training_csv)
self.face_dataset = FacialKeypointsDataset(
csv_file=self.training_csv, root_dir=self.training_data_dir)
self.face_dataset_len = len(self.face_dataset)
# define the data tranform
# order matters! i.e. rescaling should come before a smaller crop
self.data_transform = transforms.Compose(
[Rescale(250),
RandomCrop(224),
Normalize(),
ToTensor()])
self.transformed_training_data = self.transform_data(
self.training_csv, self.training_data_dir)
self.transformed_test_data = self.transform_data(
self.test_csv, self.test_data_dir)
def data_transform(npy_train, npy_test, batch_size=64, shuffle=True):
# Setting up our image transforms
DATA_TRANSFORM = transforms.Compose(
[Rescale(256), RandomCrop(224),
Normalize(), ToTensor()])
# importing in the Custome dataset
TRANSFORMED_DATASET_TRAIN = KeypointDataSet(npy_file=npy_train,
root_dir='data/',
transform=DATA_TRANSFORM)
TRANSFORMED_DATASET_TEST = KeypointDataSet(npy_file=npy_test,
root_dir='data/',
transform=DATA_TRANSFORM)
# passing in the trainformed data into the dataLoader
TRAIN_LOADER = DataLoader(TRANSFORMED_DATASET_TRAIN,
batch_size=64,
shuffle=True,
pin_memory=True)
TEST_LOADER = DataLoader(TRANSFORMED_DATASET_TEST,
batch_size=64,
shuffle=True,
pin_memory=True)
return TRAIN_LOADER, TEST_LOADER
from torch.utils.data import DataLoader
from torchvision import transforms
from data_load import FacialKeypointsDataset, Rescale, RandomCrop, Normalize, ToTensor
from models import Net
net = Net()
net.load_state_dict(
torch.load(
r'C:\Users\Semanti Basu\Documents\OneDrive_2020-02-19\3D Ceaser dataset\Image and point generation\Image and point generation\frontaltrainedmodel_10epoch.pth'
))
## print out your net and prepare it for testing (uncomment the line below)
net.eval()
data_transform = transforms.Compose(
[Rescale(225), RandomCrop(224),
Normalize(), ToTensor()])
transformed_dataset = FacialKeypointsDataset(
csv_file=
r'C:\Users\Semanti Basu\Documents\OneDrive_2020-02-19\3D Ceaser dataset\Image and point generation\Image and point generation\frontalpoints.csv',
root_dir=
r'C:\Users\Semanti Basu\Documents\OneDrive_2020-02-19\3D Ceaser dataset\Image and point generation\Image and point generation\ceasar_mat',
transform=data_transform)
# load training data in batches
batch_size = 10
train_loader = DataLoader(transformed_dataset,
batch_size=batch_size,
shuffle=True,
num_workers=0)
from torch import FloatTensor
from torch.utils.data import DataLoader
from torchvision import transforms
from data_load import FacialKeypointsDataset, Rescale, RandomCrop, Normalize, ToTensor
from models import Net
net = Net()
print(net)
criterion = nn.SmoothL1Loss()
optimizer = optim.Adam(net.parameters(), lr=0.01)
""" Load data """
# define the data transform
data_transform = transforms.Compose([Rescale(250),
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)
# load training data in batches
batch_size = 50
train_loader = DataLoader(transformed_dataset,
batch_size=batch_size,
shuffle=True,
num_workers=0)
# the transforms we defined in Notebook 1 are in the helper file `data_load.py`
from data_load import Rescale, RandomCrop, Normalize, ToTensor
from model_side import Net
import torch.nn as nn
import torch.nn.functional as F
net = Net()
## TODO: define the data_transform using transforms.Compose([all tx's, . , .])
# order matters! i.e. rescaling should come before a smaller crop
# testing that you've defined a transform
data_transform = transforms.Compose([ #Rescale(250),
#RandomCrop(224),
Rescale(225),
RandomCrop(224),
#CenterCrop([244,244]),
Normalize(),
ToTensor()
])
assert (data_transform is not None), 'Define a data_transform'
transformed_dataset = FacialKeypointsDataset(
csv_file=
r'C:\Users\Semanti Basu\Documents\OneDrive_2020-02-19\3D Ceaser dataset\Image and point generation\Image and point generation\sideviewpoints.csv',
root_dir=
r'C:\Users\Semanti Basu\Documents\OneDrive_2020-02-19\3D Ceaser dataset\Image and point generation\Image and point generation\ceasar_mat',
transform=data_transform)
# load training data in batches
batch_size = 2
# ## CNN Architecture
#
# Recall that CNN's are defined by a few types of layers:
# * Convolutional layers
# * Maxpooling layers
# * Fully-connected layers
#
#
# In[134]:
# import the usual resources
## TODO: define the data_transform using transforms.Compose([all tx's, . , .])
# order matters! i.e. rescaling should come before a smaller crop
# testing that you've defined a transform
data_transform = transforms.Compose([
Rescale(224),
# RandomCrop(224),
Normalize(),
ToTensor()
])
assert (data_transform is not None), 'Define a data_transform'
# In[ ]:
# In[136]:
# In[137]:
###########load the csv
# order matters! i.e. rescaling should come before a smaller crop
data_transform = transforms.Compose([
Rescale(224),
# RandomCrop(222),
Normalize(),
def train(epochs,
lr=1e-3,
batch_size=32,
seed=23,
kernel_width=5,
kernel_fwhm=3,
verbose=True,
save=True,
load_model=False,
model_path=None):
if load_model:
model.load_state_dict(torch.load(model_path))
torch.cuda.manual_seed_all(seed)
trsfm = transforms.Compose([Rescale(8), PlotLabels(100), ToTensor()])
train = ReadDataset(csv_file=home + "/data/dataset_cae/train_label.csv",
tif_file=home + "/data/dataset_cae/train_data.tif",
transform=trsfm)
val = ReadDataset(csv_file=home + "/data/dataset_cae/val_label.csv",
tif_file=home + "/data/dataset_cae/val_data.tif",
transform=trsfm)
train_loader = torch.utils.data.DataLoader(train,
batch_size=batch_size,
shuffle=True)
val_loader = torch.utils.data.DataLoader(val,
batch_size=batch_size,
shuffle=True)
val_iter = iter(val_loader)
# function to save and close
def saveit():
if save:
os.makedirs(home + "/data/temp/{}".format(timestamp))
file_path = home + '/data/temp/{}/cae_model_{}.pt'.format(
timestamp, timestamp)
torch.save(model.state_dict(), file_path)
print(' -------------------------------')
print("model saved:", file_path)
else:
print(' -------------------------------')
# make a gaussian kernel
def Gauss(size, fwhm=3, center=None):
""" Make a square gaussian kernel.
size is the length of a side of the square
fwhm is full-width-half-maximum, which
can be thought of as an effective radius.
"""
x = np.arange(0, size, 1, float)
y = x[:, np.newaxis]
if center is None:
x0 = y0 = size // 2
else:
x0 = center[0]
y0 = center[1]
return np.exp(-4 * np.log(2) * ((x - x0)**2 + (y - y0)**2) /
fwhm**2) # Gaussian kernel
kernel = Variable(
torch.FloatTensor(
Gauss(kernel_width, kernel_fwhm).reshape(1, 1, kernel_width,
kernel_width)).cuda())
# define the optimizer
criterion = nn.MSELoss()
optimizer = optim.Adam(model.parameters(), lr=lr, weight_decay=1e-5)
print(' epochs: ', epochs, ' batch_size: ', batch_size, ' lr: ', lr,
'seed: ', torch.cuda.initial_seed())
print('Training... ')
print(' | epoch| train_loss| n_batch|')
# Training the ConvNet auto-encoder
try:
for epoch in range(epochs): # loop over the dataset multiple times
t = tqdm(train_loader,
ncols=80,
leave=True,
bar_format='{l_bar}{bar}| {n_fmt}/{total_fmt}')
running_loss = []
for i, data in enumerate(t):
# =======inputs/labels=======
inputs, labels = data['image'], data['positions']
inputs, labels = Variable(inputs).cuda(), Variable(
labels).cuda()
# ==========forward==========
outputs = model(inputs)
loss = criterion(F.conv2d(outputs, kernel, padding=2),
F.conv2d(labels, kernel, padding=2))
# ==========backward==========
optimizer.zero_grad()
loss.backward()
optimizer.step()
# ============================
running_loss.append(loss.data[0])
# tqdm update
t.set_description(' |{:5.0f} |{:12.6f}|{:8.0f}|'.format(
epoch + 1, np.mean(running_loss), i + 1))
t.refresh()
# write to visdom
if verbose:
if epoch == 0:
vis = visdom.Visdom()
label_win = vis.images(utils.make_grid(
labels.cpu().data[:4],
padding=5,
pad_value=1,
normalize=True,
scale_each=True),
opts=dict(title='label images'))
pred_win = vis.images(utils.make_grid(
outputs.cpu().data[:4],
padding=5,
pad_value=1,
normalize=True,
scale_each=True),
opts=dict(title='prediction images'))
loss_win = vis.line(
X=np.array([epoch + 1]),
Y=np.array([np.mean(running_loss)]),
opts=dict(
width=850,
xlabel='<b>epochs</b>',
ylabel='training loss',
markersize=5,
markers=True,
title="<b> Conv_Autoencoder </b> training loss"))
else:
vis.images(utils.make_grid(labels.cpu().data[:4],
padding=5,
pad_value=1,
normalize=True,
scale_each=True),
win=label_win,
opts=dict(title='label images'))
vis.images(utils.make_grid(outputs.cpu().data[:4],
padding=5,
pad_value=1,
normalize=True,
scale_each=True),
win=pred_win,
opts=dict(title='prediction images'))
vis.line(
X=np.array([epoch + 1]),
Y=np.array([np.mean(running_loss)]),
win=loss_win,
update='append',
opts=dict(
width=850,
xlabel='<b>epochs</b>',
ylabel='training loss',
markersize=5,
markers=True,
title="<b> Conv_Autoencoder </b> training loss"))
saveit()
except KeyboardInterrupt:
saveit()
# 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[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)
n = 30
if args['model'] == "NaimishNet":
net = NaimishNet(n)
elif args['model'] == "VggFace":
net = VggFace(n)
elif args['model'] == "Custom":
net = Net2(n)
else:
net = LeNet5(n)
model_name = args['model']
print(net)
device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
# order matters! i.e. rescaling should come before a smaller crop
train_transform = transforms.Compose([Rescale(110),RandomCrop(96),Albu(),Normalize(args["dataset"]),ToTensor()])
test_transform = transforms.Compose([Normalize(args["dataset"]),ToTensor()])
# testing that you've defined a transform
assert(train_transform is not None and test_transform is not None), 'Define a data_transform'
# create the transformed dataset
if args["dataset"] == "Kaggle":
X, y = load_KagggleDataset(split=args['split'],train_30=args['train30'],train_8=args['train8'])
X_test, y_test = X[:300], y[:300]
X_train, y_train = X[300:], y[300:]
transformed_dataset = KagggleDataset(X_train, y_train, train_transform)
test_dataset = KagggleDataset(X_test, y_test, test_transform)
sub, div = 48., 48.
else:
def main():
#------------------------------------------------------------------------------------------------------------------
# Hyperparameters
hyp_epochs = 5
hyp_batch_size = 20
#hyp_optim = "SGD"
hyp_optim = "Adam"
#hyp_net = Net1()
hyp_net = Net2()
print("Hyperparameters")
print("--------------")
print("Epochs = ", hyp_epochs)
print("Batch Size = ", hyp_batch_size)
print("Optimizer = ", hyp_optim)
print("--------------")
## TODO: Define the Net in models.py
net = hyp_net
print(net)
## 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(256), RandomCrop(224),
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='../files/training_frames_keypoints.csv',
root_dir='../files/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())
# load training data in batches
batch_size = hyp_batch_size
train_loader = DataLoader(transformed_dataset,
batch_size=batch_size,
shuffle=True,
num_workers=0)
# load in the test data, using the dataset class
# AND apply the data_transform you defined above
# create the test dataset
test_dataset = FacialKeypointsDataset(
csv_file='../files/test_frames_keypoints.csv',
root_dir='../files/test/',
transform=data_transform)
# load test data in batches
batch_size = hyp_batch_size
test_loader = DataLoader(test_dataset,
batch_size=batch_size,
shuffle=True,
num_workers=0)
# test the model on a batch of test images
# call the above function
# returns: test images, test predicted keypoints, test ground truth keypoints
test_images, test_outputs, gt_pts = net_sample_output(test_loader, net)
# 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())
# visualize the output
# by default this shows a batch of 10 images
# call it
_visualise = False
if _visualise == True:
visualize_output(test_images, test_outputs, gt_pts)
## TODO: Define the loss and optimization
import torch.optim as optim
criterion = nn.MSELoss()
hyp_optimizer = None
if hyp_optim == "Adam":
hyp_optimizer = optim.Adam(net.parameters(), lr=0.001)
if hyp_optim == "SGD":
hyp_optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)
optimizer = hyp_optimizer
# train your network
n_epochs = hyp_epochs # start small, and increase when you've decided on your model structure and hyperparams
# this is a Workspaces-specific context manager to keep the connection
# alive while training your model, not part of pytorch
train_net(n_epochs, train_loader, net, criterion, optimizer)
# get a sample of test data again
test_images, test_outputs, gt_pts = net_sample_output(test_loader, net)
print(test_images.data.size())
print(test_outputs.data.size())
print(gt_pts.size())
## TODO: change the name to something uniqe for each new model
model_dir = '../saved_models/'
model_name = 'keypoints_model_2.pt'
# after training, save your model parameters in the dir 'saved_models'
torch.save(net.state_dict(), model_dir + model_name)
# --------------------------------------------------------------------
# To run the following code after retreiving an existing model,
# you can do so in the resume.py file
# --------------------------------------------------------------------
# Get the weights in the first conv layer, "conv1"
# if necessary, change this to reflect the name of your first conv layer
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')
##TODO: load in and display any image from the transformed test dataset
i = 1
show_image(test_images, w, i)
)
[IN][2]:
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
crop = RandomCrop(224)
scale = Rescale(224)
Composed = transforms.Compose([Rescale(224),
RandomCrop(224)])
data_transform = Composed
# testing that you've defined a transform
assert(data_transform is not None), 'Define a data_transform'
[IN][3]:
# create the transformed dataset
transformed_dataset = FacialKeypointsDataset(csv_file='/data/training_frames_keypoints.csv',
root_dir='/data/training/',
transform=data_transform)
import torch
from torch.autograd import Variable
from torch.utils.data import Dataset, DataLoader
from torchvision import transforms, utils
from data_load import FacialKeypointsDataset
from data_load import Rescale, RandomCrop, Normalize, ToTensor
kwargs = {'num_workers': 4} if torch.cuda.is_available() else {}
# define the data_transform
data_transform = transforms.Compose(
[Rescale((96, 96)), Normalize(),
ToTensor()])
# create the transformed dataset
transformed_dataset = FacialKeypointsDataset(
csv_file='./data/training_frames_keypoints.csv',
root_dir='./data/training/',
transform=data_transform)
# load training data in batches
batch_size = 128
train_loader = DataLoader(transformed_dataset,
batch_size=batch_size,
shuffle=True,
**kwargs)
# create the test dataset
test_dataset = FacialKeypointsDataset(
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')
model = arch()
assert args.optimizer in optimizers, f"Error: Optimizer {args.optimizer} not found."
opti = getattr(optim, args.optimizer)
optimizer = opti(model.parameters(), lr=args.lr)
assert args.loss_func in loss_funcs, f"Error: Network architecture {args.loss_func} not found."
criterion = loss_funcs[args.loss_func]
# hard-coded
scheduler = optim.lr_scheduler.StepLR(optimizer, step_size=30, gamma=0.1)
# Define a transform
data_transform = transforms.Compose([
Rescale((224,224)),
#RandomCrop(),
Normalize(),
ToTensor(),
])
# create the transformed dataset
train_val_dataset = FacialKeypointsDataset(csv_file='data/training_frames_keypoints.csv',
root_dir='data/training/',
transform=data_transform)
# for faster experimentation select only a subset of images
if args.subset_size > 0:
train_val_dataset = Subset(train_val_dataset, range(args.subset_size))
print('Number of images: ', len(train_val_dataset))
print("Downloading data...")
r = requests.get(URL + DATA_FILE, stream=True)
assert (r.ok), 'Input data files could not be downloaded from URL'
with open(str(Path(DOWNLOAD_PATH, DATA_FILE)), 'wb+') as f:
for chunk in r.iter_content(chunk_size=1024):
if chunk: f.write(chunk)
z = zipfile.ZipFile(str(Path(DOWNLOAD_PATH, DATA_FILE)))
z.extractall(DOWNLOAD_PATH)
print("Downloading and extraction complete.")
### PREPARE DATA ###
# order matters! i.e. rescaling should come before a smaller crop
data_transform = transforms.Compose(
[Rescale(100), RandomCrop(96),
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))
# create the test dataset
test_dataset = FacialKeypointsDataset(
csv_file='./data/test_frames_keypoints.csv',
root_dir='./data/test/',
transform=data_transform)
args = parser.parse_args()
args.cuda = not args.no_cuda and torch.cuda.is_available()
torch.manual_seed(args.seed)
if args.cuda:
torch.cuda.manual_seed(args.seed)
######################################################################
# Data
# ====================
from data_load import ChicagoFaceDatabase, InstagramDatabase, ToTensor, Rescale, CropSquare
CFD_train_dataset = ChicagoFaceDatabase(
root_dir='../data/ChicagoFaceDatabase/',
transform=transforms.Compose([CropSquare(),
Rescale(256),
ToTensor()]),
train=True)
CFD_train_loader = torch.utils.data.DataLoader(dataset=CFD_train_dataset,
batch_size=args.batch_size,
shuffle=True)
CFD_test_dataset = ChicagoFaceDatabase(
root_dir='../data/ChicagoFaceDatabase/',
transform=transforms.Compose([CropSquare(),
Rescale(256),
ToTensor()]),
train=False)
CFD_test_loader = torch.utils.data.DataLoader(dataset=CFD_test_dataset,
batch_size=args.batch_size,
shuffle=True)
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)
from torch.utils.data import Dataset, DataLoader
from torchvision import transforms, utils
from data_load import FacialKeypointsDataset
from data_load import Rescale, RandomCrop, Normalize, ToTensor
import torch.optim as optim
from models import *
# instantiate the model
net = AlexNet()
print(net)
# define the data transform using transfroms.Compose([..])
# Note the order is matter
data_tranform = transforms.Compose(
[Rescale((250, 250)),
RandomCrop((227, 227)),
Normalize(),
ToTensor()])
# Create the transformed dataset
transformed_dataset = FacialKeypointsDataset(
csv_file='data/training_frames_keypoints.csv',
root_dir='data/training/',
transform=data_tranform)
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]
from data_load import FacialKeypointsDataset
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
if is_debug:
print('fc1.out_shape:', x.shape)
# a modified x, having gone through all the layers of your model, should be returned
return x
if __name__ == '__main__':
import os
os.chdir('/Users/rawk/Projects/Project Zero/MLND-projects/cv-project0-facial-keypoints/')
from data_load import FacialKeypointsDataset
from data_load import Rescale, RandomCrop, Normalize, ToTensor
from torch.utils.data import Dataset, DataLoader
from torchvision import transforms, utils
data_transform = transforms.Compose([Rescale((250, 250)), RandomCrop((224, 224)), Normalize(), ToTensor()])
transformed_dataset = FacialKeypointsDataset(csv_file='./data/training_frames_keypoints.csv',
root_dir='./data/training/',
transform=data_transform)
batch_size = 2
data_loader = DataLoader(transformed_dataset,
batch_size=batch_size,
shuffle=True,
num_workers=4)
for i, sample in enumerate(data_loader):
images = sample['image']
images = images.type(torch.FloatTensor)
net = Net()
from options import options
options = options()
opts = options.parse()
from models import Net
net = Net(1).to(device)
from torch.utils.data import DataLoader
from torchvision import transforms
from data_load import FacialKeypointsDataset
from data_load import Rescale, RandomCrop, Normalize, ToTensor, RotateScale, HorizontalFlip, VerticalFlip
data_transform = transforms.Compose([RotateScale(60),
Rescale((256, 256)),
RandomCrop((224, 224)),
Normalize(),
ToTensor()])
batch_size = opts.batch
transformed_dataset = FacialKeypointsDataset(csv_file='/data/training_frames_keypoints.csv', root_dir='/data/training/', transform=data_transform)
train_loader = DataLoader(transformed_dataset, batch_size=batch_size, 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=batch_size, shuffle=True, num_workers=4)
import torch.optim as optim
criterion = opts.criterion
optimizer = optim.Adam(net.parameters(), lr=opts.lr)
import numpy as np
from train import train_net
if __name__ == "__main__":
torch.cuda.empty_cache()
offline = True
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
n_epochs = 20
print("AI Running on", device)
net = FCN().apply(initialize_weights_advance_).to(device)
print(net)
data_transform = transforms.Compose(
[Rescale(250), RandomCrop(224),
Normalize(), ToTensor()])
transformed_dataset = FacialKeypointsDataset(
csv_file='data/training_frames_keypoints.csv',
root_dir='data/training/',
transform=data_transform)
# load training data in batches
batch_size = 128
train_loader = DataLoader(transformed_dataset,
batch_size=batch_size,
shuffle=True,
num_workers=4)
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):
