def binary_output(dataloader):
embedding_net = EmbeddingResnet()
net = TripletNet(embedding_net)
#net = SiameseNet(embedding_net)
#net = ClassificationNet(embedding_net, 100)
net.load_state_dict(torch.load('./model/%s' % args.pretrained))
use_cuda = torch.cuda.is_available()
if use_cuda:
net.cuda()
full_batch_output = torch.cuda.FloatTensor()
full_batch_label = torch.cuda.LongTensor()
net.eval()
for batch_idx, (inputs, targets) in enumerate(dataloader):
if use_cuda:
inputs, targets = inputs.cuda(), targets.cuda()
inputs, targets = Variable(inputs, volatile=True), Variable(targets)
outputs = net.get_embedding(inputs).data
full_batch_output = torch.cat((full_batch_output, outputs.data), 0)
full_batch_label = torch.cat((full_batch_label, targets.data), 0)
return torch.round(full_batch_output), full_batch_label
def main():
import torch
from torch.optim import lr_scheduler
import torch.optim as optim
from torch.autograd import Variable
from trainer import fit
import numpy as np
cuda = torch.cuda.is_available()
# Training settings
parser = argparse.ArgumentParser(description='PyTorch MNIST Example')
parser.add_argument('--batch-size', type=int, default=100, metavar='N',
help='input batch size for training (default: 64)')
parser.add_argument('--test-batch-size', type=int, default=100, metavar='N',
help='input batch size for testing (default: 1000)')
parser.add_argument('--epochs', type=int, default=100, metavar='N',
help='number of epochs to train (default: 10)')
parser.add_argument('--lr', type=float, default=0.001, metavar='LR',
help='learning rate (default: 0.01)')
parser.add_argument('--momentum', type=float, default=0.5, metavar='M',
help='SGD momentum (default: 0.5)')
parser.add_argument('--no-cuda', action='store_true', default=False,
help='disables CUDA training')
parser.add_argument('--seed', type=int, default=1, metavar='S',
help='random seed (default: 1)')
parser.add_argument('--log-interval', type=int, default=10, metavar='N',
help='how many batches to wait before logging training status')
parser.add_argument('--save-model', action='store_true', default=True,
help='For Saving the current Model')
args = parser.parse_args()
use_cuda = not args.no_cuda and torch.cuda.is_available()
torch.manual_seed(args.seed)
np.random.seed(args.seed)
torch.backends.cudnn.deterministic = True
torch.backends.cudnn.benchmark = False
device = torch.device("cuda" if use_cuda else "cpu")
kwargs = {'num_workers': 1, 'pin_memory': True} if use_cuda else {}
from datetime import datetime
import os
loging = False
ismultitask = False
loso = False
if (args.save_model):
model_save_path = 'model/triplet/'
if not os.path.isdir(model_save_path):
os.makedirs(model_save_path)
if loging:
fname = model_save_path + datetime.today().strftime("%m_%d_%H_%M") + ".txt"
f = open(fname, 'w')
x_data, y_data = load_smt()
y_subj = np.zeros([108, 200])
for i in range(108):
y_subj[i, :] = i * 2
y_subj = y_data.reshape(108, 200) + y_subj
y_subj = y_subj.reshape(21600)
# nonbciilli = np.s_[0,1,2,4,5,8,16,17,18,20,21,27,28,29,30,32,35,36,38,42,43,44,51]
valtype = 'sess'
if valtype == 'loso':
pass
elif valtype == 'sess':
from networks import EmbeddingDeep4CNN, TripletNet, FineShallowCNN, EmbeddingDeepCNN, QuintupletNet, EmbeddingShallowCNN
from losses import TripletLoss_dev2
# make model for metric learning
margin = 1
embedding_net = EmbeddingShallowCNN()
# clf_net = nn.Sequential(EmbeddingDeep4CNN(),nn.Linear(1000,2),nn.Dropout(p=1),nn.LogSoftmax(dim=1))
print(embedding_net)
model = TripletNet(embedding_net)
if cuda:
model.cuda()
loss_fn = TripletLoss_dev2(margin).cuda()
n_epochs =1
log_interval = 10
load_model_path = None#'C:\\Users\dk\PycharmProjects\giga_cnn\구모델\\clf_83_8.pt'#'clf_29.pt' #'triplet_mg26.pt'#'clf_triplet2_5.pt' #'triplet_31.pt'
model.fc = nn.Sequential(nn.Linear(1000, 2), nn.Dropout(p=0.5))
if load_model_path is not None:
embedding_net.load_state_dict(torch.load(load_model_path))
# For classification
dataset_train = GigaDataset(x=x_data, y=y_data, valtype=valtype, istrain=True, sess=1)
train_loader = torch.utils.data.DataLoader(dataset_train, batch_size=args.batch_size, shuffle=True,
**kwargs)
dataset_test = GigaDataset(x=x_data, y=y_data, valtype=valtype, istrain=False, sess=2, subj=-1)
test_loader = torch.utils.data.DataLoader(dataset_test, batch_size=args.batch_size, shuffle=False,
**kwargs)
#make model for classification
newmodel = nn.Sequential(model.embedding_net,
nn.Linear(1000, 2),
nn.Dropout(p=0.5),
nn.LogSoftmax(dim=1)
).to(device)
print(newmodel)
newmodel.to(device)
optimizer = optim.SGD(newmodel.parameters(), lr=0.001, momentum=0.9)
# optimizer = optim.Adam(newmodel.parameters())
for epoch in range(0):
train(args, newmodel, device, train_loader, optimizer, epoch)
j_loss, j_score = eval(args, newmodel, device, test_loader)
# For embedding
triplet_dataset_train = TripletGiga(x=x_data, y=y_data,valtype=valtype, istrain=True, sess=1)
triplet_train_loader = torch.utils.data.DataLoader(triplet_dataset_train, batch_size=args.batch_size, shuffle=True, **kwargs)
triplet_dataset_test = TripletGiga(x=x_data, y=y_data,valtype=valtype, istrain=False, sess=2, subj=-1)
triplet_test_loader = torch.utils.data.DataLoader(triplet_dataset_test, batch_size=args.batch_size, shuffle=False, **kwargs)
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.9)
scheduler = lr_scheduler.StepLR(optimizer, 8, gamma=1, last_epoch=-1)
from sklearn.pipeline import Pipeline
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
from sklearn.model_selection import ShuffleSplit, cross_val_score
lda = LinearDiscriminantAnalysis()
Testmodel = nn.Sequential(model.embedding_net,
model.fc,
nn.LogSoftmax(dim=1)).to(device)
# tempEmbeddingNet = nn.Sequential(model.embedding_net,
# nn.Linear(1000,1000),
# nn.Sigmoid())
# model = TripletNet(embedding_net)
print(model)
for temp in range(1, 30): # 10epoch마다 세이브
fit(triplet_train_loader, triplet_test_loader, model, loss_fn, optimizer, scheduler, n_epochs, cuda,
log_interval)
j_loss, j_score = eval(args, Testmodel, device, train_loader)
j_loss, j_score = eval(args, Testmodel, device, test_loader)
torch.save(model.state_dict(), 'clf_' + str(temp) + '.pt')
torch.save(model.state_dict(), 'shallowDG_150epoch_82acc' + str(temp) + '.pt')
#for visualization
dataset_train_subj = GigaDataset(x=x_data, y=y_subj, valtype=valtype, istrain=True, sess=1)
train_loader_subj = torch.utils.data.DataLoader(dataset_train_subj, batch_size=args.batch_size, shuffle=True,
**kwargs)
dataset_test_subj = GigaDataset(x=x_data, y=y_subj, valtype=valtype, istrain=False, sess=2, subj=-1)
test_loader_subj = torch.utils.data.DataLoader(dataset_test_subj, batch_size=args.batch_size, shuffle=False,
**kwargs)
# train_embeddings_tl, train_labels_tl = extract_features(train_loader_subj.dataset, model.embedding_net.convnet,0,100)
# val_embeddings_tl, val_labels_tl = extract_embeddings(test_loader_subj, model.embedding_net, 1000)
train_embeddings_tl, train_labels_tl = extract_embeddings(train_loader_subj, model.embedding_net,1000)
val_embeddings_tl, val_labels_tl = extract_embeddings(test_loader_subj, model.embedding_net,1000)
#
# train_embeddings_tl, train_labels_tl = extract_embeddings(train_loader_subj, model.embedding_net.convnet[0], 1000)
# val_embeddings_tl, val_labels_tl = extract_embeddings(test_loader_subj, model.embedding_net, 1000)
# = train_labels_tl-train_labels_tl%2
# from torchvision import datasets, models, transforms
# temp = model.embedding_net.children()
# newmodel = torch.nn.Sequential(*(list(model.embedding_net.children())[:]))
# for param in model.embedding_net.parameters():
# param.requires_grad = True
#newembedding_net = torch.nn.Sequential(*(list(model.embedding_net.children())[:]))
#
from sklearn.manifold import TSNE
tsne = TSNE(n_components=2,perplexity=30)
#features = np.concatenate([train_embeddings_tl,val_embeddings_tl])
#val_labels_tl = val_labels_tl+2
#labels = np.concatenate([train_labels_tl,val_labels_tl])
train_tsne = tsne.fit_transform(train_embeddings_tl[0:2000])
# plot_embeddings(train_tsne,train_labels_tl[0:1000])
plot_features(train_tsne,train_labels_tl[0:2000])
plot_features3d(train_tsne,train_labels_tl[0:1000]%2)
val_tsne = tsne.fit_transform(val_embeddings_tl)
plot_embeddings(val_tsne, (val_labels_tl-108)-(val_labels_tl-108)%2)
for param in model.embedding_net.parameters():
param.requires_grad = True
#embedding_net2 = EmbeddingDeep4CNN()
newmodel = nn.Sequential(model.embedding_net,
nn.Linear(1000, 2),
nn.Dropout(p=0.5),
nn.LogSoftmax(dim=1),
).to(device)
print(newmodel)
#newmodel.fc_lr = nn.Linear(1000,2)
newmodel.to(device)
optimizer = optim.SGD(newmodel.parameters(), lr=0.001, momentum=0.9)
#optimizer = optim.Adam(newmodel.parameters())
for epoch in range(1, 100):
train(args, newmodel, device, train_loader, optimizer, epoch)
j_loss, j_score = eval(args, newmodel, device, test_loader)
if args.save_model:
torch.save(newmodel.state_dict(),'clf_83_8.pt')
newmodel.load_state_dict(torch.load(load_model_path))
# Visualize feature maps
activation = {}
def get_activation(name):
def hook(model, input, output):
activation[name] = output.detach()
return hook
handle = model.embedding_net.convnet[0].register_forward_hook(get_activation('fc'))
handle.remove()
model.embedding_net.convnet[0]._forward_hooks.clear()
train_loader.dataset
with torch.no_grad():
model.eval()
# num_ftrs = model.embedding_net.fc.out_features
embeddings = np.zeros((len(train_loader.dataset), num_ftrs))
labels = np.zeros(len(train_loader.dataset))
k = 0
for images, target in train_loader:
if cuda:
images = images.cuda()
embeddings[k:k + len(images)] = model.get_embedding(images).data.cpu().numpy()
labels[k:k + len(images)] = target.numpy()
k += len(images)
features = SaveFeatures(model.embedding_net.convnet[0])
temp = features.features.data.cpu().numpy()
del features.features
torch.cuda.empty_cache()
for images, target in train_loader:
if cuda:
images = images.cuda()
output = model.embedding_net(images)
activation = []
def get_activation():
def hook(model, input, output):
activation.append(output)
print(output)
return hook
act = activation['conv1'].squeeze()
fig, axarr = plt.subplots(act.size(0))
for idx in range(act.size(0)):
axarr[idx].imshow(act[idx])
actmap = []
def printnorm(self, input, output):
# input is a tuple of packed inputs
# output is a Tensor. output.data is the Tensor we are interested
print('Inside ' + self.__class__.__name__ + ' forward')
print('')
print('input: ', type(input))
print('input[0]: ', type(input[0]))
print('output: ', type(output))
print('')
print('input size:', input[0].size())
print('output size:', output.data.size())
print('output norm:', output.data.norm())
return output.data
model.embedding_net.convnet[0].register_forward_hook(printnorm)
out = model(input)
fig, axarr = plt.subplots(10)
for idx in range(10):
axarr[idx].imshow(temp[idx,1,:,:])
log_interval = 100
patience = 4
fit_triplet(triplet_train_loader, triplet_test_loader, model, loss_fn,
optimizer, scheduler, patience, n_epoch, cuda, log_interval)
torch.save(model, "./data/TripletNetwork.pt")
model = torch.load("./data/TripletNetwork.pt")
#below for unlabeled data
TEST_CSV = "../../Data/data/originalVectors"
with open(TEST_CSV) as csv_file:
with open('../../Data/data/reducedVectors-tripletNet', 'w') as writeFile:
csv_reader = csv.reader(csv_file, delimiter=' ')
for row in csv_reader:
vec = [float(k) for k in row]
vec = torch.FloatTensor(vec)
writeFile.write(
' '.join(map(str,
model.get_embedding(vec).data.numpy())) + "\n")
writeFile.close()
#below for labeled data
# TEST_CSV = "../../Data/data/originalVectors-MNIST"
# with open(TEST_CSV) as csv_file:
# with open('../../Data/data/reducedVectors-tripletNet-MNIST', 'w') as writeFile:
# csv_reader = csv.reader(csv_file, delimiter=' ')
# for row in csv_reader:
# vec = [float(k) for k in row]
# vec = torch.FloatTensor(vec)
# writeFile.write(' '.join(map(str, model.get_embedding(vec).data.numpy())) + "\n")
# writeFile.close()
