class MLP_Regression():
def __init__(self, label, parameters):
super().__init__()
self.writer = SummaryWriter(comment=f"_{label}_training")
self.label = label
self.lr = parameters['lr']
self.hidden_units = parameters['hidden_units']
self.mode = parameters['mode']
self.batch_size = parameters['batch_size']
self.num_batches = parameters['num_batches']
self.x_shape = parameters['x_shape']
self.y_shape = parameters['y_shape']
self.save_model_path = f'{parameters["save_dir"]}/{label}_model.pt'
self.best_loss = np.inf
self.init_net(parameters)
def init_net(self, parameters):
if not os.path.exists(parameters["save_dir"]):
os.makedirs(parameters["save_dir"])
model_params = {
'input_shape': self.x_shape,
'classes': self.y_shape,
'batch_size': self.batch_size,
'hidden_units': self.hidden_units,
'mode': self.mode
}
self.net = MLP(model_params).to(DEVICE)
self.optimiser = torch.optim.Adam(self.net.parameters(), lr=self.lr)
self.scheduler = torch.optim.lr_scheduler.StepLR(self.optimiser,
step_size=5000,
gamma=0.5)
print("MLP Parameters: ")
print(
f'batch size: {self.batch_size}, input shape: {model_params["input_shape"]}, hidden units: {model_params["hidden_units"]}, output shape: {model_params["classes"]}, lr: {self.lr}'
)
def train_step(self, train_data):
self.net.train()
for _, (x, y) in enumerate(train_data):
x, y = x.to(DEVICE), y.to(DEVICE)
self.net.zero_grad()
self.loss_info = torch.nn.functional.mse_loss(self.net(x),
y,
reduction='sum')
self.loss_info.backward()
self.optimiser.step()
self.epoch_loss = self.loss_info.item()
def evaluate(self, x_test):
self.net.eval()
with torch.no_grad():
y_test = self.net(x_test.to(DEVICE)).detach().cpu().numpy()
return y_test
def log_progress(self, step):
write_loss(self.writer, self.loss_info, step)
def load_mlp_class_model(saved_model):
'''Load model weights from path saved_model.'''
config = ClassConfig
model_params = {
'input_shape': config.x_shape,
'classes': config.classes,
'batch_size': config.batch_size,
'hidden_units': config.hidden_units,
'mode': config.mode,
'dropout': False
}
model = MLP(model_params)
model.load_state_dict(torch.load(saved_model))
return model.eval()
nc = int(opt.nc)
imageSize = int(opt.imageSize)
nz = int(opt.nz)
nblk = int(opt.nblk)
model_netG = MLP(input_dim=nc * imageSize * imageSize,
output_dim=nc * imageSize * imageSize,
dim=nz,
n_blk=nblk,
norm='none',
activ='relu').to(device)
model_netG.load_state_dict(torch.load(opt.netG, map_location=device))
print_and_write_log(test_log_file, 'netG:')
print_and_write_log(test_log_file, str(model_netG))
if opt.eval:
model_netG.eval()
for i, data in enumerate(tqdm(dataloader), 0):
img, img_path = data
img_name = os.path.splitext(os.path.basename(img_path[0]))[0] + '.png'
if i >= opt.num_test:
break
real = img.to(device)
with torch.no_grad():
recon = model_netG(real)
recon_img = tensor2im(recon)
if opt.show_input:
real_img = tensor2im(real)
real_recon_img = np.concatenate([real_img, recon_img], 1)
real_recon_img_pil = Image.fromarray(real_recon_img)
real_recon_img_pil.save(os.path.join(opt.resfwi, img_name))
class MLP_Classification():
def __init__(self, label, parameters):
super().__init__()
self.writer = SummaryWriter(comment=f"_{label}_training")
self.label = label
self.lr = parameters['lr']
self.hidden_units = parameters['hidden_units']
self.mode = parameters['mode']
self.batch_size = parameters['batch_size']
self.num_batches = parameters['num_batches']
self.x_shape = parameters['x_shape']
self.classes = parameters['classes']
self.save_model_path = f'{parameters["save_dir"]}/{label}_model.pt'
self.best_acc = 0.
self.dropout = parameters['dropout']
self.init_net(parameters)
def init_net(self, parameters):
if not os.path.exists(parameters["save_dir"]):
os.makedirs(parameters["save_dir"])
model_params = {
'input_shape': self.x_shape,
'classes': self.classes,
'batch_size': self.batch_size,
'hidden_units': self.hidden_units,
'mode': self.mode,
'dropout': self.dropout,
}
if self.dropout:
self.net = MLP_Dropout(model_params).to(DEVICE)
print('MLP Dropout Parameters: ')
print(f'batch size: {self.batch_size}, input shape: {model_params["input_shape"]}, hidden units: {model_params["hidden_units"]}, output shape: {model_params["classes"]}, lr: {self.lr}')
else:
self.net = MLP(model_params).to(DEVICE)
print('MLP Parameters: ')
print(f'batch size: {self.batch_size}, input shape: {model_params["input_shape"]}, hidden units: {model_params["hidden_units"]}, output shape: {model_params["classes"]}, lr: {self.lr}')
self.optimiser = torch.optim.SGD(self.net.parameters(), lr=self.lr)
self.scheduler = torch.optim.lr_scheduler.StepLR(self.optimiser, step_size=100, gamma=0.5)
def train_step(self, train_data):
self.net.train()
for _, (x, y) in enumerate(tqdm(train_data)):
x, y = x.to(DEVICE), y.to(DEVICE)
self.net.zero_grad()
self.loss_info = torch.nn.functional.cross_entropy(self.net(x), y, reduction='sum')
self.loss_info.backward()
self.optimiser.step()
def predict(self, X):
probs = torch.nn.Softmax(dim=1)(self.net(X))
preds = torch.argmax(probs, dim=1)
return preds, probs
def evaluate(self, test_loader):
self.net.eval()
print('Evaluating on validation data')
correct = 0
total = 0
with torch.no_grad():
for data in tqdm(test_loader):
X, y = data
X, y = X.to(DEVICE), y.to(DEVICE)
preds, _ = self.predict(X)
total += self.batch_size
correct += (preds == y).sum().item()
self.acc = correct / total
print(f'{self.label} validation accuracy: {self.acc}')
def log_progress(self, step):
write_loss(self.writer, self.loss_info, step)
write_acc(self.writer, self.acc, step)
def main(args):
seed = 999
random.seed(seed)
np.random.seed(seed)
torch.manual_seed(seed)
torch.backends.cudnn.deterministic = True
sites = ['NYU','UCLA','UM','USM']
models_cross = []
for file in sites:
if file != args.site:
model = MLP(6105,8,2).to(device)
model.load_state_dict(torch.load(os.path.join('./model/cross_overlap',file+'.pth')))
models_cross.append(model)
model_single = MLP(6105,8,2).to(device)
model_single.load_state_dict(torch.load(os.path.join('./model/single_overlap', args.site, str(args.split) + '.pth')))
data1 = dd.io.load(os.path.join(args.vec_dir,'NYU_correlation_matrix.h5'))
data2 = dd.io.load(os.path.join(args.vec_dir,'UM_correlation_matrix.h5'))
data3 = dd.io.load(os.path.join(args.vec_dir,'USM_correlation_matrix.h5'))
data4 = dd.io.load(os.path.join(args.vec_dir,'UCLA_correlation_matrix.h5'))
x1 = torch.from_numpy(data1['data']).float()
y1 = torch.from_numpy(data1['label']).long()
x2 = torch.from_numpy(data2['data']).float()
y2 = torch.from_numpy(data2['label']).long()
x3 = torch.from_numpy(data3['data']).float()
y3 = torch.from_numpy(data3['label']).long()
x4 = torch.from_numpy(data4['data']).float()
y4 = torch.from_numpy(data4['label']).long()
idNYU = dd.io.load('./idx/NYU_sub_overlap.h5')
idUM = dd.io.load('./idx/UM_sub_overlap.h5')
idUSM = dd.io.load('./idx/USM_sub_overlap.h5')
idUCLA = dd.io.load('./idx/UCLA_sub_overlap.h5')
if args.split == 0:
tr1 = idNYU['1'] + idNYU['2'] + idNYU['3'] + idNYU['4']
tr2 = idUM['1'] + idUM['2'] + idUM['3'] + idUM['4']
tr3 = idUSM['1'] + idUSM['2'] + idUSM['3'] + idUSM['4']
tr4 = idUCLA['1'] + idUCLA['2'] + idUCLA['3'] + idUCLA['4']
te1 = idNYU['0']
te2 = idUM['0']
te3 = idUSM['0']
te4 = idUCLA['0']
elif args.split == 1:
tr1 = idNYU['0'] + idNYU['2'] + idNYU['3'] + idNYU['4']
tr2 = idUM['0'] + idUM['2'] + idUM['3'] + idUM['4']
tr3 = idUSM['0'] + idUSM['2'] + idUSM['3'] + idUSM['4']
tr4 = idUCLA['0'] + idUCLA['2'] + idUCLA['3'] + idUCLA['4']
te1 = idNYU['1']
te2 = idUM['1']
te3 = idUSM['1']
te4 = idUCLA['1']
elif args.split == 2:
tr1 = idNYU['0'] + idNYU['1'] + idNYU['3'] + idNYU['4']
tr2 = idUM['0'] + idUM['1'] + idUM['3'] + idUM['4']
tr3 = idUSM['0'] + idUSM['1'] + idUSM['3'] + idUSM['4']
tr4 = idUCLA['0'] + idUCLA['1'] + idUCLA['3'] + idUCLA['4']
te1 = idNYU['2']
te2 = idUM['2']
te3 = idUSM['2']
te4 = idUCLA['2']
elif args.split == 3:
tr1 = idNYU['0'] + idNYU['1'] + idNYU['2'] + idNYU['4']
tr2 = idUM['0'] + idUM['1'] + idUM['2'] + idUM['4']
tr3 = idUSM['0'] + idUSM['1'] + idUSM['2'] + idUSM['4']
tr4 = idUCLA['0'] + idUCLA['1'] + idUCLA['2'] + idUCLA['4']
te1 = idNYU['3']
te2 = idUM['3']
te3 = idUSM['3']
te4 = idUCLA['3']
elif args.split == 4:
tr1 = idNYU['0'] + idNYU['1'] + idNYU['2'] + idNYU['3']
tr2 = idUM['0'] + idUM['1'] + idUM['2'] + idUM['3']
tr3 = idUSM['0'] + idUSM['1'] + idUSM['2'] + idUSM['3']
tr4 = idUCLA['0'] + idUCLA['1'] + idUCLA['2'] + idUCLA['3']
te1 = idNYU['4']
te2 = idUM['4']
te3 = idUSM['4']
te4 = idUCLA['4']
x1_train = x1[tr1]
y1_train = y1[tr1]
x2_train = x2[tr2]
y2_train = y2[tr2]
x3_train = x3[tr3]
y3_train = y3[tr3]
x4_train = x4[tr4]
y4_train = y4[tr4]
x1_test = x1[te1]
y1_test = y1[te1]
x2_test = x2[te2]
y2_test = y2[te2]
x3_test = x3[te3]
y3_test = y3[te3]
x4_test = x4[te4]
y4_test = y4[te4]
mean = x1_train.mean(0, keepdim=True)
dev = x1_train.std(0, keepdim=True)
x1_test = (x1_test - mean) / dev
mean = x2_train.mean(0, keepdim=True)
dev = x2_train.std(0, keepdim=True)
x2_test = (x2_test - mean) / dev
mean = x3_train.mean(0, keepdim=True)
dev = x3_train.std(0, keepdim=True)
x3_test = (x3_test - mean) / dev
mean = x4_train.mean(0, keepdim=True)
dev = x4_train.std(0, keepdim=True)
x4_test = (x4_test - mean) / dev
test1 = TensorDataset(x1_test, y1_test)
test2 = TensorDataset(x2_test, y2_test)
test3 = TensorDataset(x3_test, y3_test)
test4 = TensorDataset(x4_test, y4_test)
if args.site == 'NYU':
test = test1
elif args.site == 'UM':
test = test2
elif args.site == 'USM':
test = test3
elif args.site == 'UCLA':
test = test4
te_data = test.tensors[0].to(device)
te_outputs = []
targets = test.tensors[1].numpy()
preds =[]
#cross model
for model in models_cross:
model.eval()
te_output = model(te_data)
te_outputs.append(torch.exp(te_output))
# single_model
model_single.eval()
te_output = model_single(te_data)
te_outputs.append(torch.exp(te_output))
outputtorch = torch.stack(te_outputs,dim=0)
output_mean = torch.mean(outputtorch,dim=0)
preds = output_mean.data.max(1)[1].detach().cpu().numpy()
if not os.path.exists(args.res_dir):
os.mkdir(args.res_dir)
dd.io.save(os.path.join(args.res_dir, args.site+ '_' + str(args.split) + '.h5'),
{'preds': preds, 'targets': targets})
class VanillaAE(nn.Module):
def __init__(self, opt):
super(VanillaAE, self).__init__()
self.opt = opt
self.device = torch.device("cuda:0" if not opt.no_cuda else "cpu")
nc = int(opt.nc)
imageSize = int(opt.imageSize)
nz = int(opt.nz)
nblk = int(opt.nblk)
# generator
self.netG = MLP(input_dim=nc * imageSize * imageSize,
output_dim=nc * imageSize * imageSize,
dim=nz,
n_blk=nblk,
norm='none',
activ='relu').to(self.device)
weights_init(self.netG)
if opt.netG != '':
self.netG.load_state_dict(
torch.load(opt.netG, map_location=self.device))
print_and_write_log(opt.train_log_file, 'netG:')
print_and_write_log(opt.train_log_file, str(self.netG))
# losses
self.criterion = nn.MSELoss()
# define focal frequency loss
self.criterion_freq = FFL(loss_weight=opt.ffl_w,
alpha=opt.alpha,
patch_factor=opt.patch_factor,
ave_spectrum=opt.ave_spectrum,
log_matrix=opt.log_matrix,
batch_matrix=opt.batch_matrix).to(
self.device)
# misc
self.to(self.device)
# optimizer
self.optimizerG = optim.Adam(self.netG.parameters(),
lr=opt.lr,
betas=(opt.beta1, opt.beta2))
def forward(self):
pass
def gen_update(self, data, epoch, matrix=None):
self.netG.zero_grad()
real = data.to(self.device)
if matrix is not None:
matrix = matrix.to(self.device)
recon = self.netG(real)
# apply pixel-level loss
errG_pix = self.criterion(recon, real) * self.opt.mse_w
# apply focal frequency loss
if epoch >= self.opt.freq_start_epoch:
errG_freq = self.criterion_freq(recon, real, matrix)
else:
errG_freq = torch.tensor(0.0).to(self.device)
errG = errG_pix + errG_freq
errG.backward()
self.optimizerG.step()
return errG_pix, errG_freq
def sample(self, x):
x = x.to(self.device)
self.netG.eval()
with torch.no_grad():
recon = self.netG(x)
self.netG.train()
return recon
def save_checkpoints(self, ckpt_dir, epoch):
torch.save(self.netG.state_dict(),
'%s/netG_epoch_%03d.pth' % (ckpt_dir, epoch))
def file_classify_demo(fobjs: List[FileInfo]):
words = {}
for fobj in filter(lambda x: not x.istest, fobjs):
for kw, freq in zip(fobj.keywords, fobj.kwfreq):
if kw in words:
words[kw] += freq
else:
words[kw] = freq
# make keyword score vec: train and test
all_wordvec = []
all_wordvec_test = []
labels_train = []
labels_test = []
for fobj in fobjs:
fobj.set_wordvec(words)
if not fobj.kwfreq:
continue
if not fobj.istest:
all_wordvec.append(fobj.wordvec)
labels_train.append(fobj.label)
# curlabel = [0] * 5
# curlabel[fobj.label] = 1
# labels.append(curlabel)
else:
all_wordvec_test.append(fobj.wordvec)
labels_test.append(fobj.label)
# pca make fingerprints
inputdim = 20
outputdim = 7
pca = PCA(n_components=inputdim)
pca.fit(all_wordvec)
fprints = pca.transform(all_wordvec)
fprints_test = pca.transform(all_wordvec_test)
print('PCA ratio sum:', sum(pca.explained_variance_ratio_))
print()
x_train = torch.from_numpy(fprints).float()
x_test = torch.from_numpy(fprints_test).float()
y_train = torch.Tensor(labels_train).long() # float()
train_dataset = TensorDataset(x_train, y_train)
dloader = DataLoader(train_dataset, batch_size=6, shuffle=True)
model = MLP(inputdim, outputdim)
optimizer = optim.Adam(model.parameters(), lr=0.01)
lossfunc = nn.CrossEntropyLoss()
epoch = 300 + 1
for ecnt in range(epoch):
for i, data in enumerate(dloader):
optimizer.zero_grad()
inputs, labels = data
inputs = torch.autograd.Variable(inputs)
labels = torch.autograd.Variable(labels)
outputs = model(inputs)
loss = lossfunc(outputs, labels) # / outputs.size()[0]
# loss = torch.Tensor([0])
# for b in range(outputs.size()[0]):
# loss += sum(abs(outputs[b] - labels[b]))
# loss /= outputs.size()[0]
loss.backward()
torch.nn.utils.clip_grad_norm_(model.parameters(),
5) # clip param important
optimizer.step()
# if i % 1 == 0:
# print(i, ":", loss)
# print(outputs)
# print(labels)
if ecnt % 20 == 0:
print('Epoch:', ecnt)
model.eval()
y_train_step = model(x_train)
y_train_step_label = np.argmax(y_train_step.data, axis=1)
y_test_step = model(x_test)
y_test_step_label = np.argmax(y_test_step.data, axis=1)
tran_accu = len(
list(
filter(lambda x: x == 0, y_train_step_label -
np.array(labels_train)))) / len(labels_train)
test_accu = len(
list(
filter(lambda x: x == 0, y_test_step_label -
np.array(labels_test)))) / len(labels_test)
print('tran_accu', tran_accu)
print('test_accu', test_accu)
print()
model.train()
# save model
save_path = r'.\ai\classify-demo.pth'
torch.save(model.state_dict(), save_path)
# load model
new_model = MLP(inputdim, outputdim)
new_model.load_state_dict(torch.load(save_path))
y_train_look = new_model(x_train)
y_test = new_model(x_test)
print(y_train_look)
print(y_test)
print(np.argmax(y_test.data, axis=1))
print(labels_test)
print(len(labels_test))
print(len(labels_train))