def embed(self, sentence):
vector = []
for word in sentence:
if str(word) in self.vocab:
vector = np.concatenate((vector, self.vocab[str(word)]), axis=0)
else:
vector = np.concatenate((vector, [0]*len(self.vocab['a'])), axis=0)
return vector
if __name__ == "__main__":
#print ('warming up')
_ = handle_one(np.ones((320,320,3)))
video_capture = cv2.VideoCapture(0)
i=-1
while True:
# Capture frame-by-frame
ret, frame = video_capture.read()
i=i+1
if i%4==0:
canvas = handle_one(frame)
canvas = cv2.resize(canvas,(256,256))
#cv2.imwrite("0.png", canvas)
#canvas=cv2.imread('145.png')
temp1=np.concatenate([canvas, canvas], 1)
cv2.imwrite("./temp/test/0.png", temp1)
dataset = data_loader.load_data()
for i, data in enumerate(dataset):
data1=data
if i>0:
break
#canvas=cv2.imread('145.png')
#temp1=np.reshape(canvas,(1,3,canvas.shape[0],canvas.shape[1]))
#temp1.astype(float)
#temp2 = torch.from_numpy(temp1/255)
#temp2 = temp2.view(1,3,256,256)
#cv2.imwrite("./temp/test/temp.jpg", temp1)
#data1={}
#data1['A']=temp2
#data1['A_paths']='145.png'
def main():
# cofiguration
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu_id
torch.manual_seed(args.seed)
if args.cuda:
print('using CUDA with gpu_id:')
print(args.gpu_id)
torch.cuda.manual_seed(args.seed)
# dataset
unlabeledset = load_lua(
'/home/hankuan1993/dataset/stl10/stl10-unlabeled-scaled-tensor.t7')
unlabeledsetnp = unlabeledset.numpy()
trainset = load_lua(
'/home/hankuan1993/dataset/stl10/stl10-train-scaled-tensor.t7')
trainsetnp = trainset.numpy()
testset = load_lua(
'/home/hankuan1993/dataset/stl10/stl10-test-scaled-tensor.t7')
testsetnp = testset.numpy()
trainsetnp = np.concatenate((unlabeledsetnp, trainsetnp), axis=0)
trainlen = len(trainsetnp)
testlen = len(testsetnp)
# model
model = CVAE()
if args.loadPrev:
print('====> loading previously saved model ...')
model.load_state_dict(torch.load('./cvaeCheckPoint.pth'))
if args.cuda:
print('====> loading model to gpu ...')
model.cuda()
optimizer = optim.Adam(model.parameters(), lr=1e-4)
# train and evaluate
for epoch in range(1, args.epochs + 1):
# train
model.train()
train_loss = 0
traintime = math.ceil(trainlen / args.batch_size)
shuffleidx = np.random.permutation(trainsetnp.shape[0])
for batch_idx in range(traintime):
datanp = trainsetnp[shuffleidx[batch_idx *
args.batch_size:(batch_idx + 1) *
args.batch_size], :, :, :].astype(
np.float32) / 255.0
data = torch.from_numpy(datanp)
data = Variable(data)
if args.cuda:
data = data.cuda()
optimizer.zero_grad()
recon_batch, mu, logvar = model(data)
loss = loss_function(recon_batch, data, mu, logvar)
loss.backward()
train_loss += loss.data[0]
optimizer.step()
# if batch_idx % args.log_interval == 0:
# print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
# epoch, batch_idx * len(data), len(train_loader.dataset),
# 100. * batch_idx / len(train_loader),
# loss.data[0] / len(data)))
print('====> Epoch: {} Train Average loss: {:.4f}'.format(
epoch, train_loss / traintime / args.batch_size))
# evaluate
model.eval()
test_loss = 0
for test_idx in range(testlen):
datanp = testsetnp[test_idx, :, :, :].astype(np.float32) / 255.0
data = torch.from_numpy(datanp)
if args.cuda:
data = data.cuda()
data = Variable(data, volatile=True)
recon_batch, mu, logvar = model(data)
test_loss += loss_function(recon_batch, data, mu, logvar).data[0]
test_loss /= testlen
print('====> Test set loss: {:.4f}'.format(test_loss))
# Since training is finished, save it! :)
torch.save(model.state_dict(), './cvaeCheckPoint.pth')