def train(data_loader, alpha=0.001, n_epoch=100):
m = CNN() # initialize the model
optimizer = th.optim.SGD(m.parameters(), lr=alpha) # create an SGD optimizer
for _ in range(n_epoch): # iterate through the dataset n_epoch times
for mini_batch in data_loader: # iterate through the dataset, with one mini-batch of random training samples (x,y) at a time
x=mini_batch[0] # the gray-scale images in a mini-batch
y=mini_batch[1] # the labels of the images in a mini-batch
#########################################
## INSERT YOUR CODE HERE (5 points)
z = compute_z(x, m)
L = compute_L(z, y)
L.backward()
update_parameters(optimizer)
#########################################
return m
#-----------------
'''
TEST: Now you can test the correctness of your code above by typing the following in the terminal:
---------------------------------------------------
nosetests -v test3.py:test_train
--- OR ----
python3 -m nose -v test3.py:test_train
--- OR ----
python -m nose -v test3.py:test_train
---------------------------------------------------
'''
'''
def __init__(self, n_lattice=16, n_actions=4, loadpath=None, norm=10, lr=0.001, soft=0.1, decay=0.9, batch_size=128, capacity=10000, freq=100):
self.n_lattice = n_lattice
self.n_actions = n_actions
self.norm = norm
self.lr = lr
self.soft = soft
self.decay = decay
self.batch_size = batch_size
self.capacity = capacity
self.freq = freq
self.prediction_net = CNN()
self.target_net = CNN()
if loadpath is not None:
net = torch.load(loadpath+'/CNN3.pth')
self.prediction_net.load_state_dict(net.state_dict())
self.target_net.load_state_dict(self.prediction_net.state_dict())
self.clip = 1
self.stepcnt = 0
self.memorycnt = 0
self.states = np.zeros((capacity, 16, 4, 4))
self.actions = np.zeros((capacity, 1))
self.rewards = np.zeros((capacity, 1))
self.stateps = np.zeros((capacity, 16, 4, 4))
self.optimizer = torch.optim.SGD(self.prediction_net.parameters(), lr=self.lr)
from game2048.expectimax import board_to_move
self.consultant = board_to_move
def test(run):
print('Testing ' + str(run))
# getting the test data
test_set = torchvision.datasets.FashionMNIST(root='./data/FashionMNIST',
train=False,
download=True,
transform=transforms.Compose(
[transforms.ToTensor()]))
# load the dataset
test_loader = torch.utils.data.DataLoader(test_set,
batch_size=100,
shuffle=False)
# loading the specified model
cnn = CNN()
cnn.load(run)
test_loss = 0
test_total_correct = 0
test_accuracy = 0
for batch in test_loader:
images, labels = batch
preds = cnn(images)
loss = F.cross_entropy(preds, labels)
test_loss += loss.item()
test_total_correct += F.softmax(
preds, dim=1).argmax(dim=1).eq(labels).sum().item()
test_loss /= len(test_set)
test_accuracy = test_total_correct / len(test_set)
print('Testing ended.. total_correct: {}, loss: {}, accuracy: {}'.format(
test_total_correct, test_loss, test_accuracy))
def main(_):
keep_prob = 0.5 if config.mode == 'train' else 1.0
if config.mode == 'train':
reader = TFReader(config.data_path, config.epoch, config.batch_size,
[75 * 75 * 2], [1])
cnn_model = CNN(reader,
config.mode,
keep_prob=keep_prob,
learning_rate=config.learning_rate)
# resnet = Resnet(reader, config.mode, keep_prob=0.5, learning_rate=config.learning_rate)
train(cnn_model, config)
elif config.mode == 'evaluate':
reader = TFReader(config.data_path, config.epoch, config.batch_size,
[75 * 75 * 2], [1])
cnn_model = CNN(reader,
config.mode,
keep_prob=keep_prob,
learning_rate=config.learning_rate)
# resnet = Resnet(reader, config.mode, keep_prob=keep_prob)
evaluate(cnn_model, config)
elif config.mode == 'predict':
reader = DefaultReader(None)
cnn_model = Resnet(reader, config.mode, keep_prob=keep_prob)
predict(cnn_model, config)
elif config.mode == 'batch_predict':
reader = TFReader(config.data_path,
1,
config.batch_size, [75 * 75 * 2], [1],
shuffle=False)
# resnet = Resnet(reader, config.mode, keep_prob=keep_prob)
cnn_model = CNN(reader, config.mode, keep_prob=keep_prob)
batch_predict(cnn_model, config)
def main():
seed = 1
learning_rate = 0.1
batch_size = 64
epochs = 5
torch.manual_seed(seed)
device = torch.device("cpu")
kwargs = {'num_workers': 1, 'pin_memory': True}
train_loader = torch.utils.data.DataLoader(datasets.MNIST(
'data',
train=True,
download=True,
transform=transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307, ), (0.3081, ))
])),
batch_size=batch_size,
shuffle=True,
**kwargs)
model = CNN().to(device)
optimizer = optim.Adadelta(model.parameters(), lr=learning_rate)
scheduler = StepLR(optimizer, step_size=1, gamma=0.7)
for epoch in range(1, epochs + 1):
train(model, device, train_loader, optimizer, epoch)
scheduler.step()
torch.save(model.state_dict(), "mnist_model.pt")
def train(args):
assert args.num_classes
common.make_dir(args.checkout_dir)
nnet = CNN(args.left_context + args.right_context + 1, args.feat_dim, num_maps, pooling_size,
filter_size, conn_dim, args.num_classes)
print(nnet)
nnet.cuda()
criterion = nn.CrossEntropyLoss()
optimizer = th.optim.Adam(nnet.parameters(), lr=args.learning_rate)
train_dataset = THCHS30(root=args.data_dir, data_type='train', left_context=left_context,
right_context=right_context, model_type='cnn')
train_loader = data.DataLoader(dataset=train_dataset, batch_size=args.min_batch,
shuffle=True, num_workers=6)
test_dataset = THCHS30(root=args.data_dir, data_type='test', left_context=left_context,
right_context=right_context, model_type='cnn')
test_loader = data.DataLoader(dataset=test_dataset, batch_size=args.min_batch,
shuffle=True, num_workers=6)
cross_validate(-1, nnet, test_dataset, test_loader)
for epoch in range(args.num_epochs):
common.train_one_epoch(nnet, criterion, optimizer, train_loader)
cross_validate(epoch, nnet, test_dataset, test_loader)
th.save(nnet, common..join_path(args.checkout_dir, 'cnn.{}.pkl'.format(epoch + 1)))
def train_all(gv=global_var):
for project_name, sources in cgv.projects.items():
for i in range(len(sources) - 1):
print('begin training %s' % sources[i])
md.train_and_test_cnn(project_name=project_name,
train_name=sources[i],
test_name=sources[i + 1])
md.train_and_test_cnn_p(project_name=project_name,
train_name=sources[i],
test_name=sources[i + 1])
pc.train_and_test_cnn(project_name=project_name,
train_name=sources[i],
test_name=sources[i + 1],
dict_params=gv.plain_cnn_params)
pc.train_and_test_cnn_p(project_name=project_name,
train_name=sources[i],
test_name=sources[i + 1],
dict_params=gv.plain_cnn_params)
dn.train_and_test_dbn(project_name=project_name,
train_name=sources[i],
test_name=sources[i + 1],
dict_params=gv.dbn_params)
dn.train_and_test_dbn_plus(project_name=project_name,
train_name=sources[i],
test_name=sources[i + 1],
dict_params=gv.dbn_params)
def __init__(self,
screen_height=0,
screen_width=0,
n_actions=0,
gamma=0.999,
epsilon_start=0.9,
epsilon_end=0.05,
epsilon_decay=200,
memory_capacity=10000,
batch_size=128,
device="cpu"):
self.actions_count = 0
self.n_actions = n_actions # 总的动作个数
self.device = device # 设备，cpu或gpu等
self.gamma = gamma
# e-greedy策略相关参数
self.epsilon = 0
self.epsilon_start = epsilon_start
self.epsilon_end = epsilon_end
self.epsilon_decay = epsilon_decay
self.batch_size = batch_size
self.policy_net = CNN(screen_height, screen_width,
n_actions).to(self.device)
self.target_net = CNN(screen_height, screen_width,
n_actions).to(self.device)
self.target_net.load_state_dict(
self.policy_net.state_dict()) # target_net的初始模型参数完全复制policy_net
self.target_net.eval() # 不启用 BatchNormalization 和 Dropout
self.optimizer = optim.RMSprop(self.policy_net.parameters(
)) # 可查parameters()与state_dict()的区别，前者require_grad=True
self.loss = 0
self.memory = ReplayBuffer(memory_capacity)
def __init__(
self,
loss_flag=False,
checkpoint_name='./final_checkpoint/re3_final_checkpoint.pth'):
self.device = device
self.CNN = CNN(1, 1).to(self.device)
self.RNN = RNN(CNN_OUTPUT_SIZE, 1, 1, True).to(self.device)
if os.path.isfile(checkpoint_name):
checkpoint = torch.load(checkpoint_name, map_location='cpu')
self.CNN.load_state_dict(checkpoint['cnn_model_state_dict'])
self.RNN.load_state_dict(checkpoint['rnn_model_state_dict'])
else:
print("Invalid/No Checkpoint. Aborting...!!")
sys.exit()
self.CNN = self.CNN.to(device)
self.RNN = self.RNN.to(device)
self.forward_count = -1
self.previous_frame = None
self.cropped_input = np.zeros((2, 3, CROP_SIZE, CROP_SIZE),
dtype=np.float32)
self.calculate_loss = loss_flag
self.criterion = nn.MSELoss()
self.MSE_loss = 0
def __init__(self, ds_path, lr, iterations, batch_size, hidden_layers_out,
print_freq, save_dir, momentum, dropout):
self.train_data = torchvision.datasets.MNIST(ds_path, train=True,
transform=transforms.ToTensor(),
download=True)
self.test_data = torchvision.datasets.MNIST(ds_path, train=False,
transform=transforms.ToTensor(),
download=True)
self.train_loader = torch.utils.data.DataLoader(self.train_data, batch_size=batch_size, shuffle=True)
self.test_loader = torch.utils.data.DataLoader(self.test_data, batch_size=batch_size)
self.save_dir = save_dir
self.is_momentum = (momentum != 0.0)
# Set Model Hyperparameters
self.learning_rate = lr
self.iterations = iterations
self.print_freq = print_freq
self.model = CNN(hidden_layers_out, dropout=dropout)
self.cuda = torch.cuda.is_available()
if self.cuda:
self.model = self.model.cuda()
def test_update_parameters():
''' (5 points) update_parameters'''
x = th.zeros(2,1,64,64) # a mini-batch of 2 gray-scale images (1 channel) of size 64 X 64
y = th.zeros(2,1)
m = CNN()
m.conv1.bias.data = th.zeros(10)
m.conv2.bias.data = th.zeros(20)
m.conv3.bias.data = th.zeros(30)
m.fc.bias.data = th.zeros(1)
optimizer = th.optim.SGD(m.parameters(), lr=0.1)
z=m(x)
L = compute_L(z,y)
assert np.allclose(L.data,0.6931,atol=0.01)
L.backward()
update_parameters(optimizer)
assert np.allclose(m.fc.bias.data,[-0.05],atol=0.01)
assert np.allclose(m.conv3.bias.data,np.zeros(30),atol=0.01)
x = th.ones(4,1,64,64)
y = th.tensor([[1.],[0.],[1.],[0.]])
m.conv1.bias.data = th.zeros(10)
m.conv2.bias.data = th.zeros(20)
m.conv3.bias.data = th.zeros(30)
m.fc.bias.data = th.zeros(1)
optimizer = th.optim.SGD(m.parameters(), lr=1.)
z=m(x)
L = compute_L(z,y)
L.backward()
update_parameters(optimizer)
assert not np.allclose(m.conv3.bias.data,np.zeros(30))
th.save(m,"cnn.pt") # save the CNN for demo
def webcam():
model = CNN()
model.load_state_dict(torch.load('outputs/model'))
transform = torchvision.transforms.Compose([
torchvision.transforms.ToPILImage(),
torchvision.transforms.Resize(150, interpolation=Image.BILINEAR),
torchvision.transforms.CenterCrop((150, 200)),
torchvision.transforms.ToTensor()
])
cap = cv2.VideoCapture(0)
while cap.isOpened():
ret, frame = cap.read()
if ret:
img = transform(frame)
img_batch = img.unsqueeze(0)
outputs, _ = model(img_batch)
bbxs = find_batch_bounding_boxes(outputs)[0]
img = util.draw_bounding_boxes(img, bbxs[Label.ROBOT.value], (0, 0, 255))
img = util.draw_bounding_boxes(img, bbxs[Label.BALL.value], (255, 0, 0))
util.stream_image(img, wait=25, scale=4)
if cv2.waitKey(25) & 0xFF == ord('q'):
break
cap.release()
cv2.destroyAllWindows()
def demo_cnn():
X,y,w = load2d()
y = flatten_except_1dim(y,ndim=3)
w = flatten_except_1dim(w,ndim=2)
print(X.shape)
print(y.shape)
print(w.shape)
model = CNN()
hist = model.fit(X, y, sample_weight=w, epochs=EPOCH,batch_size=128, validation_split=0.2)
# plot_loss(hist.history,"CNN model",plt)
# plt.legend()
# plt.grid()
# plt.yscale("log")
# plt.xlabel("epoch")
# plt.ylabel("loss")
# plt.show()
model.save('./models/cnn_weighted_model.h5')
X_test,_,_ = load2d(test=True)
# y_test = model.predict(X_test)
# fig = plt.figure(figsize=(10, 7))
# fig.subplots_adjust(
# left=0, right=1, bottom=0, top=1, hspace=0.05, wspace=0.05)
# for i in range(16):
# axis = fig.add_subplot(4, 4, i+1, xticks=[], yticks=[])
# plot_sample(X_test[i], y_test[i], axis)
# plt.show()
df_y_pred = predict_single(model, X_test)
prepare_submission(df_y_pred,"cnn_weighted")
def test_model(null_split):
use_cuda = torch.cuda.is_available()
torch.manual_seed(1)
device = torch.device("cuda" if use_cuda else "cpu")
kwargs = {'num_workers': 1, 'pin_memory': True} if use_cuda else {}
test_data = train_files('/home/hansencb/MNIST/Test')
test_dataset = Test_Dataset(test_data)
batch_size = 128
test_loader = DataLoader(test_dataset, batch_size=1, shuffle=False, **kwargs)
model = CNN(1,10).to(device)
optimizer = torch.optim.Adam(model.parameters(), lr=0.0001)
model_file = 'models/saved_model_split_{}'.format(null_split)
model.load_state_dict(torch.load(model_file))
loss, accuracy, conf_matrix, correct, incorrect = test(model, device, test_loader)
correct_file = 'correct_lists/list_correct_model_split_{}'.format(null_split)
with open(correct_file, 'w') as f:
for i in correct:
line = '{} {} {}\n'.format(i[0], str(i[1]), str(i[2]))
f.write(line)
for i in incorrect:
line = '{} {} {}\n'.format(i[0], str(i[1]), str(i[2]))
f.write(line)
return accuracy
def main(argv):
conf = configparser.ConfigParser()
print(conf.read(argv))
max_smi_len = conf.getint('model', 'max_smi_len')
max_seq_len = conf.getint('model', 'max_seq_len')
data_path = conf.get('model', 'data_path')
ligands = pd.read_csv(data_path + 'ligands.csv', header=None)
proteins = pd.read_csv(data_path + 'proteins.csv', header=None)
inter = pd.read_csv(data_path + 'inter.csv', header=None)
inter = np.asarray(inter)
print(ligands.shape, proteins.shape, inter.shape)
char_smi_set = json.load(open(conf.get('model', 'char_smi')))
char_seq_set = json.load(open(conf.get('model', 'char_seq')))
cv_num = conf.getint('cv', 'cv_num', fallback=5)
problem_type = conf.getint('cv', 'problem_type', fallback=1)
if problem_type == 1:
cv_train, cv_valid = new_pair_fold(inter, cv_num)
elif problem_type == 2:
cv_train, cv_valid = new_protein_fold(inter, cv_num)
elif problem_type == 3:
cv_train, cv_valid = new_ligand_fold(inter, cv_num)
print(cv_train[0].shape, cv_valid[0].shape)
sess = tf.InteractiveSession(config=tf.ConfigProto(
allow_soft_placement=True))
model = CNN(filter_num=conf.getint('model', 'filter_num'),
smi_window_len=conf.getint('model', 'smi_window_len'),
seq_window_len=conf.getint('model', 'seq_window_len'),
max_smi_len=max_smi_len,
max_seq_len=max_seq_len,
char_smi_set_size=len(char_smi_set),
char_seq_set_size=len(char_seq_set),
embed_dim=conf.getint('model', 'embed_dim'))
for cv_id in range(cv_num):
print('start cv', cv_id)
model_path = os.path.join(conf.get('model', 'path', fallback='tmp'),
'cv-' + str(cv_id) + '.model')
trainX, trainy = get_feature(ligands, proteins, inter, cv_train[cv_id],
max_smi_len, char_smi_set, max_seq_len,
char_seq_set)
validX, validy = get_feature(ligands, proteins, inter, cv_valid[cv_id],
max_smi_len, char_smi_set, max_seq_len,
char_seq_set)
print(trainX.shape, trainy.shape, validX.shape, validy.shape)
model.train(sess,
trainX,
trainy,
validX,
validy,
nb_epoch=conf.getint('model', 'num_epoch'),
batch_size=conf.getint('model', 'batch_size'),
model_path=model_path)
def load_model(lr):
model = CNN()
loss_fnc = torch.nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(), lr=lr)
return model, loss_fnc, optimizer
def load_model():
"""
加载本地模型
:return:
"""
model = CNN()
model.load_weights('./models/cnn3_best_weights.h5')
return model
def __init__(self):
self.epsilon = EPSILON_MAX
self.epsilon_min = EPSILON_MIN
self.epsilon_decay = EPSILON_DECAY
self.memory = deque(maxlen=MEMORY_SIZE)
self.offline = CNN((4, 84, 84), 6)
self.online = CNN((4, 84, 84), 6)
def train_model(null_split):
use_cuda = torch.cuda.is_available()
torch.manual_seed(1)
device = torch.device("cuda" if use_cuda else "cpu")
kwargs = {'num_workers': 1, 'pin_memory': True} if use_cuda else {}
train_data = train_files('/home/local/VANDERBILT/hansencb/MNIST/Train')
test_data = train_files('/home/local/VANDERBILT/hansencb/MNIST/Validate')
train_dataset = Train_Dataset(train_data, null_split=null_split)
test_dataset = Test_Dataset(test_data)
batch_size = 128
train_loader = DataLoader(train_dataset, batch_size=batch_size, shuffle=True, **kwargs)
test_loader = DataLoader(test_dataset, batch_size=1, shuffle=False, **kwargs)
model = CNN(1,10).to(device)
optimizer = torch.optim.Adam(model.parameters(), lr=0.0001)
train_loss_file = 'results/train_loss_split_{}.txt'.format(null_split)
f = open(train_loss_file, 'w')
f.close()
validate_loss_file = 'results/validate_loss_split_{}.txt'.format(null_split)
f = open(validate_loss_file, 'w')
f.close()
train_accuracy_file = 'results/train_accuracy_split_{}.txt'.format(null_split)
f = open(train_accuracy_file, 'w')
f.close()
validate_accuracy_file = 'results/validate_accuracy_split_{}.txt'.format(null_split)
f = open(validate_accuracy_file, 'w')
f.close()
model_file = 'models/saved_model_split_{}'.format(null_split)
for epoch in range(1, 101):
print('\nEpoch %d: ' % epoch)
loss, accuracy = train(model, device, train_loader, optimizer)
with open(train_loss_file, "a") as file:
file.write(str(loss))
file.write('\n')
with open(train_accuracy_file, "a") as file:
file.write(str(accuracy))
file.write('\n')
loss, accuracy, confusion, correct_data, incorrect_data = test(model, device, test_loader)
with open(validate_loss_file, "a") as file:
file.write(str(loss))
file.write('\n')
with open(validate_accuracy_file, "a") as file:
file.write(str(accuracy))
file.write('\n')
if epoch % 5 == 0:
with open(model_file, 'wb') as f:
torch.save(model.state_dict(), f)
def eval_cnn():
model = CNN()
config = ConfigManager(model).load()
optimizer = optim.SGD(model.parameters(),
lr=float(config["LEARNING_RATE"]),
momentum=float(config["MOMENTUM"]))
criterion = torch.nn.NLLLoss()
trainer = Trainer(model, MNIST(batch_size=10), optimizer, criterion, True)
trainer.evaluate()
def run_train(args):
# 设置训练的类型，是provinces, area, letters
conf.set_train_params(args.type)
# 载入数据
train_loader, val_loader, train_size = load_train(conf)
conf.train_size = train_size
# 实例化模型和loss函数、优化器
model = CNN(conf).to(device)
criterion = torch.nn.CrossEntropyLoss()
if conf.opt == 'adam':
optimizer = torch.optim.Adam(model.parameters(), lr=conf.learning_rate)
else:
optimizer = torch.optim.Adadelta(model.parameters())
# 开始训练
loss_count, acc_count = [], []
for epoch in range(conf.n_epoch):
print("=" * 15, "epoch: ", str(epoch), "=" * 20)
for i, (x, y) in enumerate(train_loader):
x = x.unsqueeze(1)
batch_x = Variable(x)
batch_y = Variable(y)
output = model(batch_x)
loss = criterion(output, batch_y)
optimizer.zero_grad()
loss.backward()
optimizer.step()
if i % conf.print_per_batch == 0:
loss_count.append(loss)
print('train step: {} [{}/{} ({:.0f}%)]'.format(
i, i * len(batch_x), conf.train_size,
100. * i / len(train_loader)))
batch_acc = 100.0 * (output.argmax(1) == batch_y
).float().sum().item() / len(batch_x)
print("\t minibatch loss: %.3f,\t acc: %.1f%%" %
(loss.item(), batch_acc))
acc_count.append(batch_acc)
print("\t validation accuracy: %.1f%%" %
(eval_in_batches(val_loader, model) * 100))
if args.show:
show_results(conf.train_type,
loss_count,
acc_count,
conf.result_fig_path,
show=False)
# 保存模型
if args.save:
print("save model: %s" % conf.model_path)
torch.save(model, conf.model_path)
def load_cnn_model():
"""
载入CNN模型
:return:
"""
from model import CNN
model = CNN()
model.load_weights('./models/cnn_best_weights.h5')
return model
def load_and_train_model(model_path, load_pretrained):
pcg = PCG(model_path)
if load_pretrained:
pcg.load("/tmp")
else:
pcg.initialize_wav_data()
cnn = CNN(pcg, epochs=100, dropout=0.5)
cnn.train()
def load_model(lr, optm, afunc, kernal_size, padding, pool, dilation):
model = CNN(afunc, kernal_size, padding, pool, dilation)
loss_fnc = torch.nn.CrossEntropyLoss()
if optm == "SGD":
optimizer = torch.optim.SGD(model.parameters(), lr = lr, momentum=0.5)
elif optm == "Adam":
optimizer = torch.optim.Adam(model.parameters(), lr = lr, eps=1e-8)#, weight_decay=0.001)
return model, loss_fnc, optimizer
def load_and_train_model(model_path, load_pretrained):
pcg = PCG(model_path)
if load_pretrained:
pcg.load("/tmp")
else:
pcg.initialize_wav_data()
cnn = CNN(pcg, epochs=200, dropout=0.5)
cnn.train()
def train(X_train, y_train, X_val, y_val, X_test, y_test):
X_train = torch.from_numpy(X_train).float()
y_train = torch.from_numpy(y_train).long()
X_test = torch.from_numpy(X_test).float()
y_test = torch.from_numpy(y_test).long()
model = CNN()
# loss_fun = F.cross_entropy
loss_func = nn.CrossEntropyLoss().cuda()
optimizer = torch.optim.Adam(model.parameters(), lr=0.001)
if GPU:
model = model.cuda()
print('model:', model)
print(X_train.shape)
print(y_train.shape)
trainset = TensorDataset(X_train, y_train)
# valset = TensorDataset(torch.from_numpy(X_val), torch.from_numpy(y_val))
testset = TensorDataset(X_test, y_test)
train_loader = DataLoaderX(trainset,batch_size=16,num_workers=0,pin_memory=True,shuffle=True)
test_loader = DataLoaderX(testset,batch_size=16,num_workers=0,pin_memory=True)
train_size = len(X_train) / 16
preloader = data_prefetcher(train_loader)
for epoch in tqdm(range(EPOCH)):
print('start epoch', epoch, ' / ', EPOCH)
running_loss = 0.0
e_st = time.time()
x, y = preloader
for i, (x, y) in enumerate(tqdm(train_loader)):
if i >= train_size - 1 :
continue
x = x.cuda()
y = y.cuda()
y_hat = model(x)
loss = loss_func(y_hat, y).cuda()
optimizer.zero_grad()
loss.backward()
optimizer.step()
running_loss += loss.data.item()
if i % 100 == 99:
print('[%d, %5d] loss: %.3f' %
(epoch + 1, i + 1, running_loss / 100))
running_loss = 0.0
e_et = time.time()
print('epoch:', epoch, ' use ', show_time(e_et-e_st))
print("Finished Training")
print("Beginning Testing")
correct = 0
total = 0
for data in test_loader:
x, y = data
y_hat = model(x.float())
_, pred = torch.max(y_hat.data, 1)
total += y.size(0)
correct += (pred == y).sum()
print('Accuracy of model on test set:%d %%' % (100 * correct / total))
def model_creator(layers):
model = CNN(32, 3, args.channels, 10, layers, n_nodes=args.nodes)
criterion = nn.CrossEntropyLoss()
optim = torch.optim.SGD(model.parameters(),
0.025,
momentum=0.9,
weight_decay=3.0E-4)
lr_scheduler = torch.optim.lr_scheduler.CosineAnnealingLR(
optim, args.epochs, eta_min=0.001)
return model, criterion, optim, lr_scheduler
def load_model(params):
path = f"saved_models/{params['DATASET']}_static_{params['EPOCH']}.pt"
try:
model = CNN(**params)
model.load_state_dict(torch.load(path))
print(f"Model in {path} loaded successfully!")
return model
except:
print(f"No available model such as {path}.")
exit()
def main(argv):
conf = configparser.ConfigParser()
print(conf.read(argv))
max_smi_len = conf.getint('model', 'max_smi_len')
max_seq_len = conf.getint('model', 'max_seq_len')
data_path = conf.get('model', 'data_path')
ligands = pd.read_csv(data_path + 'ligands.csv',
header=None,
names=['id', 'smi'])
proteins = pd.read_csv(data_path + 'proteins.csv',
header=None,
names=['id', 'seq'])
pairs = pd.read_csv(data_path + 'pairs.csv', header=None)
print(ligands.shape, proteins.shape, pairs.shape)
char_smi_set = json.load(open(conf.get('model', 'char_smi')))
char_seq_set = json.load(open(conf.get('model', 'char_seq')))
smi_feature, seq_feature = get_data(ligands, proteins, max_smi_len,
max_seq_len, char_smi_set,
char_seq_set)
print(smi_feature.shape, seq_feature.shape)
sess = tf.InteractiveSession(config=tf.ConfigProto(
allow_soft_placement=True))
model = CNN(filter_num=conf.getint('model', 'filter_num'),
smi_window_len=conf.getint('model', 'smi_window_len'),
seq_window_len=conf.getint('model', 'seq_window_len'),
max_smi_len=max_smi_len,
max_seq_len=max_seq_len,
char_smi_set_size=len(char_smi_set),
char_seq_set_size=len(char_seq_set),
embed_dim=conf.getint('model', 'embed_dim'))
trainy = np.asarray(pairs.iloc[:, 2]).reshape([-1, 1])
trainX = []
for idx, row in pairs.iterrows():
ligand_index = ligands[ligands.id == row[0]].index.values[0]
protein_index = proteins[proteins.id == row[1]].index.values[0]
trainX.append([smi_feature[ligand_index], seq_feature[protein_index]])
trainX = np.asarray(trainX)
model_path = os.path.join(conf.get('model', 'path', fallback='tmp'),
'all.model')
model.train(sess,
trainX,
trainy,
nb_epoch=conf.getint('model', 'num_epoch'),
batch_size=conf.getint('model', 'batch_size'),
model_path=model_path)
def main(argv):
conf = configparser.ConfigParser()
print(conf.read(argv))
max_smi_len = conf.getint('model', 'max_smi_len')
max_seq_len = conf.getint('model', 'max_seq_len')
char_smi_set = json.load(open(conf.get('model', 'char_smi')))
char_seq_set = json.load(open(conf.get('model', 'char_seq')))
data_path = conf.get('data', 'path')
data_predicted = conf.get('data', 'prediction').split(',')
sess = tf.InteractiveSession(
config=tf.ConfigProto(allow_soft_placement=True))
''' SMILES + seq '''
model = CNN(filter_num=conf.getint('model', 'filter_num'),
smi_window_len=conf.getint('model', 'smi_window_len'),
seq_window_len=conf.getint('model', 'seq_window_len'),
max_smi_len=max_smi_len,
max_seq_len=max_seq_len,
char_smi_set_size=len(char_smi_set),
char_seq_set_size=len(char_seq_set),
embed_dim=conf.getint('model', 'embed_dim'))
''' ECFP + seq '''
# model = ECFPCNN(filter_num=conf.getint('model', 'filter_num'),
# seq_window_len=conf.getint('model', 'seq_window_len'),
# char_seq_set_size=len(char_seq_set),
# embed_dim=conf.getint('model', 'embed_dim'),
# max_smi_len=max_smi_len,
# max_seq_len=max_seq_len)
model_path = os.path.join(
conf.get('model', 'path', fallback='tmp'), 'all.model')
for data_name in data_predicted:
path = data_path + data_name + '/'
ligands = pd.read_csv(path + 'ligands.csv', header=None)
proteins = pd.read_csv(path + 'proteins.csv', header=None)
smi_feature, seq_feature = get_data(
ligands, proteins, max_smi_len, max_seq_len, char_smi_set, char_seq_set)
inputs = []
for smif in smi_feature:
inputs.append([smif, seq_feature[0]])
res = model.predict(sess, np.asarray(inputs), batch_size=conf.getint(
'model', 'batch_size'), model_path=model_path)
names = [x.split('.')[0] for x in list(ligands.iloc[:, 0])]
final_data = pd.DataFrame(np.asarray(list(zip(names, res))))
final_data.to_csv(path + 'res.csv', index=None, header=None)
def __init__(self):
self.epsilon = EPSILON_MAX
self.epsilon_min = EPSILON_MIN
self.epsilon_decay = EPSILON_DECAY
self.memory = deque(maxlen=MEMORY_SIZE)
self.offline = CNN((4, 84, 84), 6)
self.online = CNN((4, 84, 84), 6)
if PLAY_FROM_WEIGHTS:
self.epsilon = 0.0
self.offline.model.load_weights('online_model.h5')
self.online.model.load_weights('online_model.h5')
def train_pred(x_train, y_train, x_test, seed):
print 'Building the CNN ...'
rng = np.random.RandomState(seed)
model = CNN(rng, .1)
model.load_params('./param')
print 'Training with early stop .. '
x_train, y_train, x_valid, y_valid = split_train_set(x_train, y_train)
model.train(x_train, y_train, x_valid, y_valid)
model.save_params('./param')
pred = model.predict(x_test)
write_data(pred)
# load vocab, vocab_size, max_length
with open('vocab.json', 'r') as fp:
vocab = json.load(fp)
# load configuration
with open('config.txt', 'r') as f:
vocab_size = int(re.sub('\n', '', f.readline()))
max_length = int(f.readline())
# open session
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
sess = tf.Session(config=config)
# make model instance
model = CNN(sess=sess, vocab_size=vocab_size, sequence_length=max_length, trainable=True)
# load trained model
saver = tf.train.Saver()
saver.restore(sess, tf.train.latest_checkpoint(PATH))
# inference
while True:
test = input("User >> ")
if test == "exit":
break
speak = sentence_to_index_morphs([test], vocab, max_length)
label, prob = model.predict(speak)
if prob[0] < 0.6:
response = '차분해 보이시네요 :)'
else:
# save vocab, vocab_size, max_length
with open('vocab.json', 'w') as fp:
json.dump(vocab, fp)
# save configuration
with open('config.txt', 'w') as f:
f.write(str(vocab_size) + '\n')
f.write(str(max_length))
# open session
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
sess = tf.Session(config=config)
# make model instance
model = CNN(sess=sess, vocab_size=vocab_size, sequence_length=max_length, trainable=True)
# assign pretrained embedding vectors
model.embedding_assign(embedding)
# make train batches
batches = batch_iter(list(zip(x_input, y_input)), batch_size=64, num_epochs=5)
# model saver
saver = tf.train.Saver(max_to_keep=3, keep_checkpoint_every_n_hours=0.5)
# train model
print('모델 훈련을 시작합니다.')
avgLoss = []
for step, batch in enumerate(batches):
x_train, y_train = zip(*batch)
