def train_CNN():
print('[+] Load Data')
text, label, train_data, valid_data, test_data = ld.load_data()
print('[+] Build Vocabulary')
text, label = ld.build_vocabulary(text, label, train_data)
print('[+] Set Iterators')
train_iter, valid_iter, test_iter = ld.fetch_iterators(
train_data, valid_data, test_data)
print('[i] Train Iterator Info: \n')
print(f'[i] Length of Train Iter: {len(train_iter)}')
cnn_model = build.set_NN(text, label)
print(
f'[i] The model has {build.count_parameters(cnn_model):,} trainable parameters'
)
cnn_model = build.embed_vectors(text, cnn_model)
print('[+] Save Text Data')
with open('model/TEXT.Field', 'wb') as f:
dill.dump(text, f)
cnn_model, optimizer, criterion = build.fetch_loss_utils(cnn_model)
best_valid_loss = float('inf')
for epoch in range(p.configure()['EPOCHS']):
start = time.time()
train_loss, train_acc = build.train(cnn_model, train_iter, optimizer,
criterion)
valid_loss, valid_acc = build.evaluate(cnn_model, valid_iter,
criterion)
end = time.time()
epoch_mins, epoch_secs = build.epoch_times(start, end)
if valid_loss < best_valid_loss:
best_valid_loss = valid_loss
torch.save(cnn_model, p.configure()['MODEL'])
print(f'Epoch: {epoch+1:02} | Epoch Time: {epoch_mins}m {epoch_secs}s')
print(
f'\tTrain Loss: {train_loss:.3f} | Train Acc: {train_acc*100:.2f}%'
)
print(
f'\t Val. Loss: {valid_loss:.3f} | Val. Acc: {valid_acc*100:.2f}%'
)
return cnn_model
def train_test_model(msg=''):
msg = msg.replace('true', 'True')
msg = msg.replace('false', 'False')
msg = ast.literal_eval(msg)
if (type(msg) == dict):
input_data = msg
else:
return "BAD JSON!!"
file_name = input_data['FileName']
if (input_data['Train'] == False):
pred = build.predict(file_name, input_data['Bars'])
print(pred)
responseJSON = {}
responseJSON['Pred'] = pred
return json.dumps(responseJSON) + "\r\n"
data = input_data['Data']
date = input_data['Time']
testSize = int(input_data['TestingPart'] / 100 * len(data))
trainSize = len(data) - testSize
train = build.train(training_set=data[:trainSize],
date=date[:trainSize],
lr=input_data['LearningRate'],
scale=input_data['Scale'],
epochs=input_data['Epochs'],
momentum=input_data['Momentum'],
optimizer=input_data['Optimizer'],
loss=input_data['Loss'],
file_name=file_name,
architecture=input_data['Architecture'],
cuda=input_data['GPU'])
test = build.test(testing_set=data[trainSize:],
date=date[trainSize:],
file_name=input_data['FileName'])
print(train)
print(test)
evaluate = build.evaluate(file_name=file_name,
testing_weight=input_data['TestingWeight'])
print(evaluate)
pred = build.predict(file_name, input_data['Bars'])
print(pred)
responseJSON = {}
responseJSON['Eval'] = evaluate
responseJSON['Pred'] = pred
return json.dumps(responseJSON) + "\r\n"
def experiment(param):
command = CliArgs(param)
args = command.parse()
layout = args.layout
train_data = DataPipe(args.train_data, layout)
predict_data = DataPipe(args.predict_data, layout)
output_data = args.output_data
if train_data is not None:
train_dataset = train_data.run()
output_data = train(train_dataset, layout)
def train_model():
# prepare data
text, label, train_data, valid_data, test_data = ds.fetch_data()
text, label = ds.build_vocabulary(text, label, train_data)
train_iter, valid_iter, test_iter = ds.fetch_iterators(
train_data, valid_data, test_data)
# build model and set parameters
cnn_model = build.set_NN(text)
print(
f'The model has {build.count_parameters(cnn_model):,} trainable parameters'
)
cnn_model = build.embed_vectors(text, cnn_model)
cnn_model, optimizer, criterion = build.fetch_loss_utils(cnn_model)
# 'save model' conditional
best_valid_loss = float('inf')
# training loop
print('[i] Begin Training...')
for epoch in range(P.configure()['EPOCHS']):
start_time = time.time()
train_loss, train_acc = build.train(cnn_model, train_iter, optimizer,
criterion)
valid_loss, valid_acc = build.evaluate(cnn_model, valid_iter,
criterion)
end_time = time.time()
epoch_mins, epoch_secs = build.epoch_time(start_time, end_time)
if valid_loss < best_valid_loss:
best_valid_loss = valid_loss
torch.save(cnn_model, P.configure()['model'])
print(f'Epoch: {epoch+1:02} | Epoch Time: {epoch_mins}m {epoch_secs}s')
print(
f'\tTrain Loss: {train_loss:.3f} | Train Acc: {train_acc*100:.2f}%'
)
print(
f'\t Val. Loss: {valid_loss:.3f} | Val. Acc: {valid_acc*100:.2f}%'
)
print('[i] Training Finished...\n')
return cnn_model, text
from build import train
train('new-training.yaml', 'my_file.yaml', docker_user = '******', github_user = '******', train_name = 'emote-trainb33', version='4.4')