parameters_cached = [x for x in parameters()]
optim = torch.optim.SGD(parameters(), lr=args.learning_rate, momentum=0.0) # 0.02, 0.9
named_modules = {"rnn" : rnn, "output" : output, "char_embeddings" : char_embeddings, "optim" : optim}
if args.load_from is not None:
checkpoint = torch.load("/checkpoint/mhahn/"+args.load_from+".pth.tar")
for name, module in named_modules.items():
module.load_state_dict(checkpoint[name])
from torch.autograd import Variable
data = AcqdivReaderPartition(acqdivCorpusReader, partition="train").reshuffledIterator(blankBeforeEOS=False, originalIterator=AcqdivReader.iteratorMorph)
numeric_with_blanks = []
indices_with_blanks = []
count = 0
print("Prepare chunks")
for chunk in data:
indices_with_blanks.append((chunk, -1))
numeric_with_blanks.append(stoi[" "]+3)
countInChunk = 0
for char in chunk[0]:
# print((char if char != "\n" else "\\n", stoi[char]+3 if char in stoi else 2))
indices_with_blanks.append((chunk, countInChunk))
optim = torch.optim.SGD(parameters(), lr=args.learning_rate, momentum=0.0) # 0.02, 0.9
named_modules = {"rnn" : rnn, "output" : output, "char_embeddings" : char_embeddings, "optim" : optim}
# Load the model from the checkpoint
if args.load_from is not None:
checkpoint = torch.load(MODELS_HOME+"/"+args.load_from+".pth.tar")
for name, module in named_modules.items():
module.load_state_dict(checkpoint[name])
from torch.autograd import Variable
data = AcqdivReaderPartition(acqdivCorpusReader, partition="train").reshuffledIterator(blankBeforeEOS=False)
# Read the data into a list of integers
numeric_with_blanks = []
count = 0
print("Prepare chunks")
for chunk in data:
numeric_with_blanks.append(stoi[" "]+3)
for char in chunk:
count += 1
if char not in stoi:
print(char)
numeric_with_blanks.append(stoi[char]+3 if char in stoi else 2)
# select a portion
def backward(loss, printHere):
optim.zero_grad()
if printHere:
print(loss)
loss.backward()
torch.nn.utils.clip_grad_value_(parameters_cached,
5.0) #, norm_type="inf")
optim.step()
import time
devLosses = []
for epoch in range(10000):
print(epoch)
training_data = AcqdivReaderPartition(acqdivCorpusReader,
"train").reshuffledIterator()
print("Got data")
training_chars = prepareDatasetChunks(training_data, train=True)
rnn_drop.train(True)
startTime = time.time()
trainChars = 0
counter = 0
while True:
counter += 1
try:
numeric = [next(training_chars) for _ in range(args.batchSize)]
except StopIteration:
break
printHere = (counter % 50 == 0)
loss, charCounts = forward(numeric, printHere=printHere, train=True)
