def computeDevLoss():
global printHere
# global counter
# global devSurprisalTable
devLoss = 0.0
devWords = 0
# corpusDev = getNextSentence("valid")
corpusDev = corpusIteratorWikiWords.dev(args.language)
stream = prepareDatasetChunks(corpusDev, train=False)
surprisalTable = [0 for _ in range(args.horizon)]
devCounter = 0
devMemory = 0
while True:
devCounter += 1
printHere = (devCounter % 50 == 0)
try:
with torch.no_grad():
_, _, _, newLoss, newWords, devMemoryHere = forward(
next(stream),
surprisalTable=surprisalTable,
doDropout=False,
batchSizeHere=args.batchSize)
except StopIteration:
break
devMemory += devMemoryHere.data.cpu().numpy()
devLoss += newLoss
devWords += newWords
if printHere:
print "Dev examples " + str(devCounter)
devSurprisalTableHere = [
surp / (devCounter * args.batchSize) for surp in surprisalTable
]
return devLoss / devWords, devSurprisalTableHere, devMemory / devCounter
def computeDevLoss():
global printHere
# global counter
# global devSurprisalTable
devLoss = 0.0
devWords = 0
# corpusDev = getNextSentence("valid")
corpusDev = corpusIteratorWikiWords.dev(args.language)
stream = createStream(corpusDev)
surprisalTable = [0 for _ in range(args.horizon)]
devCounter = 0
devMemory = 0
while True:
# try:
# input_indices, wordStartIndices = next(stream)
try:
input_indices_list = []
wordStartIndices_list = []
for _ in range(args.batchSize):
input_indices, wordStartIndices = next(stream)
input_indices_list.append(input_indices)
wordStartIndices_list.append(wordStartIndices)
except StopIteration:
break
devCounter += 1
# counter += 1
printHere = (devCounter % 50 == 0)
with torch.no_grad():
_, _, _, newLoss, newWords, devMemoryHere = doForwardPass(
input_indices_list,
wordStartIndices_list,
surprisalTable=surprisalTable,
doDropout=False,
batchSizeHere=args.batchSize)
devMemory += devMemoryHere.data.cpu().numpy()
devLoss += newLoss
devWords += newWords
if printHere:
print "Dev examples " + str(devCounter)
devSurprisalTableHere = [
surp / (devCounter * args.batchSize) for surp in surprisalTable
]
return devLoss / devWords, devSurprisalTableHere, devMemory / devCounter
assert False
####################################
from torch.autograd import Variable
#data = AcqdivReaderPartition(acqdivCorpusReader, partition="train").reshuffledIterator(blankBeforeEOS=False)
rnn_drop.train(False)
data = corpusIteratorWikiWords.dev(args.language)
print("Got data")
numeric_with_blanks = []
count = 0
print("Prepare chunks")
for chunk in data:
for word in chunk:
numeric_with_blanks.append(stoi[" "]+3)
for char in word:
# print((char if char != "\n" else "\\n", stoi[char]+3 if char in stoi else 2))
count += 1
if char not in stoi:
print(char)
if (labels[-1] == 1) and relevantNextWords[-1].startswith(
relevantWords[-1]
): # this is actually not a hard assertion, it should just be quite unlikely in languages such as English
print("WARNING",
list(zip(boundaries[j][i:], boundariesAll[j][i:])))
# if len(relevantWords[-1]) > 1:
# assert False
import time
devLosses = []
#for epoch in range(10000):
if True:
training_data = corpusIteratorWikiWords.dev(args.language,
removeMarkup=False)
training_data_c = corpusIteratorWiki.dev(args.language, doShuffling=False)
print("Got data")
training_chars = prepareDatasetChunks(training_data,
training_data_c,
train=False)
rnn_drop.train(False)
startTime = time.time()
trainChars = 0
counter = 0
while True:
counter += 1
try:
numeric = [next(training_chars) for _ in range(args.batchSize)]
"components": [c.state_dict() for c in modules]
}
torch.save(
state, "/u/scr/mhahn/CODEBOOKS/" + args.language1 + "AND" +
args.language2 + "_" + __file__ + "_code_" + str(args.myID) +
".txt")
if (time.time() - totalStartTime) / 60 > 4000:
print("Breaking early to get some result within 72 hours")
totalStartTime = time.time()
break
# break
rnn_drop.train(False)
dev_data_1 = corpusIteratorWikiWords.dev(args.language1)
dev_data_2 = corpusIteratorWikiWords.dev(args.language2)
print("Got data")
dev_chars = prepareDatasetChunksTwo(dev_data_1, dev_data_2, train=False)
dev_loss = 0
dev_char_count = 0
counter = 0
hidden, beginning = None, None
while True:
counter += 1
try:
numeric = next(dev_chars)
except StopIteration:
