# parameters.extend(qBot.parameters())
# aqmBot = nn.DataParallel(aqmBot)
# Setup pytorch dataloader
dataset.split = 'train'
dataloader = DataLoader(dataset,
batch_size=params['batchSize'],
shuffle=False,
num_workers=params['numWorkers'],
drop_last=True,
collate_fn=dataset.collate_fn,
pin_memory=False)
# Initializing visdom environment for plotting data
viz = VisdomVisualize(enable=bool(params['enableVisdom']),
env_name=params['visdomEnv'],
server=params['visdomServer'],
port=params['visdomServerPort'])
pprint.pprint(params)
viz.addText(pprint.pformat(params, indent=4))
# Setup optimizer
if params['continue']:
# Continuing from a loaded checkpoint restores the following
startIterID = params['ckpt_iterid'] + 1 # Iteration ID
lRate = params['ckpt_lRate'] # Learning rate
print("Continuing training from iterId[%d]" % startIterID)
else:
# Beginning training normally, without any checkpoint
lRate = params['learningRate']
startIterID = 0
# Load naming of data splits
split_names = json.load(open(params['splitNames'], 'r'))
# Load category specification
if params['qaCategory'] and params['categoryMap']:
category_mapping = json.load(open(params['categoryMap'], 'r'))
val_split_name = split_names['val']
test_split_name = split_names['test']
category_mapping_splits = {
'val': category_mapping[val_split_name][params['qaCategory']],
'test': category_mapping[test_split_name][params['qaCategory']]
}
# Plotting on vizdom
viz = VisdomVisualize(enable=bool(params['enableVisdom']),
env_name=params['visdomEnv'],
server=params['visdomServer'],
port=params['visdomServerPort'])
pprint.pprint(params)
viz.addText(pprint.pformat(params, indent=4))
logging.info("Running evaluation!")
numRounds = params['numRounds']
if 'ckpt_iterid' in params:
iterId = params['ckpt_iterid'] + 1
else:
iterId = -1
for split in splits:
if split == 'train':
splitName = 'full train - {}'.format(params['evalTitle'])
if split == 'val': splitName = 'full Val - {}'.format(params['evalTitle'])
if params["qstartFrom"]:
qBot, loadedParams, _ = utils.loadModel(params, "qbot", overwrite=True)
assert qBot.encoder.vocabSize == params[
"vocabSize"], "Vocab size mismatch!"
for key in loadedParams:
params[key] = loadedParams[key]
qBot.eval()
# Retaining certain dataloder parameters
for key in excludeParams:
params[key] = dlparams[key]
# Plotting on vizdom
viz = VisdomVisualize(
enable=bool(params["enableVisdom"]),
env_name=params["visdomEnv"],
server=params["visdomServer"],
port=params["visdomServerPort"],
)
pprint.pprint(params)
viz.addText(pprint.pformat(params, indent=4))
print("Running evaluation!")
numRounds = params["numRounds"]
if "ckpt_iterid" in params:
iterId = params["ckpt_iterid"] + 1
else:
iterId = -1
if "test" in splits:
split = "test"
splitName = "test - {}".format(params["evalTitle"])
print("tot eval batches", batch_idx)
all_metrics = {}
all_metrics.update(sparse_metrics.retrieve(reset=True))
all_metrics.update(ndcg.retrieve(reset=True))
return all_metrics
if __name__ == '__main__':
params = options.read_command_line()
os.makedirs('checkpoints', exist_ok=True)
if not os.path.exists(params['save_path']):
os.mkdir(params['save_path'])
viz = VisdomVisualize(enable=bool(params['enable_visdom']),
env_name=params['visdom_env'],
server=params['visdom_server'],
port=params['visdom_server_port'])
pprint.pprint(params)
viz.addText(pprint.pformat(params, indent=4))
dataset = VisdialDataset(params)
dataset.split = 'train'
dataloader = DataLoader(
dataset,
batch_size= params['batch_size']//params['sequences_per_image'] if (params['batch_size']//params['sequences_per_image']) \
else 1 if not params['overfit'] else 5,
shuffle=True,
num_workers=params['num_workers'],
drop_last=True,
pin_memory=False)
params[key] = loadedParams[key]
parameters.extend(aBot.parameters())
# Setup pytorch dataloader
dataset.split = 'train'
dataloader = DataLoader(dataset,
batch_size=params['batchSize'],
shuffle=False,
num_workers=params['numWorkers'],
drop_last=True,
collate_fn=dataset.collate_fn,
pin_memory=False)
# Initializing visdom environment for plotting data
viz = VisdomVisualize(enable=bool(params['enableVisdom']),
env_name=params['visdomEnv'],
server=params['visdomServer'],
port=params['visdomServerPort'])
pprint.pprint(params)
viz.addText(pprint.pformat(params, indent=4))
# Setup optimizer
if params['continue']:
# Continuing from a loaded checkpoint restores the following
startIterID = params['ckpt_iterid'] + 1 # Iteration ID
lRate = params['ckpt_lRate'] # Learning rate
print("Continuing training from iterId[%d]" % startIterID)
else:
# Beginning training normally, without any checkpoint
lRate = params['learningRate']
startIterID = 0
# dataloader (pytorch)
# ---------------------------------------------------------------------------
dataset.split = 'train'
dataloader = DataLoader(dataset,
batch_size=params['batchSize'],
shuffle=False,
num_workers=params['numWorkers'],
drop_last=True,
collate_fn=dataset.collate_fn,
pin_memory=False)
# ---------------------------------------------------------------------------
# plotting (visdom)
# ---------------------------------------------------------------------------
viz = VisdomVisualize(enable=bool(params['enableVisdom']),
env_name=params['visdomEnv'],
server=params['visdomServer'],
port=params['visdomServerPort'])
pprint.pprint(params)
viz.addText(pprint.pformat(params, indent=4))
# ---------------------------------------------------------------------------
# optimizer, loss, numIterPerEpoch, rlRound
# ---------------------------------------------------------------------------
if params['continue']:
# Continuing from a loaded checkpoint restores the following
startIterID = params['ckpt_iterid'] + 1 # Iteration ID
lRate = params['ckpt_lRate'] # Learning rate
print("Continuing training from iterId[%d]" % startIterID)
else:
# Beginning training normally, without any checkpoint
lRate = params['learningRate']