default=None,
required=False)
args = parser.parse_args()
if args.plot is not None or args.sample is not None:
import matplotlib
matplotlib.use('Agg')
import matplotlib.pyplot as plt
if args.sample is not None:
checkpoint_file = args.sample
else:
checkpoint_file = args.plot
if not os.path.exists(checkpoint_file):
raise ValueError("Checkpoint file path %s" % checkpoint_file,
" does not exist!")
print(checkpoint_file)
checkpoint_dict = load_checkpoint(checkpoint_file)
train_costs = checkpoint_dict["train_costs"]
valid_costs = checkpoint_dict["valid_costs"]
plt.plot(train_costs)
plt.plot(valid_costs)
plt.savefig("costs.png")
X_mb, X_mb_mask, c_mb, c_mb_mask = next(valid_itr)
valid_itr.reset()
prev_h1, prev_h2, prev_h3 = [
np_zeros((minibatch_size, n_hid)) for i in range(3)
]
prev_kappa = np_zeros((minibatch_size, att_size))
prev_w = np_zeros((minibatch_size, n_chars))
if args.sample is not None:
predict_function = checkpoint_dict["predict_function"]
grads = tensor.grad(reg_cost, params)
grads = gradient_clipping(grads, 10.)
learning_rate = 1E-4
opt = adam(params, learning_rate)
updates = opt.updates(params, grads)
if args.cont is not None:
print("Continuing training from saved model")
continue_path = args.cont
if not os.path.exists(continue_path):
raise ValueError("Continue model %s, path not "
"found" % continue_path)
saved_checkpoint = load_checkpoint(continue_path)
checkpoint_dict = saved_checkpoint
train_function = checkpoint_dict["train_function"]
cost_function = checkpoint_dict["cost_function"]
predict_function = checkpoint_dict["predict_function"]
else:
train_function = theano.function([X_sym, X_mask_sym],
[cost],
updates=updates,
on_unused_input='warn')
cost_function = theano.function([X_sym, X_mask_sym],
[cost],
on_unused_input='warn')
predict_function = theano.function([X_sym, X_mask_sym],
[pred],
on_unused_input='warn')
default=None,
required=False)
args = parser.parse_args()
if args.plot is not None or args.sample is not None:
import matplotlib
matplotlib.use('Agg')
import matplotlib.pyplot as plt
if args.sample is not None:
checkpoint_file = args.sample
else:
checkpoint_file = args.plot
if not os.path.exists(checkpoint_file):
raise ValueError("Checkpoint file path %s" % checkpoint_file,
" does not exist!")
print(checkpoint_file)
checkpoint_dict = load_checkpoint(checkpoint_file)
train_costs = checkpoint_dict["overall_train_costs"]
valid_costs = checkpoint_dict["overall_valid_costs"]
plt.plot(train_costs)
plt.plot(valid_costs)
plt.savefig("costs.png")
X_mb, X_mb_mask, c_mb, c_mb_mask = next(valid_itr)
valid_itr.reset()
prev_h1, prev_h2, prev_h3 = [np_zeros((minibatch_size, n_hid))
for i in range(3)]
prev_kappa = np_zeros((minibatch_size, att_size))
prev_w = np_zeros((minibatch_size, n_chars))
bias = args.bias
if args.sample is not None:
grads = tensor.grad(reg_cost, params)
grads = gradient_clipping(grads, 10.)
learning_rate = 1E-4
opt = adam(params, learning_rate)
updates = opt.updates(params, grads)
if args.cont is not None:
print("Continuing training from saved model")
continue_path = args.cont
if not os.path.exists(continue_path):
raise ValueError("Continue model %s, path not "
"found" % continue_path)
saved_checkpoint = load_checkpoint(continue_path)
checkpoint_dict = saved_checkpoint
train_function = checkpoint_dict["train_function"]
cost_function = checkpoint_dict["cost_function"]
predict_function = checkpoint_dict["predict_function"]
else:
train_function = theano.function([X_sym, X_mask_sym], [cost],
updates=updates,
on_unused_input='warn')
cost_function = theano.function([X_sym, X_mask_sym], [cost],
on_unused_input='warn')
predict_function = theano.function([X_sym, X_mask_sym], [pred],
on_unused_input='warn')
print("Beginning training loop")
checkpoint_dict = {}
checkpoint_dict["train_function"] = train_function
