本文整理汇总了Python中chainer.functions.select_item方法的典型用法代码示例。如果您正苦于以下问题:Python functions.select_item方法的具体用法?Python functions.select_item怎么用?Python functions.select_item使用的例子?那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类chainer.functions
的用法示例。
在下文中一共展示了functions.select_item方法的14个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: softmax_cross_entropy
# 需要导入模块: from chainer import functions [as 别名]
# 或者: from chainer.functions import select_item [as 别名]
def softmax_cross_entropy(self, y, t):
import numpy as np
log_softmax = F.log_softmax(y)
# SelectItem is not supported by onnx-chainer.
# TODO(hamaji): Support it?
# log_prob = F.select_item(log_softmax, t)
# TODO(hamaji): Currently, F.sum with axis=1 cannot be
# backpropped properly.
# log_prob = F.sum(log_softmax * t, axis=1)
# self.batch_size = chainer.Variable(np.array(t.size, np.float32),
# name='batch_size')
# return -F.sum(log_prob, axis=0) / self.batch_size
log_prob = F.sum(log_softmax * t, axis=(0, 1))
batch_size = chainer.Variable(np.array(t.shape[0], np.float32),
name='batch_size')
self.extra_inputs = [batch_size]
loss = -log_prob / batch_size
loss.name = 'loss'
return loss
示例2: forward
# 需要导入模块: from chainer import functions [as 别名]
# 或者: from chainer.functions import select_item [as 别名]
def forward(self, x, t):
xp = cuda.get_array_module(x)
y = self.predictor(x)
log_softmax = F.log_softmax(y)
# SelectItem is not supported by onnx-chainer.
# TODO(hamaji): Support it?
# log_prob = F.select_item(log_softmax, t)
batch_size = chainer.Variable(xp.array(t.size, xp.float32),
name='batch_size')
self.extra_inputs = [batch_size]
# TODO(hamaji): Currently, F.sum with axis=1 cannot be
# backpropped properly.
# log_prob = F.sum(log_softmax * t, axis=1)
# return -F.sum(log_prob, axis=0) / self.batch_size
log_prob = F.sum(log_softmax * t, axis=(0, 1))
loss = -log_prob / batch_size
reporter.report({'loss': loss}, self)
if self.compute_accuracy:
acc = accuracy.accuracy(y, xp.argmax(t, axis=1))
reporter.report({'accuracy': acc}, self)
loss.name = 'loss'
return loss
示例3: softmax_cross_entropy
# 需要导入模块: from chainer import functions [as 别名]
# 或者: from chainer.functions import select_item [as 别名]
def softmax_cross_entropy(self, y, t):
import numpy as np
log_softmax = F.log_softmax(y)
# SelectItem is not supported by onnx-chainer.
# TODO(hamaji): Support it?
# log_prob = F.select_item(log_softmax, t)
# TODO(hamaji): Currently, F.sum with axis=1 cannot be
# backpropped properly.
# log_prob = F.sum(log_softmax * t, axis=1)
# self.batch_size = chainer.Variable(np.array(t.size, np.float32),
# name='batch_size')
# return -F.sum(log_prob, axis=0) / self.batch_size
log_prob = F.sum(log_softmax * t, axis=(0, 1))
batch_size = chainer.Variable(self.xp.array(t.shape[0], np.float32),
name='batch_size')
self.extra_inputs = [batch_size]
loss = -log_prob / batch_size
loss.name = 'loss'
return loss
示例4: update
# 需要导入模块: from chainer import functions [as 别名]
# 或者: from chainer.functions import select_item [as 别名]
def update(Q, target_Q, opt, samples, gamma=0.99, target_type='double_dqn'):
"""Update a Q-function with given samples and a target Q-function."""
dtype = chainer.get_dtype()
xp = Q.xp
obs = xp.asarray([sample[0] for sample in samples], dtype=dtype)
action = xp.asarray([sample[1] for sample in samples], dtype=np.int32)
reward = xp.asarray([sample[2] for sample in samples], dtype=dtype)
done = xp.asarray([sample[3] for sample in samples], dtype=dtype)
obs_next = xp.asarray([sample[4] for sample in samples], dtype=dtype)
# Predicted values: Q(s,a)
y = F.select_item(Q(obs), action)
# Target values: r + gamma * max_b Q(s',b)
with chainer.no_backprop_mode():
if target_type == 'dqn':
next_q = F.max(target_Q(obs_next), axis=1)
elif target_type == 'double_dqn':
next_q = F.select_item(target_Q(obs_next),
F.argmax(Q(obs_next), axis=1))
else:
raise ValueError('Unsupported target_type: {}'.format(target_type))
target = reward + gamma * (1 - done) * next_q
loss = mean_clipped_loss(y, target)
Q.cleargrads()
loss.backward()
opt.update()
示例5: prob
# 需要导入模块: from chainer import functions [as 别名]
# 或者: from chainer.functions import select_item [as 别名]
def prob(self, x):
return F.select_item(self.all_prob, x)
示例6: log_prob
# 需要导入模块: from chainer import functions [as 别名]
# 或者: from chainer.functions import select_item [as 别名]
def log_prob(self, x):
return F.select_item(self.all_log_prob, x)
示例7: max
# 需要导入模块: from chainer import functions [as 别名]
# 或者: from chainer.functions import select_item [as 别名]
def max(self):
with chainer.force_backprop_mode():
return F.select_item(self.q_values, self.greedy_actions)
示例8: evaluate_actions
# 需要导入模块: from chainer import functions [as 别名]
# 或者: from chainer.functions import select_item [as 别名]
def evaluate_actions(self, actions):
return F.select_item(self.q_values, actions)
示例9: sampled_actions_log_probs
# 需要导入模块: from chainer import functions [as 别名]
# 或者: from chainer.functions import select_item [as 别名]
def sampled_actions_log_probs(self):
return F.select_item(
self.log_probs,
chainer.Variable(np.asarray(self.action_indices, dtype=np.int32)))
示例10: gen_select_item_test
# 需要导入模块: from chainer import functions [as 别名]
# 或者: from chainer.functions import select_item [as 别名]
def gen_select_item_test(test_name):
input = V(aranges(4, 3))
indices = V([1, 2, 0, 1])
output = F.select_item(input, indices)
node = onnx.helper.make_node(
'ChainerSelectItem',
inputs=['input', 'indices'],
outputs=['output'])
expect(node, inputs=[input, indices], outputs=[output], name=test_name)
示例11: check_forward
# 需要导入模块: from chainer import functions [as 别名]
# 或者: from chainer.functions import select_item [as 别名]
def check_forward(self, x_data, t_data):
x = chainer.Variable(x_data)
t = chainer.Variable(t_data)
y = functions.select_item(x, t)
y_exp = cuda.to_cpu(x_data)[range(t_data.size), cuda.to_cpu(t_data)]
self.assertEqual(y.data.dtype, self.dtype)
numpy.testing.assert_equal(cuda.to_cpu(y.data), y_exp)
示例12: check_backward
# 需要导入模块: from chainer import functions [as 别名]
# 或者: from chainer.functions import select_item [as 别名]
def check_backward(self, x_data, t_data, gy_data):
gradient_check.check_backward(
functions.select_item,
(x_data, t_data), gy_data, eps=0.01, dtype='d',
**self.check_backward_options)
示例13: check_double_backward
# 需要导入模块: from chainer import functions [as 别名]
# 或者: from chainer.functions import select_item [as 别名]
def check_double_backward(self, x_data, t_data, gy_data, ggx_data):
def f(x):
return functions.select_item(x, t_data)
gradient_check.check_double_backward(
f, x_data, gy_data, ggx_data, eps=0.01, dtype='d',
**self.check_backward_options)
示例14: check_value_check
# 需要导入模块: from chainer import functions [as 别名]
# 或者: from chainer.functions import select_item [as 别名]
def check_value_check(self, x_data, t_data):
x = chainer.Variable(x_data)
t = chainer.Variable(t_data)
if self.valid:
# Check if it throws nothing
functions.select_item(x, t)
else:
with self.assertRaises(ValueError):
functions.select_item(x, t)