本文整理汇总了Python中cntk.classification_error方法的典型用法代码示例。如果您正苦于以下问题:Python cntk.classification_error方法的具体用法?Python cntk.classification_error怎么用?Python cntk.classification_error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cntk
的用法示例。
在下文中一共展示了cntk.classification_error方法的6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: _create_model_and_execute_test
# 需要导入模块: import cntk [as 别名]
# 或者: from cntk import classification_error [as 别名]
def _create_model_and_execute_test(params):
# Create CNTK model
input_var = C.input_variable(params['input_dim'], np.float32)
params['input_var'] = input_var
params['act_fun'] = C.layers.blocks.identity
params['init_fun'] = C.glorot_uniform()
model = params['create_model'](params)
label_var = C.input_variable((params['label_dim']), np.float32)
loss = C.cross_entropy_with_softmax(model, label_var)
eval_error = C.classification_error(model, label_var)
lr_schedule = C.learning_rate_schedule(0.05, C.UnitType.minibatch)
learner = C.sgd(model.parameters, lr_schedule)
trainer = C.Trainer(model, (loss, eval_error), [learner])
input_value, label_value = _generate_random_sample(
params['batch_size'],
params['input_dim'],
params['label_dim']
)
# Import to ngraph
ng_loss, placeholders = CNTKImporter(batch_size=params['batch_size']).import_model(loss)
parallel_update = CommonSGDOptimizer(0.05).minimize(ng_loss, ng_loss.variables())
transformer = ng.transformers.make_transformer()
update_fun = transformer.computation([ng_loss, parallel_update], *placeholders)
# Execute on CNTK
trainer.train_minibatch({input_var: input_value, label_var: label_value})
cntk_ret = trainer.previous_minibatch_loss_average
# Execute on ngraph
input_value = np.moveaxis(input_value, 0, -1)
label_value = np.moveaxis(label_value, 0, -1)
ng_ret = update_fun(input_value, label_value)[0]
return cntk_ret, ng_ret
示例2: classification_error
# 需要导入模块: import cntk [as 别名]
# 或者: from cntk import classification_error [as 别名]
def classification_error(target, output, axis=-1):
return C.ops.reduce_mean(
C.equal(
argmax(
output,
axis=-1),
argmax(
target,
axis=-1)),
axis=C.Axis.all_axes())
示例3: in_top_k
# 需要导入模块: import cntk [as 别名]
# 或者: from cntk import classification_error [as 别名]
def in_top_k(predictions, targets, k):
_targets = C.one_hot(targets, predictions.shape[-1])
result = C.classification_error(predictions, _targets, topN=k)
return 1 - C.reshape(result, shape=())
示例4: create_criterion_function_preferred
# 需要导入模块: import cntk [as 别名]
# 或者: from cntk import classification_error [as 别名]
def create_criterion_function_preferred(model, labels):
ce = C.cross_entropy_with_softmax(model, labels)
errs = C.classification_error(model, labels)
return ce, errs # (model, labels) -> (loss, error metric)
示例5: create_criterion_function
# 需要导入模块: import cntk [as 别名]
# 或者: from cntk import classification_error [as 别名]
def create_criterion_function(model):
labels = C.placeholder(name='labels')
ce = C.cross_entropy_with_softmax(model, labels)
errs = C.classification_error(model, labels)
return C.combine([ce, errs]) # (features, labels) -> (loss, metric)
示例6: classification_error
# 需要导入模块: import cntk [as 别名]
# 或者: from cntk import classification_error [as 别名]
def classification_error(output, target, axis=-1):
return C.ops.reduce_mean(
C.equal(
argmax(
output,
axis=-1),
argmax(
target,
axis=-1)),
axis=C.Axis.all_axes())