Python layers.get_all_params方法代碼示例

本文整理匯總了Python中lasagne.layers.get_all_params方法的典型用法代碼示例。如果您正苦於以下問題：Python layers.get_all_params方法的具體用法？Python layers.get_all_params怎麽用？Python layers.get_all_params使用的例子？那麽, 這裏精選的方法代碼示例或許可以為您提供幫助。您也可以進一步了解該方法所在類lasagne.layers的用法示例。

在下文中一共展示了layers.get_all_params方法的5個代碼示例，這些例子默認根據受歡迎程度排序。您可以為喜歡或者感覺有用的代碼點讚，您的評價將有助於係統推薦出更棒的Python代碼示例。

示例1: net_updates

# 需要導入模塊: from lasagne import layers [as 別名]
# 或者: from lasagne.layers import get_all_params [as 別名]
def net_updates(net, loss, lr):    
                        
    # Get all trainable parameters (weights) of our net
    params = l.get_all_params(net, trainable=True)

    # We use the adam update, other options are available
    if cfg.OPTIMIZER == 'adam':
        param_updates = updates.adam(loss, params, learning_rate=lr, beta1=0.9)
    elif cfg.OPTIMIZER == 'nesterov':
        param_updates = updates.nesterov_momentum(loss, params, learning_rate=lr, momentum=0.9)
    elif cfg.OPTIMIZER == 'sgd':
        param_updates = updates.sgd(loss, params, learning_rate=lr)    

    return param_updates

#################### TRAIN FUNCTION #####################

開發者ID:kahst，項目名稱:BirdCLEF-Baseline，代碼行數:18，代碼來源:lasagne_net.py

示例2: make_training_functions

# 需要導入模塊: from lasagne import layers [as 別名]
# 或者: from lasagne.layers import get_all_params [as 別名]
def make_training_functions(network, new_params, input_var, aug_var, target_var):
    output = lasagne.layers.get_output(network, deterministic=True, batch_norm_use_averages=True, batch_norm_update_averages=False);
    loss = lasagne.objectives.binary_crossentropy(output, target_var).mean();

    deter_output = lasagne.layers.get_output(network, deterministic=True);
    deter_loss = lasagne.objectives.binary_crossentropy(deter_output, target_var).mean();

    params = layers.get_all_params(network, trainable=True);
    updates = lasagne.updates.nesterov_momentum(loss, params, learning_rate=LearningRate, momentum=0.985);
    new_params_updates = lasagne.updates.nesterov_momentum(loss, new_params, learning_rate=LearningRate, momentum=0.985);

    val_fn = theano.function([input_var, aug_var, target_var], [deter_loss, deter_output]);
    train_fn = theano.function([input_var, aug_var, target_var], loss, updates=updates);
    new_params_train_fn = theano.function([input_var, aug_var, target_var], loss, updates=new_params_updates);

    return train_fn, new_params_train_fn, val_fn;

開發者ID:SBU-BMI，項目名稱:u24_lymphocyte，代碼行數:18，代碼來源:deep_conv_classification_alt48_luad10_skcm10.py

示例3: make_training_functions

# 需要導入模塊: from lasagne import layers [as 別名]
# 或者: from lasagne.layers import get_all_params [as 別名]
def make_training_functions(network, new_params, input_var, aug_var, target_var):
    output = lasagne.layers.get_output(network);
    loss = lasagne.objectives.binary_crossentropy(output, target_var).mean();

    deter_output = lasagne.layers.get_output(network, deterministic=True);
    deter_loss = lasagne.objectives.binary_crossentropy(deter_output, target_var).mean();

    params = layers.get_all_params(network, trainable=True);
    updates = lasagne.updates.nesterov_momentum(loss, params, learning_rate=LearningRate, momentum=0.985);
    new_params_updates = lasagne.updates.nesterov_momentum(loss, new_params, learning_rate=LearningRate, momentum=0.985);

    val_fn = theano.function([input_var, aug_var, target_var], [deter_loss, deter_output]);
    train_fn = theano.function([input_var, aug_var, target_var], loss, updates=updates);
    new_params_train_fn = theano.function([input_var, aug_var, target_var], loss, updates=new_params_updates);

    return train_fn, new_params_train_fn, val_fn;

開發者ID:SBU-BMI，項目名稱:u24_lymphocyte，代碼行數:18，代碼來源:deep_conv_classification_alt48_adeno_t1.py

示例4: make_training_functions

# 需要導入模塊: from lasagne import layers [as 別名]
# 或者: from lasagne.layers import get_all_params [as 別名]
def make_training_functions(network, new_params, input_var, aug_var, target_var):
    output = lasagne.layers.get_output(network, deterministic=False);
    loss = lasagne.objectives.binary_crossentropy(output, target_var).mean();

    deter_output = lasagne.layers.get_output(network, deterministic=True);
    deter_loss = lasagne.objectives.binary_crossentropy(deter_output, target_var).mean();

    params = layers.get_all_params(network, trainable=True);
    updates = lasagne.updates.nesterov_momentum(loss, params, learning_rate=LearningRate, momentum=0.985);
    new_params_updates = lasagne.updates.nesterov_momentum(loss, new_params, learning_rate=LearningRate, momentum=0.985);

    val_fn = theano.function([input_var, aug_var, target_var], [deter_loss, deter_output]);
    train_fn = theano.function([input_var, aug_var, target_var], loss, updates=updates);
    new_params_train_fn = theano.function([input_var, aug_var, target_var], loss, updates=new_params_updates);

    return train_fn, new_params_train_fn, val_fn;

開發者ID:SBU-BMI，項目名稱:u24_lymphocyte，代碼行數:18，代碼來源:deep_conv_classification_alt53.py

示例5: make_training_functions

# 需要導入模塊: from lasagne import layers [as 別名]
# 或者: from lasagne.layers import get_all_params [as 別名]
def make_training_functions(network, new_params, input_var, aug_var, target_var):
    output = lasagne.layers.get_output(network, deterministic=True);
    loss = lasagne.objectives.binary_crossentropy(output, target_var).mean();

    deter_output = lasagne.layers.get_output(network, deterministic=True);
    deter_loss = lasagne.objectives.binary_crossentropy(deter_output, target_var).mean();

    params = layers.get_all_params(network, trainable=True);
    updates = lasagne.updates.nesterov_momentum(loss, params, learning_rate=LearningRate, momentum=0.985);
    new_params_updates = lasagne.updates.nesterov_momentum(loss, new_params, learning_rate=LearningRate, momentum=0.985);

    val_fn = theano.function([input_var, aug_var, target_var], [deter_loss, deter_output]);
    train_fn = theano.function([input_var, aug_var, target_var], loss, updates=updates);
    new_params_train_fn = theano.function([input_var, aug_var, target_var], loss, updates=new_params_updates);

    return train_fn, new_params_train_fn, val_fn;

開發者ID:SBU-BMI，項目名稱:u24_lymphocyte，代碼行數:18，代碼來源:deep_conv_classification_lpatch_alt3.py

注：本文中的lasagne.layers.get_all_params方法示例由純淨天空整理自Github/MSDocs等開源代碼及文檔管理平台，相關代碼片段篩選自各路編程大神貢獻的開源項目，源碼版權歸原作者所有，傳播和使用請參考對應項目的License；未經允許，請勿轉載。