本文整理汇总了Python中dataset.Dataset.setup_pretraining_dataset方法的典型用法代码示例。如果您正苦于以下问题：Python Dataset.setup_pretraining_dataset方法的具体用法？Python Dataset.setup_pretraining_dataset怎么用？Python Dataset.setup_pretraining_dataset使用的例子？那么恭喜您, 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dataset.Dataset的用法示例。
在下文中一共展示了Dataset.setup_pretraining_dataset方法的3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: get_data_patches
# 需要导入模块: from dataset import Dataset [as 别名]
# 或者: from dataset.Dataset import setup_pretraining_dataset [as 别名]
def get_data_patches(data):
ds = Dataset(is_binary=True)
ds.setup_pretraining_dataset(data_dict[data_key],
train_split_scale=1.0,
patch_size=(8, 8))
ds_test = Dataset(is_binary=True)
ds_test.setup_pretraining_dataset(data_dict["ds_test"],
train_split_scale=1.0,
patch_size=(8, 8))
XTrain, YTrain = ds.Xtrain_patches, ds.Ytrain
XTest, YTest = ds_test.Xtrain_patches, ds_test.Ytrain
return XTrain, YTrain, XTest, YTest示例2: normalize
# 需要导入模块: from dataset import Dataset [as 别名]
# 或者: from dataset.Dataset import setup_pretraining_dataset [as 别名]
print "Normalizing patch-mlp's outputs"
pre_train_probs = normalize(pre_train_probs)
pre_test_train_probs = normalize(pre_test_train_probs)
pre_test_test_probs = normalize(pre_test_test_probs)
csvm.train(pre_train_probs, train_set_labels, **post_cs_args["train_args"])
print "starting post-testing on training dataset"
train_error = csvm.test(pre_test_train_probs, train_set_labels, **post_cs_args["test_args"])
print "For training %s" %(train_error)
print "starting post-testing on the dataset"
test_error = csvm.test(pre_test_test_probs, test_set_labels, **post_cs_args["test_args"])
print "For testing %s" %(test_error)
import ipdb; ipdb.set_trace()
if __name__=="__main__":
print "Loading the dataset"
ds = Dataset()
patch_size=(16,16)
ds.setup_pretraining_dataset(data_path="/RQusagers/gulcehre/dataset/pentomino/rnd_pieces/pento64x64_40k_seed_39112222_16patches_rnd.npy", patch_size=patch_size, normalize_inputs=False)
x = T.matrix('x')
n_hiddens = [1024, 768]
prmlp = PatchBasedMLP(x, n_in=16*16, n_hiddens=n_hiddens, n_out=11,
no_of_patches=16, activation=NeuralActivations.Rectifier, use_adagrad=False)
csvm = CSVM()
pre_training(prmlp, csvm, ds)
示例3: Dataset
# 需要导入模块: from dataset import Dataset [as 别名]
# 或者: from dataset.Dataset import setup_pretraining_dataset [as 别名]
test_scores.append(numpy.mean(prmlps[i].test_scores))
if pre_test_probs == None:
pre_test_probs = prmlps[i].pretrain_test_probs
else:
pre_test_probs = numpy.column_stack((pre_test_probs, prmlps[i].pretrain_test_probs))
print "In the end the test score is %f " % (numpy.mean(test_scores))
return pre_test_probs
if __name__=="__main__":
x = T.matrix('x')
dataset = "/data/lisa/data/pentomino/pentomino64x64_4k_pre.npy"
ds = Dataset()
print "starting pretrain"
ds.setup_pretraining_dataset(data_path=dataset)
train_set_patches, train_set_pre, train_set_labels = ds.Xtrain_patches, ds.Xtrain_presences, ds.Ytrain
test_set_patches, test_set_pre, test_set_labels = ds.Xtest_patches, ds.Xtest_presences, ds.Ytest
prmlps = [PreMLP(x) for each in xrange(64)]
print "starting pretest"
pre_train_probs = train_prmlp(prmlps, train_set_patches, train_set_pre)
pre_test_probs = test_prmlp(prmlps, test_set_patches, test_set_pre)
post_mlp = PosttrainMLP(x, n_in=64*11, n_hidden=200, n_out=10)
post_mlp.posttrain(data=pre_train_probs, labels=train_set_labels, batch_size=80)
post_mlp.posttest(data=pre_test_probs, labels=test_set_labels)