jittor.models

这里是Jittor的骨干网络模块的API文档，您可以通过from jittor import models来获取该模块。

class jittor.models.AlexNet(num_classes=1000)

AlexNet model architecture.

Args:

• num_classes: Number of classes. Default: 1000.

Example:

model = jittor.models.AlexNet(500)
x = jittor.random([10,3,224,224])
y = model(x) # [10, 500]

execute(x)

Executes the module computation.

Raises NotImplementedError if the subclass does not override the method.

class jittor.models.DenseNet(growth_rate=32, block_config=(6, 12, 24, 16), num_init_features=64, bn_size=4, drop_rate=0, num_classes=1000)

Densenet-BC model class, based on “Densely Connected Convolutional Networks”

Args:

growth_rate (int) - how many filters to add each layer (k in paper) block_config (list of 4 ints) - how many layers in each pooling block num_init_features (int) - the number of filters to learn in the first convolution layer bn_size (int) - multiplicative factor for number of bottle neck layers

(i.e. bn_size * k features in the bottleneck layer)

drop_rate (float) - dropout rate after each dense layer num_classes (int) - number of classification classes

execute(x)

Executes the module computation.

Raises NotImplementedError if the subclass does not override the method.

class jittor.models.GoogLeNet(num_classes=1000, aux_logits=True, init_weights=True, blocks=None)

GoogLeNet model architecture.

Args:

• num_classes: Number of classes. Default: 1000.

• aux_logits: If True, add an auxiliary branch that can improve training. Default: True

• init_weights: Defualt: True.

• blocks: List of three blocks, [conv_block, inception_block, inception_aux_block]. If None, will use [BasicConv2d, Inception, InceptionAux] instead. Default: None.

eager_outputs(x, aux2, aux1)

execute(x)

Executes the module computation.

Raises NotImplementedError if the subclass does not override the method.

class jittor.models.Inception3(num_classes=1000, aux_logits=True, inception_blocks=None, init_weights=True)

Inceptionv3 model architecture.

Args:

• num_classes: Number of classes. Default: 1000.

• aux_logits: If True, add an auxiliary branch that can improve training. Default: True

• inception_blocks: List of seven blocks, [conv_block, inception_a, inception_b, inception_c, inception_d, inception_e, inception_aux]. If None, will use [BasicConv2d, InceptionA, InceptionB, InceptionC, InceptionD, InceptionE, InceptionAux] instead. Default: None.

• init_weights: Defualt: True.

eager_outputs(x, aux)

execute(x)

Executes the module computation.

Raises NotImplementedError if the subclass does not override the method.

class jittor.models.MNASNet(alpha, num_classes=1000, dropout=0.2)

MNASNet model architecture. version=2.

Args:

• alpha: Depth multiplier.

• num_classes: Number of classes. Default: 1000.

• dropout: Dropout probability of dropout layer.

execute(x)

Executes the module computation.

Raises NotImplementedError if the subclass does not override the method.

class jittor.models.MobileNetV2(num_classes=1000, width_mult=1.0, inverted_residual_setting=None, round_nearest=8, block=None)

MobileNetV2 model architecture.

Args:

• num_classes: Number of classes. Default: 1000.

• width_mult: Width multiplier - adjusts number of channels in each layer by this amount. Default: 1.0.

• init_weights: Defualt: True.

• inverted_residual_setting: Network structure

• round_nearest: Round the number of channels in each layer to be a multiple of this number. Set to 1 to turn off rounding. Default: 8.

• block: Module specifying inverted residual building block for mobilenet. If None, use InvertedResidual instead. Default: None.

execute(x)

Executes the module computation.

Raises NotImplementedError if the subclass does not override the method.

class jittor.models.OrderedDict

Dictionary that remembers insertion order

clear() → None.  Remove all items from od.

copy() → a shallow copy of od

fromkeys(value=None)

Create a new ordered dictionary with keys from iterable and values set to value.

items() → a set-like object providing a view on D’s items

keys() → a set-like object providing a view on D’s keys

move_to_end(key, last=True)

Move an existing element to the end (or beginning if last is false).

Raise KeyError if the element does not exist.

pop(k[, d]) → v, remove specified key and return the corresponding

value. If key is not found, d is returned if given, otherwise KeyError is raised.

popitem(last=True)

Remove and return a (key, value) pair from the dictionary.

Pairs are returned in LIFO order if last is true or FIFO order if false.

setdefault(key, default=None)

Insert key with a value of default if key is not in the dictionary.

Return the value for key if key is in the dictionary, else default.

update([E, ]**F) → None.  Update D from dict/iterable E and F.

If E is present and has a .keys() method, then does: for k in E: D[k] = E[k] If E is present and lacks a .keys() method, then does: for k, v in E: D[k] = v In either case, this is followed by: for k in F: D[k] = F[k]

values() → an object providing a view on D’s values

jittor.models.Resnet101(pretrained=False, **kwargs)

ResNet-101 model architecture.

Example:

model = jittor.models.Resnet101()
x = jittor.random([10,3,224,224])
y = model(x) # [10, 1000]

jittor.models.Resnet152(pretrained=False, **kwargs)

jittor.models.Resnet18(pretrained=False, **kwargs)

jittor.models.Resnet26(pretrained=False, **kwargs)

jittor.models.Resnet34(pretrained=False, **kwargs)

jittor.models.Resnet38(pretrained=False, **kwargs)

jittor.models.Resnet50(pretrained=False, **kwargs)

jittor.models.Resnext101_32x8d(pretrained=False, **kwargs)

jittor.models.Resnext50_32x4d(pretrained=False, **kwargs)

jittor.models.Wide_resnet101_2(pretrained=False, **kwargs)

jittor.models.Wide_resnet50_2(pretrained=False, **kwargs)

jittor.models.alexnet(pretrained=False, **kwargs)

jittor.models.densenet121(pretrained=False, **kwargs)

Densenet-121 model from “Densely Connected Convolutional Networks”

Args:

pretrained (bool): If True, returns a model pre-trained on ImageNet

jittor.models.densenet161(pretrained=False, **kwargs)

Densenet-161 model from “Densely Connected Convolutional Networks”

Args:

pretrained (bool): If True, returns a model pre-trained on ImageNet

jittor.models.densenet169(pretrained=False, **kwargs)

Densenet-169 model from “Densely Connected Convolutional Networks”

Args:

pretrained (bool): If True, returns a model pre-trained on ImageNet

jittor.models.densenet201(pretrained=False, **kwargs)

Densenet-201 model from “Densely Connected Convolutional Networks”

Args:

pretrained (bool): If True, returns a model pre-trained on ImageNet

jittor.models.googlenet(pretrained=False, **kwargs)

jittor.models.inception_v3(pretrained=False, progress=True, **kwargs)

jittor.models.mnasnet0_5(pretrained=False, **kwargs)

jittor.models.mnasnet0_75(pretrained=False, **kwargs)

jittor.models.mnasnet1_0(pretrained=False, **kwargs)

jittor.models.mnasnet1_3(pretrained=False, **kwargs)

jittor.models.mobilenet_v2(pretrained=False)

jittor.models.res2net101(pretrained=False, **kwargs)

Constructs a Res2Net-50_26w_4s model. Args:

pretrained (bool): If True, returns a model pre-trained on ImageNet

jittor.models.res2net50(pretrained=False, **kwargs)

Constructs a Res2Net-50 model. Res2Net-50 refers to the Res2Net-50_26w_4s. Args:

pretrained (bool): If True, returns a model pre-trained on ImageNet

jittor.models.resnet101(pretrained=False, **kwargs)

ResNet-101 model architecture.

Example:

model = jittor.models.Resnet101()
x = jittor.random([10,3,224,224])
y = model(x) # [10, 1000]

jittor.models.resnet152(pretrained=False, **kwargs)

jittor.models.resnet18(pretrained=False, **kwargs)

jittor.models.resnet26(pretrained=False, **kwargs)

jittor.models.resnet34(pretrained=False, **kwargs)

jittor.models.resnet38(pretrained=False, **kwargs)

jittor.models.resnet50(pretrained=False, **kwargs)

jittor.models.resnext101_32x8d(pretrained=False, **kwargs)

jittor.models.resnext50_32x4d(pretrained=False, **kwargs)

jittor.models.shufflenet_v2_x0_5(pretrained=False)

jittor.models.shufflenet_v2_x1_0(pretrained=False)

jittor.models.shufflenet_v2_x1_5(pretrained=False)

jittor.models.shufflenet_v2_x2_0(pretrained=False)

jittor.models.squeezenet1_0(pretrained=False, **kwargs)

jittor.models.squeezenet1_1(pretrained=False, **kwargs)

jittor.models.vgg11(pretrained=False, **kwargs)

jittor.models.vgg11_bn(pretrained=False, **kwargs)

jittor.models.vgg13(pretrained=False, **kwargs)

jittor.models.vgg13_bn(pretrained=False, **kwargs)

jittor.models.vgg16(pretrained=False, **kwargs)

jittor.models.vgg16_bn(pretrained=False, **kwargs)

jittor.models.vgg19(pretrained=False, **kwargs)

jittor.models.vgg19_bn(pretrained=False, **kwargs)

jittor.models.wide_resnet101_2(pretrained=False, **kwargs)

jittor.models.wide_resnet50_2(pretrained=False, **kwargs)