Python torch.nn.AdaptiveMaxPool3d() Examples

The following are 6 code examples of torch.nn.AdaptiveMaxPool3d(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module torch.nn , or try the search function .
Example #1
Source File: factories.py    From MONAI with Apache License 2.0 5 votes vote down vote up 
def adaptive_maxpooling_factory(dim):
    types = [nn.AdaptiveMaxPool1d, nn.AdaptiveMaxPool2d, nn.AdaptiveMaxPool3d]
    return types[dim - 1]
Example #2
Source File: flops_counter.py    From Efficient-Segmentation-Networks with MIT License 5 votes vote down vote up 
def is_supported_instance(module):
    if isinstance(module, (torch.nn.Conv1d, torch.nn.Conv2d, torch.nn.Conv3d,
                           torch.nn.ReLU, torch.nn.PReLU, torch.nn.ELU, \
                           torch.nn.LeakyReLU, torch.nn.ReLU6, torch.nn.Linear, \
                           torch.nn.MaxPool2d, torch.nn.AvgPool2d, torch.nn.BatchNorm2d, \
                           torch.nn.Upsample, nn.AdaptiveMaxPool2d, nn.AdaptiveAvgPool2d, \
                           torch.nn.MaxPool1d, torch.nn.AvgPool1d, torch.nn.BatchNorm1d, \
                           nn.AdaptiveMaxPool1d, nn.AdaptiveAvgPool1d, \
                           nn.ConvTranspose2d, torch.nn.BatchNorm3d,
                           torch.nn.MaxPool3d, torch.nn.AvgPool3d, nn.AdaptiveMaxPool3d, nn.AdaptiveAvgPool3d)):
        return True

    return False
Example #3
Source File: flops_counter.py    From Efficient-Segmentation-Networks with MIT License 5 votes vote down vote up 
def add_flops_counter_hook_function(module):
    if is_supported_instance(module):
        if hasattr(module, '__flops_handle__'):
            return

        if isinstance(module, (torch.nn.Conv1d, torch.nn.Conv2d, torch.nn.Conv3d)):
            handle = module.register_forward_hook(conv_flops_counter_hook)
        elif isinstance(module, (torch.nn.ReLU, torch.nn.PReLU, torch.nn.ELU, \
                                 torch.nn.LeakyReLU, torch.nn.ReLU6)):
            handle = module.register_forward_hook(relu_flops_counter_hook)
        elif isinstance(module, torch.nn.Linear):
            handle = module.register_forward_hook(linear_flops_counter_hook)
        elif isinstance(module, (torch.nn.AvgPool2d, torch.nn.MaxPool2d, nn.AdaptiveMaxPool2d, \
                                 nn.AdaptiveAvgPool2d, torch.nn.MaxPool3d, torch.nn.AvgPool3d, \
                                 torch.nn.AvgPool1d, torch.nn.MaxPool1d, nn.AdaptiveMaxPool1d, \
                                 nn.AdaptiveAvgPool1d, nn.AdaptiveMaxPool3d, nn.AdaptiveAvgPool3d)):
            handle = module.register_forward_hook(pool_flops_counter_hook)
        elif isinstance(module, (torch.nn.BatchNorm1d, torch.nn.BatchNorm2d, torch.nn.BatchNorm3d)):
            handle = module.register_forward_hook(bn_flops_counter_hook)
        elif isinstance(module, torch.nn.Upsample):
            handle = module.register_forward_hook(upsample_flops_counter_hook)
        elif isinstance(module, torch.nn.ConvTranspose2d):
            handle = module.register_forward_hook(deconv_flops_counter_hook)
        else:
            handle = module.register_forward_hook(empty_flops_counter_hook)
        module.__flops_handle__ = handle
Example #4
Source File: flops_counter.py    From ESNet with MIT License 5 votes vote down vote up 
def is_supported_instance(module):
    if isinstance(module, (torch.nn.Conv1d, torch.nn.Conv2d, torch.nn.Conv3d,
                           torch.nn.ReLU, torch.nn.PReLU, torch.nn.ELU, \
                           torch.nn.LeakyReLU, torch.nn.ReLU6, torch.nn.Linear, \
                           torch.nn.MaxPool2d, torch.nn.AvgPool2d, torch.nn.BatchNorm2d, \
                           torch.nn.Upsample, nn.AdaptiveMaxPool2d, nn.AdaptiveAvgPool2d, \
                           torch.nn.MaxPool1d, torch.nn.AvgPool1d, torch.nn.BatchNorm1d, \
                           nn.AdaptiveMaxPool1d, nn.AdaptiveAvgPool1d, \
                           nn.ConvTranspose2d, torch.nn.BatchNorm3d,
                           torch.nn.MaxPool3d, torch.nn.AvgPool3d, nn.AdaptiveMaxPool3d, nn.AdaptiveAvgPool3d)):
        return True

    return False
Example #5
Source File: flops_counter.py    From ESNet with MIT License 5 votes vote down vote up 
def add_flops_counter_hook_function(module):
    if is_supported_instance(module):
        if hasattr(module, '__flops_handle__'):
            return

        if isinstance(module, (torch.nn.Conv1d, torch.nn.Conv2d, torch.nn.Conv3d)):
            handle = module.register_forward_hook(conv_flops_counter_hook)
        elif isinstance(module, (torch.nn.ReLU, torch.nn.PReLU, torch.nn.ELU, \
                                 torch.nn.LeakyReLU, torch.nn.ReLU6)):
            handle = module.register_forward_hook(relu_flops_counter_hook)
        elif isinstance(module, torch.nn.Linear):
            handle = module.register_forward_hook(linear_flops_counter_hook)
        elif isinstance(module, (torch.nn.AvgPool2d, torch.nn.MaxPool2d, nn.AdaptiveMaxPool2d, \
                                 nn.AdaptiveAvgPool2d, torch.nn.MaxPool3d, torch.nn.AvgPool3d, \
                                 torch.nn.AvgPool1d, torch.nn.MaxPool1d, nn.AdaptiveMaxPool1d, \
                                 nn.AdaptiveAvgPool1d, nn.AdaptiveMaxPool3d, nn.AdaptiveAvgPool3d)):
            handle = module.register_forward_hook(pool_flops_counter_hook)
        elif isinstance(module, (torch.nn.BatchNorm1d, torch.nn.BatchNorm2d, torch.nn.BatchNorm3d)):
            handle = module.register_forward_hook(bn_flops_counter_hook)
        elif isinstance(module, torch.nn.Upsample):
            handle = module.register_forward_hook(upsample_flops_counter_hook)
        elif isinstance(module, torch.nn.ConvTranspose2d):
            handle = module.register_forward_hook(deconv_flops_counter_hook)
        else:
            handle = module.register_forward_hook(empty_flops_counter_hook)
        module.__flops_handle__ = handle
Example #6
Source File: simple_spatial_temporal_module.py    From mmaction with Apache License 2.0 5 votes vote down vote up 
def __init__(self, spatial_type='avg', spatial_size=7, temporal_size=1):
        super(SimpleSpatialTemporalModule, self).__init__()

        assert spatial_type in ['avg', 'max']
        self.spatial_type = spatial_type

        self.spatial_size = spatial_size
        if spatial_size != -1:
            self.spatial_size = (spatial_size, spatial_size)

        self.temporal_size = temporal_size

        assert not (self.spatial_size == -1) ^ (self.temporal_size == -1)

        if self.temporal_size == -1 and self.spatial_size == -1:
            self.pool_size = (1, 1, 1)
            if self.spatial_type == 'avg':
                self.pool_func = nn.AdaptiveAvgPool3d(self.pool_size)
            if self.spatial_type == 'max':
                self.pool_func = nn.AdaptiveMaxPool3d(self.pool_size)
        else:
            self.pool_size = (self.temporal_size, ) + self.spatial_size
            if self.spatial_type == 'avg':
                self.pool_func = nn.AvgPool3d(self.pool_size, stride=1, padding=0)
            if self.spatial_type == 'max':
                self.pool_func = nn.MaxPool3d(self.pool_size, stride=1, padding=0)