torch.nn.SmoothL1Loss(*size_average=None*, *reduce=None*, *reduction='mean'*, *beta=1.0*) torch.nn.functional.smooth_l1_loss(*input*, *target*, *size_average=None*, *reduce=None*, *reduction='mean'*, *beta=1.0*) import torch loss = torch.nn.SmoothL1Loss() input = torch.randn(...
torch.nn.functional.conv_transpose2d(input, weight, bias=None, stride=1, padding=0, output_padding=0, groups=1, dilation=1)→ Tensorsource在由几个输入平面组成的输入图像上应用2D转置卷积,有时也被称为去卷积。 有关详细信息和输出形状,参考ConvTranspose2d。
torch.nn.functional.max_unpool2d(input, indices, kernel_size, stride=None, padding=0, output_size=None) torch.nn.functional.max_unpool3d(input, indices, kernel_size, stride=None, padding=0, output_size=None) torch.nn.functional.lp_pool2d(input, norm_type, kernel_size, stride=None, ceil...
损失函数(Loss functions) Vision functions) Convolution 函数 torch.nn.functional.conv1d(input, weight, bias=None, stride=1, padding=0, dilation=1, groups=1) 对由几个输入平面组成的输入信号应用一维卷积。 详细信息和输出形状,查看Conv1d 参数: ...
expand_as(gt_regr).float() regr = regr * mask gt_regr = gt_regr * mask regr_loss = nn.functional.smooth_l1_loss(regr, gt_regr, size_average=False) regr_loss = regr_loss / (num + 1e-4) return regr_loss Example #8Source File: DQN.py From BCQ with MIT License 6 votes def...
smooth_l1_loss¶ torch.nn.functional.smooth_l1_loss(input, target, size_average=None, reduce=None, reduction='mean', beta=1.0)[source]¶ Function that uses a squared term if the absolute element-wise error falls below beta and an L1 term otherwise. See SmoothL1Loss for details. soft_...
torch.nn.functional.conv3d(input, weight, bias=None, stride=1, padding=0, dilation=1, groups=1) 对几个输入平面组成的输入信号应用3D卷积。 有关详细信息和输出形状,请参见Conv3d。 参数: - input – 输入张量的形状 (minibatch x in_channels x iT x iH x iW) ...
()torch.nn.functional.hardsigmoid()torch.nn.functional.hardswish()torch.nn.functional.hardtanh()torch.nn.functional.hardtanh_()torch.nn.functional.hinge_embedding_loss()torch.nn.functional.instance_norm()torch.nn.functional.interpolate()torch.nn.functional.kl_div()torch.nn.functional.l1_loss()Show...
torch.nn.functional.unfold Unsupported. 8 torch.nn.functional.fold Unsupported. 9 torch.nn.functional.avg_pool1d Supported 10 torch.nn.functional.avg_pool2d Supported 11 torch.nn.functional.avg_pool3d Unsupported. 12 torch.nn.functional.max_pool1d ...
torch.nn.SmoothL1Loss Supported 175 torch.nn.SoftMarginLoss Unsupported. 176 torch.nn.MultiLabelSoftMarginLoss Supported 177 torch.nn.CosineEmbeddingLoss Supported 178 torch.nn.MultiMarginLoss Unsupported. 179 torch.nn.TripletMarginLoss Supported 180 torch.nn.PixelShuffle Supported ...