API名称 |
是否支持 |
限制与说明 |
|---|---|---|
torch.nn.functional.conv1d |
||
torch.nn.functional.conv2d |
||
torch.nn.functional.conv3d |
||
torch.nn.functional.conv_transpose1d |
||
torch.nn.functional.conv_transpose2d |
||
torch.nn.functional.conv_transpose3d |
||
torch.nn.functional.unfold |
||
torch.nn.functional.fold |
||
torch.nn.functional.avg_pool1d |
||
torch.nn.functional.avg_pool2d |
||
torch.nn.functional.avg_pool3d |
||
torch.nn.functional.max_pool1d |
||
torch.nn.functional.max_pool2d |
||
torch.nn.functional.max_pool3d |
||
torch.nn.functional.max_unpool1d |
||
torch.nn.functional.max_unpool2d |
||
torch.nn.functional.max_unpool3d |
||
torch.nn.functional.lp_pool1d |
||
torch.nn.functional.lp_pool2d |
||
torch.nn.functional.adaptive_max_pool1d |
||
torch.nn.functional.adaptive_max_pool2d |
||
torch.nn.functional.adaptive_max_pool3d |
否 |
|
torch.nn.functional.adaptive_avg_pool1d |
||
torch.nn.functional.adaptive_avg_pool2d |
||
torch.nn.functional.adaptive_avg_pool3d |
||
torch.nn.functional.fractional_max_pool2d |
否 |
|
torch.nn.functional.fractional_max_pool3d |
否 |
|
torch.nn.functional.scaled_dot_product_attention |
否 |
|
torch.nn.functional.threshold |
||
torch.nn.functional.threshold_ |
||
torch.nn.functional.relu |
||
torch.nn.functional.relu_ |
||
torch.nn.functional.hardtanh |
||
torch.nn.functional.hardtanh_ |
||
torch.nn.functional.hardswish |
||
torch.nn.functional.relu6 |
||
torch.nn.functional.elu |
||
torch.nn.functional.elu_ |
||
torch.nn.functional.selu |
||
torch.nn.functional.celu |
||
torch.nn.functional.leaky_relu |
||
torch.nn.functional.leaky_relu_ |
||
torch.nn.functional.prelu |
||
torch.nn.functional.rrelu |
||
torch.nn.functional.rrelu_ |
||
torch.nn.functional.glu |
||
torch.nn.functional.gelu |
否 |
|
torch.nn.functional.logsigmoid |
||
torch.nn.functional.hardshrink |
||
torch.nn.functional.tanhshrink |
||
torch.nn.functional.softsign |
||
torch.nn.functional.softplus |
||
torch.nn.functional.softmin |
||
torch.nn.functional.softmax |
||
torch.nn.functional.softshrink |
||
torch.nn.functional.gumbel_softmax |
||
torch.nn.functional.log_softmax |
||
torch.nn.functional.tanh |
||
torch.nn.functional.sigmoid |
||
torch.nn.functional.hardsigmoid |
||
torch.nn.functional.silu |
||
torch.nn.functional.mish |
否 |
|
torch.nn.functional.batch_norm |
||
torch.nn.functional.group_norm |
否 |
|
torch.nn.functional.instance_norm |
||
torch.nn.functional.layer_norm |
||
torch.nn.functional.local_response_norm |
||
torch.nn.functional.normalize |
||
torch.nn.functional.linear |
||
torch.nn.functional.bilinear |
||
torch.nn.functional.dropout |
||
torch.nn.functional.alpha_dropout |
||
torch.nn.functional.feature_alpha_dropout |
||
torch.nn.functional.dropout1d |
否 |
|
torch.nn.functional.dropout2d |
||
torch.nn.functional.dropout3d |
||
torch.nn.functional.embedding |
||
torch.nn.functional.embedding_bag |
||
torch.nn.functional.one_hot |
||
torch.nn.functional.pairwise_distance |
||
torch.nn.functional.cosine_similarity |
||
torch.nn.functional.pdist |
||
torch.nn.functional.binary_cross_entropy |
||
torch.nn.functional.binary_cross_entropy_with_logits |
||
torch.nn.functional.poisson_nll_loss |
||
torch.nn.functional.cosine_embedding_loss |
||
torch.nn.functional.cross_entropy |
||
torch.nn.functional.ctc_loss |
||
torch.nn.functional.gaussian_nll_loss |
||
torch.nn.functional.hinge_embedding_loss |
||
torch.nn.functional.kl_div |
||
torch.nn.functional.l1_loss |
||
torch.nn.functional.mse_loss |
||
torch.nn.functional.margin_ranking_loss |
||
torch.nn.functional.multilabel_margin_loss |
||
torch.nn.functional.multilabel_soft_margin_loss |
||
torch.nn.functional.multi_margin_loss |
||
torch.nn.functional.nll_loss |
||
torch.nn.functional.huber_loss |
否 |
|
torch.nn.functional.smooth_l1_loss |
||
torch.nn.functional.soft_margin_loss |
||
torch.nn.functional.triplet_margin_loss |
||
torch.nn.functional.triplet_margin_with_distance_loss |
||
torch.nn.functional.pixel_shuffle |
||
torch.nn.functional.pixel_unshuffle |
||
torch.nn.functional.pad |
||
torch.nn.functional.interpolate |
||
torch.nn.functional.upsample |
||
torch.nn.functional.upsample_nearest |
||
torch.nn.functional.upsample_bilinear |
||
torch.nn.functional.grid_sample |
||
torch.nn.functional.affine_grid |
||
torch.nn.parallel.data_parallel |
否 |