Searched refs:net_loss (Results 1 – 13 of 13) sorted by relevance
/third_party/mindspore/mindspore/nn/probability/toolbox/ |
D | uncertainty_evaluation.py | 123 net_loss = SoftmaxCrossEntropyWithLogits( 126 model = Model(self.epi_uncer_model, net_loss, 129 net_loss = MSELoss() 131 model = Model(self.epi_uncer_model, net_loss, 178 net_loss = AleatoricLoss(self.task_type) 181 model = Model(self.ale_uncer_model, net_loss, 184 model = Model(self.ale_uncer_model, net_loss,
|
D | anomaly_detection.py | 58 net_loss = ELBO() 60 net_with_loss = WithLossCell(self.vae, net_loss)
|
/third_party/mindspore/tests/st/quantization/lenet_quant/ |
D | test_lenet_quant.py | 72 net_loss = nn.SoftmaxCrossEntropyWithLogits(sparse=True, reduction="mean") 82 model = Model(network, net_loss, net_opt, metrics={"Accuracy": Accuracy()}) 116 net_loss = nn.SoftmaxCrossEntropyWithLogits(sparse=True, reduction="mean") 121 model = Model(network, net_loss, net_opt, metrics={"Accuracy": Accuracy()})
|
/third_party/mindspore/tests/st/broadcast/ |
D | lenet_broadcast_auto_parallel.py | 54 net_loss = nn.SoftmaxCrossEntropyWithLogits(sparse=True, reduction="mean") 58 model = Model(network, net_loss, net_opt, metrics={"Accuracy": Accuracy()})
|
/third_party/mindspore/tests/st/probability/dpn/ |
D | test_gpu_svi_vae.py | 98 net_loss = ELBO(latent_prior='Normal', output_prior='Normal') 103 net_with_loss = nn.WithLossCell(vae, net_loss)
|
D | test_gpu_svi_cvae.py | 108 net_loss = ELBO(latent_prior='Normal', output_prior='Normal') 114 net_with_loss = CVAEWithLossCell(cvae, net_loss)
|
D | test_gpu_vae_gan.py | 160 net_loss = VaeGanLoss() 163 net_with_loss = nn.WithLossCell(vae_gan, net_loss)
|
/third_party/mindspore/tests/st/ps/full_ps/ |
D | test_full_ps_lenet.py | 127 net_loss = nn.SoftmaxCrossEntropyWithLogits(sparse=True, reduction="mean") variable 129 model = Model(network, net_loss, net_opt, metrics={"Accuracy": Accuracy()})
|
/third_party/mindspore/tests/st/probability/zhusuan/vae/ |
D | vae_mnist.py | 135 net_loss = ReduceMeanLoss() 141 model = Model(network, net_loss, net_opt)
|
/third_party/mindspore/tests/st/networks/ |
D | test_gradient_accumulation.py | 215 net_loss = nn.SoftmaxCrossEntropyWithLogits(sparse=True, reduction="mean") 217 model = GradientAccumulation(network, net_loss, net_opt)
|
D | test_gpu_lenet.py | 196 net_loss = nn.SoftmaxCrossEntropyWithLogits(sparse=True, reduction="mean") 198 model = Model(network, net_loss, net_opt, metrics={"Accuracy": Accuracy()})
|
/third_party/mindspore/tests/st/fl/cross_silo_femnist/ |
D | test_cross_silo_femnist.py | 306 net_loss = nn.SoftmaxCrossEntropyWithLogits(sparse=True, reduction='mean') 309 model = Model(network, net_loss, net_opt, metrics={"Accuracy": Accuracy(), 'Loss': nn.Loss()})
|
/third_party/mindspore/mindspore/nn/probability/ |
D | README.md | 225 net_loss = ELBO(latent_prior='Normal', output_prior='Normal') 227 net_with_loss = nn.WithLossCell(vae, net_loss)
|