*.pt
For coil dataset，the shape of one data is [160,160,5]
For transformer dataset，the shape of one data is [400,400,5]
For IPM motor dataset，the shape of one data is [180,180,5]
The first five layers consist of input device property information, while the sixth layer represents the FEA magnetic field distribution results.
When using, please note to split the dataset into two parts, with x being transformed as follows:
X = data[:, :, :5]
X = np.transpose(X, (2, 0, 1))
X = torch.from_numpy(X)
, and y being transformed as follows:
- Categories:
272 Views
Each dataset is splitted by trainset, devset and testset.
Please read them with pytorch.
- Categories:
1066 Views
Data augmentation is commonly used to increase the size and diversity of the datasets in machine learning. It is of particular importance to evaluate the robustness of the existing machine learning methods. With progress in geometrical and 3D machine learning, many methods exist to augment a 3D object, from the generation of random orientations to exploring different perspectives of an object. In high-precision applications, the machine learning model must be robust with respect to the small perturbations of the input object.
- Categories:
214 Views