J.-C. Jiang
J.-C. Jiang
Upon attempting to run tutorials on the CPU device, I encountered the following error: `RuntimeError: Expected all tensors to be on the same device, but found at least two devices,...
In the `KAN.train` function, the dataset is sent to the device within the function. However, for `KAN.initialize_from_another_model`, the dataset needs to be sent before calling the function. This PR allows...
In issues #105, #113 and #127, it was discovered that using input data type Double (np.float64) resulted in a `RuntimeError: expected scalar type Double but found Float`. This PR proposes...
Make support to colab. It will fix Issue #4. Also due to YouTube API quota limit (6 videos/day), I also make some configuration changes to support multiple Clients.
The equation 114 contains an additional slicing operator that triggers an exception when attempting to create a dataset.
### Description **Add PyTorch-style complex number support**, including: #### 1. Data Types - `complex32` (2xfloat16) - `complex64` (2×float32) - `complex128` (2×float64) #### 2. Tensor Creation from PyTorch ```python x =...