wassname/ml-debug
1
0
Fork 0
mirror of https://github.com/wassname/ml-debug.git synced 2026-06-27 17:31:04 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix: apply Gemini review fixes (device kwarg, gradcheck requires_grad, torch prefix)

Browse Source 
Review: Gemini 3.1 Pro approved. 3 fixes applied:
- pinn/SKILL.md: PchipFunction torch.tensor missing device=h.device (GPU crash)
- SKILL.md: gradcheck needs .requires_grad_(True) on doubled inputs
- SKILL.md: loss surface pseudocode now has torch. prefix + indexing='ij'
This commit is contained in:
wassname
2026-03-06 12:15:37 +08:00
parent 2db012dd2c
commit 463c8fdbbc
2 changed files with 7 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files
pinn/SKILL.md
+3 -3
View File
@@ -281,13 +281,13 @@ For heat exchangers with phase change, the T(h) mapping from REFPROP/GERG-2008 m
def forward(ctx, h):
T = pchip_interp(h.detach().numpy()) # scipy
ctx.save_for_backward(h)
return torch.tensor(T, dtype=h.dtype)
return torch.tensor(T, dtype=h.dtype, device=h.device)
@staticmethod
def backward(ctx, grad_output):
h, = ctx.saved_tensors
dTdh = pchip_interp.derivative()(h.detach().numpy()) # scipy
return grad_output * torch.tensor(dTdh, dtype=h.dtype)
dTdh = pchip_interp.derivative()(h.detach().cpu().numpy()) # scipy
return grad_output * torch.tensor(dTdh, dtype=h.dtype, device=h.device)
```
5. Use float64 throughout. float32 loses precision near the phase boundary where dT/dh is small.