Fixed the docstring for Huber and SmoothL1 loss
This commit is contained in:
@@ -117,12 +117,12 @@
|
||||
| [Ptn BCE Loss](ptn_bce_loss.md) | A class to compute the binary cross entropy loss. |
|
||||
| [Ptn BCE With Logits Loss](ptn_bce_with_logits_loss.md) | A class to compute the sigmoid then binary cross entropy loss. |
|
||||
| [Ptn Cross Entropy Loss](ptn_cross_entropy_loss.md) | A class to compute the cross entropy loss. |
|
||||
| [Ptn Huber Loss](ptn_huber_loss.md) | |
|
||||
| [Ptn Huber Loss](ptn_huber_loss.md) | A class to compute the Huber loss. |
|
||||
| [Ptn KL Div Loss](ptn_kl_div_loss.md) | A class to compute the KL divergence loss. |
|
||||
| [Ptn L1 Loss](ptn_l1_loss.md) | A class to compute the L1 loss. |
|
||||
| [Ptn MSE Loss](ptn_mse_loss.md) | A class to compute the squared loss. |
|
||||
| [Ptn NLL Loss](ptn_nll_loss.md) | A model to compute the negative log likelihood (NLL) loss. |
|
||||
| [Ptn Smooth L1 Loss](ptn_smooth_l1_loss.md) | |
|
||||
| [Ptn Smooth L1 Loss](ptn_smooth_l1_loss.md) | A class to compute the Smooth L1 loss. |
|
||||
## PyTorch wrapper - Math operations
|
||||
| Node | Description |
|
||||
| --- | --- |
|
||||
|
||||
@@ -12,7 +12,7 @@ Unlike the Ptn BCE Loss With Logits node, which takes logits as input, this node
|
||||
## Input
|
||||
| Name | Data type |
|
||||
|---|---|
|
||||
| reduction | Mean |
|
||||
| reduction | |
|
||||
|
||||
## Output
|
||||
| Data type |
|
||||
|
||||
@@ -10,7 +10,7 @@ A class to compute the sigmoid then binary cross entropy loss.
|
||||
## Input
|
||||
| Name | Data type |
|
||||
|---|---|
|
||||
| reduction | Mean |
|
||||
| reduction | |
|
||||
|
||||
## Output
|
||||
| Data type |
|
||||
|
||||
@@ -12,7 +12,7 @@ Unlike Ptn NLL Loss node which takes log probabilities for input, input to this
|
||||
## Input
|
||||
| Name | Data type |
|
||||
|---|---|
|
||||
| reduction | Mean |
|
||||
| reduction | |
|
||||
|
||||
## Output
|
||||
| Data type |
|
||||
|
||||
@@ -14,7 +14,7 @@ Please see [PyTorch documentation](https://pytorch.org/docs/stable/generated/tor
|
||||
## Input
|
||||
| Name | Data type |
|
||||
|---|---|
|
||||
| reduction | Mean |
|
||||
| reduction | |
|
||||
| delta | Float |
|
||||
|
||||
## Output
|
||||
|
||||
@@ -14,7 +14,7 @@ A class to compute the KL divergence loss.
|
||||
## Input
|
||||
| Name | Data type |
|
||||
|---|---|
|
||||
| reduction | None |
|
||||
| reduction | |
|
||||
| log_target | Boolean |
|
||||
|
||||
## Output
|
||||
|
||||
@@ -10,7 +10,7 @@ A class to compute the L1 loss.
|
||||
## Input
|
||||
| Name | Data type |
|
||||
|---|---|
|
||||
| reduction | Mean |
|
||||
| reduction | |
|
||||
|
||||
## Output
|
||||
| Data type |
|
||||
|
||||
@@ -10,7 +10,7 @@ A class to compute the squared loss.
|
||||
## Input
|
||||
| Name | Data type |
|
||||
|---|---|
|
||||
| reduction | Mean |
|
||||
| reduction | |
|
||||
|
||||
## Output
|
||||
| Data type |
|
||||
|
||||
@@ -12,7 +12,7 @@ Unlike Ptn Cross Entropy which takes input in logits, input to this nodes needs
|
||||
## Input
|
||||
| Name | Data type |
|
||||
|---|---|
|
||||
| reduction | Mean |
|
||||
| reduction | |
|
||||
|
||||
## Output
|
||||
| Data type |
|
||||
|
||||
@@ -14,7 +14,7 @@ Please see [PyTorch documentation](https://pytorch.org/docs/stable/generated/tor
|
||||
## Input
|
||||
| Name | Data type |
|
||||
|---|---|
|
||||
| reduction | Mean |
|
||||
| reduction | |
|
||||
| beta | Float |
|
||||
|
||||
## Output
|
||||
|
||||
@@ -6,7 +6,6 @@ import torch.nn as nn
|
||||
class PtnHuberLoss:
|
||||
"""
|
||||
Ptn Huber Loss:
|
||||
|
||||
A class to compute the Huber loss.
|
||||
|
||||
Please see [PyTorch documentation](https://pytorch.org/docs/stable/generated/torch.nn.HuberLoss.html) for details.
|
||||
|
||||
@@ -6,7 +6,6 @@ import torch.nn as nn
|
||||
class PtnSmoothL1Loss:
|
||||
"""
|
||||
Ptn Smooth L1 Loss:
|
||||
|
||||
A class to compute the Smooth L1 loss.
|
||||
|
||||
Please see [PyTorch documentation](https://pytorch.org/docs/stable/generated/torch.nn.SmoothL1Loss.html) for details and exact formulation.
|
||||
|
||||
Reference in New Issue
Block a user