forked from tinygrad/tinygrad
remove broken paperswithcode links in doc (#11497)
This commit is contained in:
chenyu
@@ -10,7 +10,6 @@ class BatchNorm:
|
||||
"""
|
||||
Applies Batch Normalization over a 2D or 3D input.
|
||||
|
||||
- Described: https://paperswithcode.com/method/batch-normalization
|
||||
- Paper: https://arxiv.org/abs/1502.03167v3
|
||||
|
||||
See: `Tensor.batchnorm`
|
||||
@@ -182,7 +181,6 @@ class GroupNorm:
|
||||
"""
|
||||
Applies Group Normalization over a mini-batch of inputs.
|
||||
|
||||
- Described: https://paperswithcode.com/method/group-normalization
|
||||
- Paper: https://arxiv.org/abs/1803.08494v3
|
||||
|
||||
```python exec="true" source="above" session="tensor" result="python"
|
||||
@@ -213,7 +211,6 @@ class InstanceNorm:
|
||||
"""
|
||||
Applies Instance Normalization over a mini-batch of inputs.
|
||||
|
||||
- Described: https://paperswithcode.com/method/instance-normalization
|
||||
- Paper: https://arxiv.org/abs/1607.08022v3
|
||||
|
||||
```python exec="true" source="above" session="tensor" result="python"
|
||||
@@ -240,7 +237,6 @@ class LayerNorm:
|
||||
"""
|
||||
Applies Layer Normalization over a mini-batch of inputs.
|
||||
|
||||
- Described: https://paperswithcode.com/method/layer-normalization
|
||||
- Paper: https://arxiv.org/abs/1607.06450v1
|
||||
|
||||
```python exec="true" source="above" session="tensor" result="python"
|
||||
@@ -287,7 +283,6 @@ class RMSNorm:
|
||||
"""
|
||||
Applies Root Mean Square Normalization to input.
|
||||
|
||||
- Described: https://paperswithcode.com/method/rmsnorm
|
||||
- Paper: https://arxiv.org/abs/1910.07467
|
||||
|
||||
```python exec="true" source="above" session="tensor" result="python"
|
||||
|
||||
@@ -76,8 +76,6 @@ def SGD(params: list[Tensor], lr=0.001, momentum=0.0, weight_decay=0.0, nesterov
|
||||
Stochastic Gradient Descent (SGD) optimizer with optional momentum and weight decay.
|
||||
|
||||
`classic` is a boolean flag that determines whether to use the popular momentum update rule or the classic momentum update rule.
|
||||
|
||||
- Described: https://paperswithcode.com/method/sgd
|
||||
"""
|
||||
return LARS(params, lr, momentum, weight_decay, nesterov, classic, tcoef=0.0, fused=fused)
|
||||
|
||||
@@ -85,7 +83,6 @@ class LARS(Optimizer):
|
||||
"""
|
||||
Layer-wise Adaptive Rate Scaling (LARS) optimizer with optional momentum and weight decay.
|
||||
|
||||
- Described: https://paperswithcode.com/method/lars
|
||||
- Paper: https://arxiv.org/abs/1708.03888v3
|
||||
"""
|
||||
def __init__(self, params:list[Tensor], lr=0.001, momentum=0.9, weight_decay=1e-4, nesterov=False, classic=True, tcoef=0.001, fused=FUSE_OPTIM):
|
||||
@@ -119,7 +116,6 @@ def AdamW(params: list[Tensor], lr=0.001, b1=0.9, b2=0.999, eps=1e-8, weight_dec
|
||||
"""
|
||||
AdamW optimizer with optional weight decay.
|
||||
|
||||
- Described: https://paperswithcode.com/method/adamw
|
||||
- Paper: https://arxiv.org/abs/1711.05101v3
|
||||
"""
|
||||
return LAMB(params, lr, b1, b2, eps, weight_decay, adam=True, fused=fused)
|
||||
@@ -127,7 +123,6 @@ def Adam(params: list[Tensor], lr=0.001, b1=0.9, b2=0.999, eps=1e-8, fused=FUSE_
|
||||
"""
|
||||
Adam optimizer.
|
||||
|
||||
- Described: https://paperswithcode.com/method/adam
|
||||
- Paper: https://arxiv.org/abs/1412.6980
|
||||
"""
|
||||
return LAMB(params, lr, b1, b2, eps, 0.0, adam=True, fused=fused)
|
||||
@@ -136,7 +131,6 @@ class LAMB(Optimizer):
|
||||
"""
|
||||
LAMB optimizer with optional weight decay.
|
||||
|
||||
- Described: https://paperswithcode.com/method/lamb
|
||||
- Paper: https://arxiv.org/abs/1904.00962
|
||||
"""
|
||||
def __init__(self, params: list[Tensor], lr=0.001, b1=0.9, b2=0.999, eps=1e-6, weight_decay=0.0, adam=False, fused=FUSE_OPTIM):
|
||||
|
||||
@@ -2332,8 +2332,6 @@ class Tensor(MathTrait):
|
||||
|
||||
NOTE: unlike PyTorch, this implementation is not limited to only 2d pooling and instead works for any number of dimensions.
|
||||
|
||||
See: https://paperswithcode.com/method/average-pooling
|
||||
|
||||
```python exec="true" source="above" session="tensor" result="python"
|
||||
t = Tensor.arange(25).reshape(1, 1, 5, 5)
|
||||
print(t.avg_pool2d().numpy())
|
||||
@@ -2380,8 +2378,6 @@ class Tensor(MathTrait):
|
||||
|
||||
NOTE: unlike PyTorch, this implementation is not limited to only 2d pooling and instead works for any number of dimensions.
|
||||
|
||||
See: https://paperswithcode.com/method/max-pooling
|
||||
|
||||
```python exec="true" source="above" session="tensor" result="python"
|
||||
t = Tensor.arange(25).reshape(1, 1, 5, 5)
|
||||
print(t.max_pool2d().numpy())
|
||||
@@ -3010,8 +3006,6 @@ class Tensor(MathTrait):
|
||||
"""
|
||||
Applies the Rectified Linear Unit (ReLU) function element-wise.
|
||||
|
||||
- Described: https://paperswithcode.com/method/relu
|
||||
|
||||
```python exec="true" source="above" session="tensor" result="python"
|
||||
print(Tensor([-3., -2., -1., 0., 1., 2., 3.]).relu().numpy())
|
||||
```
|
||||
@@ -3048,7 +3042,6 @@ class Tensor(MathTrait):
|
||||
Applies the Hardsigmoid function element-wise.
|
||||
NOTE: default `alpha` and `beta` values are taken from torch
|
||||
|
||||
- Described: https://paperswithcode.com/method/hard-sigmoid
|
||||
- See: https://pytorch.org/docs/stable/generated/torch.nn.functional.hardsigmoid.html
|
||||
|
||||
```python exec="true" source="above" session="tensor" result="python"
|
||||
@@ -3291,7 +3284,6 @@ class Tensor(MathTrait):
|
||||
"""
|
||||
Applies the Exponential Linear Unit (ELU) function element-wise.
|
||||
|
||||
- Described: https://paperswithcode.com/method/elu
|
||||
- Paper: https://arxiv.org/abs/1511.07289v5
|
||||
|
||||
```python exec="true" source="above" session="tensor" result="python"
|
||||
@@ -3304,7 +3296,6 @@ class Tensor(MathTrait):
|
||||
"""
|
||||
Applies the Continuously differentiable Exponential Linear Unit (CELU) function element-wise.
|
||||
|
||||
- Described: https://paperswithcode.com/method/celu
|
||||
- Paper: https://arxiv.org/abs/1704.07483
|
||||
|
||||
```python exec="true" source="above" session="tensor" result="python"
|
||||
@@ -3317,7 +3308,6 @@ class Tensor(MathTrait):
|
||||
"""
|
||||
Applies the Scaled Exponential Linear Unit (SELU) function element-wise.
|
||||
|
||||
- Described: https://paperswithcode.com/method/selu
|
||||
- Paper: https://arxiv.org/abs/1706.02515v5
|
||||
|
||||
```python exec="true" source="above" session="tensor" result="python"
|
||||
@@ -3342,7 +3332,6 @@ class Tensor(MathTrait):
|
||||
"""
|
||||
Applies the Sigmoid Linear Unit (SiLU) function element-wise.
|
||||
|
||||
- Described: https://paperswithcode.com/method/silu
|
||||
- Paper: https://arxiv.org/abs/1606.08415
|
||||
|
||||
```python exec="true" source="above" session="tensor" result="python"
|
||||
@@ -3355,7 +3344,6 @@ class Tensor(MathTrait):
|
||||
"""
|
||||
Applies the ReLU6 function element-wise.
|
||||
|
||||
- Described: https://paperswithcode.com/method/relu6
|
||||
- Paper: https://arxiv.org/abs/1704.04861v1
|
||||
|
||||
```python exec="true" source="above" session="tensor" result="python"
|
||||
@@ -3368,7 +3356,6 @@ class Tensor(MathTrait):
|
||||
"""
|
||||
Applies the Hardswish function element-wise.
|
||||
|
||||
- Described: https://paperswithcode.com/method/hard-swish
|
||||
- Paper: https://arxiv.org/abs/1905.02244v5
|
||||
|
||||
```python exec="true" source="above" session="tensor" result="python"
|
||||
@@ -3453,8 +3440,6 @@ class Tensor(MathTrait):
|
||||
"""
|
||||
Applies the Hardtanh function element-wise.
|
||||
|
||||
- Described: https://paperswithcode.com/method/hardtanh-activation
|
||||
|
||||
```python exec="true" source="above" session="tensor" result="python"
|
||||
print(Tensor([-1.5, -1.0, -0.5, 0., 0.5, 1.0, 1.5]).hardtanh().numpy())
|
||||
```
|
||||
@@ -3479,7 +3464,6 @@ class Tensor(MathTrait):
|
||||
"""
|
||||
Applies the Gaussian Error Linear Unit (GELU) function element-wise.
|
||||
|
||||
- Described: https://paperswithcode.com/method/gelu
|
||||
- Paper: https://arxiv.org/abs/1606.08415v5
|
||||
|
||||
```python exec="true" source="above" session="tensor" result="python"
|
||||
@@ -3492,8 +3476,6 @@ class Tensor(MathTrait):
|
||||
"""
|
||||
Applies the Sigmoid GELU approximation element-wise.
|
||||
|
||||
- Described: https://paperswithcode.com/method/gelu
|
||||
|
||||
```python exec="true" source="above" session="tensor" result="python"
|
||||
print(Tensor([-3., -2., -1., 0., 1., 2., 3.]).quick_gelu().numpy())
|
||||
```
|
||||
@@ -3504,8 +3486,6 @@ class Tensor(MathTrait):
|
||||
"""
|
||||
Applies the Leaky ReLU function element-wise.
|
||||
|
||||
- Described: https://paperswithcode.com/method/leaky-relu
|
||||
|
||||
```python exec="true" source="above" session="tensor" result="python"
|
||||
print(Tensor([-3., -2., -1., 0., 1., 2., 3.]).leaky_relu().numpy())
|
||||
```
|
||||
@@ -3519,7 +3499,6 @@ class Tensor(MathTrait):
|
||||
"""
|
||||
Applies the Mish function element-wise.
|
||||
|
||||
- Described: https://paperswithcode.com/method/mish
|
||||
- Paper: https://arxiv.org/abs/1908.08681v3
|
||||
|
||||
```python exec="true" source="above" session="tensor" result="python"
|
||||
@@ -3532,8 +3511,6 @@ class Tensor(MathTrait):
|
||||
"""
|
||||
Applies the Softplus function element-wise.
|
||||
|
||||
- Described: https://paperswithcode.com/method/softplus
|
||||
|
||||
```python exec="true" source="above" session="tensor" result="python"
|
||||
print(Tensor([-3., -2., -1., 0., 1., 2., 3.]).softplus().numpy())
|
||||
```
|
||||
@@ -3544,8 +3521,6 @@ class Tensor(MathTrait):
|
||||
"""
|
||||
Applies the Softsign function element-wise.
|
||||
|
||||
- Described: https://paperswithcode.com/method/softsign
|
||||
|
||||
```python exec="true" source="above" session="tensor" result="python"
|
||||
print(Tensor([-3., -2., -1., 0., 1., 2., 3.]).softsign().numpy())
|
||||
```
|
||||
@@ -3839,7 +3814,6 @@ class Tensor(MathTrait):
|
||||
"""
|
||||
Applies Layer Normalization over a mini-batch of inputs.
|
||||
|
||||
- Described: https://paperswithcode.com/method/layer-normalization
|
||||
- Paper: https://arxiv.org/abs/1607.06450v1
|
||||
|
||||
```python exec="true" source="above" session="tensor" result="python"
|
||||
@@ -3858,7 +3832,6 @@ class Tensor(MathTrait):
|
||||
"""
|
||||
Applies Batch Normalization over a mini-batch of inputs.
|
||||
|
||||
- Described: https://paperswithcode.com/method/batch-normalization
|
||||
- Paper: https://arxiv.org/abs/1502.03167
|
||||
|
||||
```python exec="true" source="above" session="tensor" result="python"
|
||||
@@ -3883,7 +3856,6 @@ class Tensor(MathTrait):
|
||||
|
||||
NOTE: dropout is only applied when `Tensor.training` is `True`.
|
||||
|
||||
- Described: https://paperswithcode.com/method/dropout
|
||||
- Paper: https://jmlr.org/papers/v15/srivastava14a.html
|
||||
|
||||
```python exec="true" source="above" session="tensor" result="python"
|
||||
@@ -3925,7 +3897,6 @@ class Tensor(MathTrait):
|
||||
Computes scaled dot-product attention.
|
||||
`self` is the query tensor, `key` is the key tensor, and `value` is the value tensor.
|
||||
|
||||
- Described: https://paperswithcode.com/method/scaled
|
||||
- Paper: https://arxiv.org/abs/1706.03762v7
|
||||
|
||||
```python exec="true" source="above" session="tensor" result="python"
|
||||
|
||||
Reference in New Issue
Block a user