Fix docs typos

Author: qubvel

README.md

@@ -46,8 +46,8 @@ import segmentation_models_pytorch as smp
 
 model = smp.Unet(
     encoder_name="resnet34",        # choose encoder, e.g. mobilenet_v2 or efficientnet-b7
-    encoder_weights="imagenet",     # use `imagenet` pretrained weights for encoder initialization
-    in_channels=1,                  # model input channels (1 for grayscale images, 3 for RGB, etc.)
+    encoder_weights="imagenet",     # use `imagenet` pre-trained weights for encoder initialization
+    in_channels=1,                  # model input channels (1 for gray-scale images, 3 for RGB, etc.)
     classes=3,                      # model output channels (number of classes in your dataset)
 )
 ```
@@ -56,7 +56,7 @@ model = smp.Unet(
 
 #### 2. Configure data preprocessing
 
-All encoders have pretrained weights. Preparing your data the same way as during weights pretraining may give your better results (higher metric score and faster convergence). But it is relevant only for 1-2-3-channels images and **not necessary** in case you train the whole model, not only decoder.
+All encoders have pretrained weights. Preparing your data the same way as during weights pre-training may give your better results (higher metric score and faster convergence). But it is relevant only for 1-2-3-channels images and **not necessary** in case you train the whole model, not only decoder.
 
 ```python
 from segmentation_models_pytorch.encoders import get_preprocessing_fn

docs/insights.rst

@@ -15,8 +15,8 @@ All segmentation models in SMP (this library short name) are made of:
 2. Creating your own encoder
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-Encoder is a "classification model" which extarct features from image and pass it to decoder.
-Each encoder should have following attributes and methods and be inherited from `segmetation_models_pytorch.encoders._base.EncoderMixin`
+Encoder is a "classification model" which extract features from image and pass it to decoder.
+Each encoder should have following attributes and methods and be inherited from `segmentation_models_pytorch.encoders._base.EncoderMixin`
 
 .. code-block:: python
 
@@ -29,13 +29,13 @@ Each encoder should have following attributes and methods and be inherited from
             self._out_channels: List[int] = [3, 16, 64, 128, 256, 512]
 
             # A number of stages in decoder (in other words number of downsampling operations), integer
-            # use in in forward pass to reduce number of returning fatures
+            # use in in forward pass to reduce number of returning features
             self._depth: int = 5 
 
             # Default number of input channels in first Conv2d layer for encoder (usually 3)
             self._in_channels: int = 3 
             
-            # Define enoder modules below
+            # Define encoder modules below
             ...
 
         def forward(self, x: torch.Tensor) -> List[torch.Tensor]:
@@ -60,7 +60,7 @@ When you write your own Encoder class register its build parameters
 .. code-block:: python
 
     smp.encoders.encoders["my_awesome_encoder"] = {
-        "encoder": MyEncoder, # enocoder class here
+        "encoder": MyEncoder, # encoder class here
         "pretrained_settings": {
             "imagenet": {
                 "mean": [0.485, 0.456, 0.406],

docs/quickstart.rst

@@ -11,8 +11,8 @@ Segmentation model is just a PyTorch nn.Module, which can be created as easy as:
 
     model = smp.Unet(
         encoder_name="resnet34",        # choose encoder, e.g. mobilenet_v2 or efficientnet-b7
-        encoder_weights="imagenet",     # use `imagenet` pretreined weights for encoder initialization
-        in_channels=1,                  # model input channels (1 for grayscale images, 3 for RGB, etc.)
+        encoder_weights="imagenet",     # use `imagenet` pre-trained weights for encoder initialization
+        in_channels=1,                  # model input channels (1 for gray-scale images, 3 for RGB, etc.)
         classes=3,                      # model output channels (number of classes in your dataset)
     )
 
@@ -21,7 +21,7 @@ Segmentation model is just a PyTorch nn.Module, which can be created as easy as:
 
 **2. Configure data preprocessing**
 
-All encoders have pretrained weights. Preparing your data the same way as during weights pretraining may give your better results (higher metric score and faster convergence). But it is relevant only for 1-2-3-channels images and **not necessary** in case you train the whole model, not only decoder.
+All encoders have pretrained weights. Preparing your data the same way as during weights pre-training may give your better results (higher metric score and faster convergence). But it is relevant only for 1-2-3-channels images and **not necessary** in case you train the whole model, not only decoder.
 
 .. code-block:: python
 

segmentation_models_pytorch/losses/constants.py

@@ -1,6 +1,6 @@
 #: Loss binary mode suppose you are solving binary segmentation task.
 #: That mean yor have only one class which pixels are labled as **1**,
-#: the rest pixels are backgroud and labeled as **0**.
+#: the rest pixels are background and labeled as **0**.
 #: Target mask shape - (N, H, W), model output mask shape (N, 1, H, W).
 BINARY_MODE: str = "binary"
 

segmentation_models_pytorch/losses/dice.py

@@ -31,8 +31,8 @@ def __init__(
             from_logits: If True, assumes input is raw logits
             smooth: Smoothness constant for dice coefficient (a)
             ignore_index: Label that indicates ignored pixels (does not contribute to loss)
-            eps: A small epsilon for numerical stability to avoid zero divison error 
-                (denominator wiil be always greater or equal to eps)
+            eps: A small epsilon for numerical stability to avoid zero division error 
+                (denominator will be always greater or equal to eps)
 
         Shape
              - **y_pred** - torch.Tensor of shape (N, C, H, W)

segmentation_models_pytorch/losses/focal.py

@@ -26,7 +26,7 @@ def __init__(
         Args:
             mode: Loss mode 'binary', 'multiclass' or 'multilabel'
             alpha: Prior probability of having positive value in target.
-            gamma: Power factor for dampening weight (focal strenght).
+            gamma: Power factor for dampening weight (focal strength).
             ignore_index: If not None, targets may contain values to be ignored.
                 Target values equal to ignore_index will be ignored from loss computation.
             normalized: Compute normalized focal loss (https://arxiv.org/pdf/1909.07829.pdf).

segmentation_models_pytorch/losses/jaccard.py

@@ -30,8 +30,8 @@ def __init__(
             from_logits: If True, assumes input is raw logits
             smooth: Smoothness constant for dice coefficient
             ignore_index: Label that indicates ignored pixels (does not contribute to loss)
-            eps: A small epsilon for numerical stability to avoid zero divison error 
-                (denominator wiil be always greater or equal to eps)
+            eps: A small epsilon for numerical stability to avoid zero division error 
+                (denominator will be always greater or equal to eps)
 
         Shape
              - **y_pred** - torch.Tensor of shape (N, C, H, W)

segmentation_models_pytorch/losses/lovasz.py

@@ -55,7 +55,7 @@ def _lovasz_hinge(logits, labels, per_image=True, ignore=None):
 def _lovasz_hinge_flat(logits, labels):
     """Binary Lovasz hinge loss
     Args:
-        logits: [P] Variable, logits at each prediction (between -iinfinity and +iinfinity)
+        logits: [P] Variable, logits at each prediction (between -infinity and +infinity)
         labels: [P] Tensor, binary ground truth labels (0 or 1)
         ignore: label to ignore
     """