refine_flowvision

README.md

@@ -221,9 +221,9 @@ We have conducted all the tests under the same setting, please refer to the mode
 
 ## Quick Start
 ### Create a model
-In flowvision we support two ways to create a model.
+FlowVision supports two ways to create a model:
 
-- Import the target model from `flowvision.models`, e.g., create `alexnet` from flowvision
+- Import the target model from `flowvision.models`, e.g., create `alexnet` from FlowVision
 
 ```python
 from flowvision.models.alexnet import alexnet
@@ -284,8 +284,8 @@ You can get the results like:
 ╘════════════════════════════════════════════╧══════════════╛
 ```
 
-### Search for supported model by Wildcard
-It is easy to search for model architectures by using Wildcard as below:
+### Search for supported model by wildcard
+It is easy to search for model architectures by using wildcard as below:
 ```python
 from flowvision.models import ModelCreator
 all_efficientnet_models = ModelCreator.model_table("**efficientnet**")
@@ -314,8 +314,8 @@ You can get the results like:
 ╘════════════════════╧══════════════╛
 ```
 
-### List all models supported in flowvision
-`ModelCreator.model_list` has similar function as `ModelCreator.model_table` but return a list object, which gives the user a more flexible way to check the supported model in flowvision.
+### List all models supported in FlowVision
+`ModelCreator.model_list` has similar function as `ModelCreator.model_table` but returns a list object, which gives the user a more flexible way to check the supported model in flowvision.
 - List all models with pretrained weights
 ```python
 from flowvision.models import ModelCreator

docs/README.md

@@ -1,7 +1,7 @@
 
 ## Steps for Build Docs
 
-Before generating the doc, you need to install flowvision by:
+Before generating the doc, you need to install FlowVision by:
 
 ```bash
 cd ${flow-vision-path}

docs/source/tutorials/Getting Started.md

@@ -1,7 +1,7 @@
 # Getting Started
 
 ## Installation
-- To install latest stable release of flowvision:
+- To install the latest stable release of FlowVision:
 ```bash
 pip install flowvision==0.1.0
 ```
@@ -14,9 +14,9 @@ pip install -e .
 
 ## Usage
 ### Create a model
-In flowvision we support two ways to create a model.
+FlowVision supports two ways to create a model:
 
-- Import the target model from `flowvision.models`, e.g., create `alexnet` from flowvision
+- Import the target model from `flowvision.models`, e.g., create `alexnet` from FlowVision
 
 ```python
 from flowvision.models.alexnet import alexnet
@@ -77,8 +77,8 @@ You can get the results like:
 ╘════════════════════════════════════════════╧══════════════╛
 ```
 
-### Search for supported model by Wildcard
-It is easy to search for model architectures by using Wildcard as below:
+### Search for the supported model by wildcard
+It is easy to search for model architectures by using wildcard as below:
 ```python
 from flowvision.models import ModelCreator
 all_efficientnet_models = ModelCreator.model_table("**efficientnet**")
@@ -107,8 +107,8 @@ You can get the results like:
 ╘════════════════════╧══════════════╛
 ```
 
-### List all models supported in flowvision
-`ModelCreator.model_list` has similar function as `ModelCreator.model_table` but return a list object, which gives the user a more flexible way to check the supported model in flowvision.
+### List all models supported in FlowVision
+`ModelCreator.model_list` has a similar function as `ModelCreator.model_table` but returns a list object, which gives the user a more flexible way to check the supported model in FlowVision.
 - List all models with pretrained weights
 ```python
 from flowvision.models import ModelCreator

flowvision/data/auto_augment.py

@@ -539,11 +539,11 @@ def __repr__(self):
 
 def auto_augment_transform(config_str, hparams):
     """
-    Create a AutoAugment transform
+    Creates a AutoAugment transform
 
     :param config_str: String defining configuration of auto augmentation. Consists of multiple sections separated by
         dashes ('-'). The first section defines the AutoAugment policy (one of 'v0', 'v0r', 'original', 'originalr').
-        The remaining sections, not order sepecific determine
+        The remaining sections, not order specific determine
             * 'mstd' -  float std deviation of magnitude noise applied
 
         Example: 'original-mstd0.5' results in AutoAugment with original policy, magnitude_std 0.5
@@ -681,15 +681,15 @@ def __repr__(self):
 
 def rand_augment_transform(config_str, hparams):
     """
-    Create a RandAugment transform
+    Creates a RandAugment transform
 
     :param config_str: String defining configuration of random augmentation. Consists of multiple sections separated by
         dashes ('-'). The first section defines the specific variant of rand augment (currently only 'rand'). The remaining
-        sections, not order sepecific determine
+        sections, not order specific determine
 
             * 'm' - integer magnitude of rand augment
             * 'n' - integer num layers (number of transform ops selected per image)
-            * 'w' - integer probabiliy weight index (index of a set of weights to influence choice of op)
+            * 'w' - integer probability weight index (index of a set of weights to influence choice of op)
             * 'mstd' -  float std deviation of magnitude noise applied, or uniform sampling if infinity (or > 100)
             * 'mmax' - set upper bound for magnitude to something other than default of  _LEVEL_DENOM (10)
             * 'inc' - integer (bool), use augmentations that increase in severity with magnitude (default: 0)
@@ -846,11 +846,11 @@ def __repr__(self):
 
 
 def augment_and_mix_transform(config_str, hparams):
-    """ Create AugMix OneFlow transform
+    """ Creates AugMix OneFlow transform
 
     :param config_str: String defining configuration of random augmentation. Consists of multiple sections separated by
         dashes ('-'). The first section defines the specific variant of rand augment (currently only 'rand'). The remaining
-        sections, not order sepecific determine
+        sections, not order specific determine
 
             * 'm' - integer magnitude (severity) of augmentation mix (default: 3)
             * 'w' - integer width of augmentation chain (default: 3)

flowvision/data/mixup.py

@@ -20,7 +20,7 @@ def one_hot(x, num_classes, on_value=1.0, off_value=0.0, device="cuda"):
 
 def mixup_target(target, num_classes, lam=1.0, smoothing=0.0, device="cuda"):
     """
-    Mixup the targets with label-smoothing
+    Mixes up the targets with label-smoothing
     """
     off_value = smoothing / num_classes
     on_value = 1.0 - smoothing + off_value
@@ -39,7 +39,7 @@ def mixup_target(target, num_classes, lam=1.0, smoothing=0.0, device="cuda"):
 
 def rand_bbox(img_shape, lam, margin=0.0, count=None):
     """ Standard CutMix bounding-box
-    Generates a random square bbox based on lambda value. This impl includes
+    generates a random square bbox based on lambda value. This implementation includes
     support for enforcing a border margin as percent of bbox dimensions.
 
     Args:
@@ -90,7 +90,7 @@ def rand_bbox_minmax(img_shape, minmax, count=None):
 def cutmix_bbox_and_lam(
     img_shape, lam, ratio_minmax=None, correct_lam=True, count=None
 ):
-    """ Generate bbox and apply lambda correction.
+    """ Generates bbox and apply lambda correction.
     """
     if ratio_minmax is not None:
         yl, yu, xl, xu = rand_bbox_minmax(img_shape, ratio_minmax, count=count)

flowvision/data/random_erasing.py

@@ -26,7 +26,7 @@ class RandomErasing:
     or single image tensor after it has been normalized by dataset mean and std.
 
     Args:
-        probability: Probability that the Random Erasing operation will be performed
+        probability: Probability that the RandomErasing operation will be performed
         min_area: Minimum percentage of erased area wrt input image area
         max_area: Maximum percentage of erased area wrt input image area
         min_aspect: Minimum aspect ratio of erased area
@@ -36,7 +36,7 @@ class RandomErasing:
             * 'rand'  - erase block is same per-channel random (normal) color
             * 'pixel' - erase block is per-pixel random (normal) color
 
-        max_count: Maximum number of erasing blocks per image, area per box is scaled by count.
+        max_count: Maximum number of erasing blocks per image, and area per box is scaled by count.
             per-image count is randomly chosen between 1 and this value
     """
 

flowvision/layers/blocks/boxes.py

@@ -32,7 +32,7 @@ def batched_nms(
     """
     Performs non-maximum suppression in a batched fashion.
 
-    Each index value correspond to a category, and NMS
+    Each index value corresponds to a category, and NMS
     will not be applied between elements of different categories.
 
     Args:
@@ -151,7 +151,7 @@ def _box_inter_union(boxes1: Tensor, boxes2: Tensor) -> Tuple[Tensor, Tensor]:
 
 def box_iou(boxes1: Tensor, boxes2: Tensor) -> Tensor:
     """
-    Return intersection-over-union (Jaccard index) between two sets of boxes.
+    Returns intersection-over-union (Jaccard index) between two sets of boxes.
 
     Both sets of boxes are expected to be in ``(x1, y1, x2, y2)`` format with
     ``0 <= x1 < x2`` and ``0 <= y1 < y2``.

flowvision/models/detection/faster_rcnn.py

@@ -47,7 +47,7 @@ class FasterRCNN(GeneralizedRCNN):
     The input to the model is expected to be a list of tensors, each of shape [C, H, W], one for each
     image, and should be in 0-1 range. Different images can have different sizes.
 
-    The behavior of the model changes depending if it is in training or evaluation mode.
+    The behavior of the model changes depending on if it is in training or evaluation mode.
 
     During training, the model expects both the input tensors, as well as a targets (list of dictionary),
     containing:
@@ -309,15 +309,15 @@ def fasterrcnn_resnet50_fpn(
     **kwargs,
 ):
     """
-    Constructs a Faster R-CNN model with a ResNet-50-FPN backbone.
+    Constructs the Faster R-CNN model with a ResNet-50-FPN backbone.
 
     Reference: `"Faster R-CNN: Towards Real-Time Object Detection with
     Region Proposal Networks" <https://arxiv.org/abs/1506.01497>`_.
 
     The input to the model is expected to be a list of tensors, each of shape ``[C, H, W]``, one for each
     images, and should be in ``0-1`` range. Different images can have different sizes.
 
-    The behavior of the model changes depending if it is in training or evaluation mode.
+    The behavior of the model changes depending on if it is in training or evaluation mode.
 
     During training, the model expects both the input tensors, as well as a targets (list of dictionary),
     containing:
@@ -475,7 +475,7 @@ def fasterrcnn_mobilenet_v3_large_320_fpn(
     **kwargs,
 ):
     """
-    Constructs a low resolution Faster R-CNN model with a MobileNetV3-Large FPN backbone tunned for mobile use-cases.
+    Constructs the low resolution Faster R-CNN model with a MobileNetV3-Large FPN backbone tunned for mobile use-cases.
     It works similarly to Faster R-CNN with ResNet-50 FPN backbone. See
     :func:`~flowvision.models.detection.fasterrcnn_resnet50_fpn` for more
     details.
@@ -528,7 +528,7 @@ def fasterrcnn_mobilenet_v3_large_fpn(
     **kwargs,
 ):
     """
-    Constructs a high resolution Faster R-CNN model with a MobileNetV3-Large FPN backbone.
+    Constructs the high resolution Faster R-CNN model with a MobileNetV3-Large FPN backbone.
     It works similarly to Faster R-CNN with ResNet-50 FPN backbone. See
     :func:`~flowvision.models.detection.fasterrcnn_resnet50_fpn` for more
     details.

flowvision/models/detection/fcos.py

@@ -298,7 +298,7 @@ class FCOS(nn.Module):
     The input to the model is expected to be a list of tensors, each of shape [C, H, W], one for each
     image, and should be in 0-1 range. Different images can have different sizes.
 
-    The behavior of the model changes depending if it is in training or evaluation mode.
+    The behavior of the model changes depending on if it is in training or evaluation mode.
 
     During training, the model expects both the input tensors, as well as a targets (list of dictionary),
     containing:
@@ -729,7 +729,7 @@ def fcos_resnet50_fpn(
     The input to the model is expected to be a list of tensors, each of shape ``[C, H, W]``, one for each
     image, and should be in ``0-1`` range. Different images can have different sizes.
 
-    The behavior of the model changes depending if it is in training or evaluation mode.
+    The behavior of the model changes depending on if it is in training or evaluation mode.
 
     During training, the model expects both the input tensors, as well as a targets (list of dictionary),
     containing:

flowvision/models/detection/mask_rcnn.py

@@ -24,7 +24,7 @@ class MaskRCNN(FasterRCNN):
     The input to the model is expected to be a list of tensors, each of shape [C, H, W], one for each
     image, and should be in 0-1 range. Different images can have different sizes.
 
-    The behavior of the model changes depending if it is in training or evaluation mode.
+    The behavior of the model changes depending on if it is in training or evaluation mode.
 
     During training, the model expects both the input tensors, as well as a targets (list of dictionary),
     containing:
@@ -275,7 +275,7 @@ def maskrcnn_resnet50_fpn(
     The input to the model is expected to be a list of tensors, each of shape ``[C, H, W]``, one for each
     image, and should be in ``0-1`` range. Different images can have different sizes.
 
-    The behavior of the model changes depending if it is in training or evaluation mode.
+    The behavior of the model changes depending on if it is in training or evaluation mode.
     During training, the model expects both the input tensors, as well as a targets (list of dictionary),
     containing:
 

flowvision/models/detection/retinanet.py

@@ -278,7 +278,7 @@ class RetinaNet(nn.Module):
     The input to the model is expected to be a list of tensors, each of shape [C, H, W], one for each
     image, and should be in 0-1 range. Different images can have different sizes.
 
-    The behavior of the model changes depending if it is in training or evaluation mode.
+    The behavior of the model changes depending on if it is in training or evaluation mode.
 
     During training, the model expects both the input tensors, as well as a targets (list of dictionary),
     containing:
@@ -663,14 +663,14 @@ def retinanet_resnet50_fpn(
     **kwargs,
 ):
     """
-    Constructs a RetinaNet model with a ResNet-50-FPN backbone.
+    Constructs the RetinaNet model with a ResNet-50-FPN backbone.
 
     Reference: `"Focal Loss for Dense Object Detection" <https://arxiv.org/abs/1708.02002>`_.
 
     The input to the model is expected to be a list of tensors, each of shape ``[C, H, W]``, one for each
     image, and should be in ``0-1`` range. Different images can have different sizes.
 
-    The behavior of the model changes depending if it is in training or evaluation mode.
+    The behavior of the model changes depending on if it is in training or evaluation mode.
 
     During training, the model expects both the input tensors, as well as a targets (list of dictionary),
     containing:

flowvision/models/detection/ssd.py

@@ -117,7 +117,7 @@ class SSD(nn.Module):
     image, and should be in 0-1 range. Different images can have different sizes but they will be resized
     to a fixed size before passing it to the backbone.
 
-    The behavior of the model changes depending if it is in training or evaluation mode.
+    The behavior of the model changes depending on if it is in training or evaluation mode.
 
     During training, the model expects both the input tensors, as well as a targets (list of dictionary),
     containing:
@@ -599,15 +599,15 @@ def ssd300_vgg16(
     trainable_backbone_layers: Optional[int] = None,
     **kwargs: Any
 ):
-    """Constructs an SSD model with input size 300x300 and a VGG16 backbone.
+    """Constructs the SSD model with input size 300x300 and a VGG16 backbone.
 
     Reference: `"SSD: Single Shot MultiBox Detector" <https://arxiv.org/abs/1512.02325>`_.
 
     The input to the model is expected to be a list of tensors, each of shape [C, H, W], one for each
-    image, and should be in 0-1 range. Different images can have different sizes but they will be resized
+    image, and should be in 0-1 range. Different images can have different sizes, but they will be resized
     to a fixed size before passing it to the backbone.
 
-    The behavior of the model changes depending if it is in training or evaluation mode.
+    The behavior of the model changes depending on if it is in training or evaluation mode.
 
     During training, the model expects both the input tensors, as well as a targets (list of dictionary),
     containing:

flowvision/models/detection/ssdlite.py

@@ -237,7 +237,7 @@ def ssdlite320_mobilenet_v3_large(
     norm_layer: Optional[Callable[..., nn.Module]] = None,
     **kwargs: Any
 ):
-    """Constructs an SSDlite model with input size 320x320 and a MobileNetV3 Large backbone, as described at
+    """Constructs the SSDlite model with input size 320x320 and a MobileNetV3 Large backbone, as described at
     `"Searching for MobileNetV3"
     <https://arxiv.org/abs/1905.02244>`_ and
     `"MobileNetV2: Inverted Residuals and Linear Bottlenecks"

flowvision/models/segmentation/deeplabv3.py

@@ -193,7 +193,7 @@ def _load_weights(model, arch_type, backbone, progress):
 def deeplabv3_resnet50_coco(
     pretrained=False, progress=True, num_classes=21, aux_loss=None, **kwargs
 ):
-    """Constructs a DeepLabV3 model with a ResNet-50 backbone.
+    """Constructs the DeepLabV3 model with a ResNet-50 backbone.
     Args:
         pretrained (bool): If True, returns a model pre-trained on COCO train2017 which
             contains the same classes as Pascal VOC
@@ -218,7 +218,7 @@ def deeplabv3_resnet50_coco(
 def deeplabv3_resnet101_coco(
     pretrained=False, progress=True, num_classes=21, aux_loss=None, **kwargs
 ):
-    """Constructs a DeepLabV3 model with a ResNet-101 backbone.
+    """Constructs the DeepLabV3 model with a ResNet-101 backbone.
     Args:
         pretrained (bool): If True, returns a model pre-trained on COCO train2017 which
             contains the same classes as Pascal VOC
@@ -243,7 +243,7 @@ def deeplabv3_resnet101_coco(
 def deeplabv3_mobilenet_v3_large_coco(
     pretrained=False, progress=True, num_classes=21, aux_loss=None, **kwargs
 ):
-    """Constructs a DeepLabV3 model with a MobileNetV3-Large backbone.
+    """Constructs the DeepLabV3 model with a MobileNetV3-Large backbone.
     Args:
         pretrained (bool): If True, returns a model pre-trained on COCO train2017 which
             contains the same classes as Pascal VOC

flowvision/models/segmentation/fcn.py

@@ -121,7 +121,7 @@ def _load_weights(model, arch_type, backbone, progress):
 def fcn_resnet50_coco(
     pretrained=False, progress=True, num_classes=21, aux_loss=None, **kwargs
 ):
-    """Constructs a Fully-Convolutional Network model with a ResNet-50 backbone.
+    """Constructs the Fully-Convolutional Network model with a ResNet-50 backbone.
 
     Args:
         pretrained (bool): If True, returns a model pre-trained on COCO train2017 which
@@ -147,7 +147,7 @@ def fcn_resnet50_coco(
 def fcn_resnet101_coco(
     pretrained=False, progress=True, num_classes=21, aux_loss=None, **kwargs
 ):
-    """Constructs a Fully-Convolutional Network model with a ResNet-101 backbone.
+    """Constructs the Fully-Convolutional Network model with a ResNet-101 backbone.
 
     Args:
         pretrained (bool): If True, returns a model pre-trained on COCO train2017 which

flowvision/models/segmentation/lraspp.py

@@ -121,7 +121,7 @@ def _segm_lraspp_mobilenetv3(backbone_name, num_classes, pretrained_backbone=Tru
 def lraspp_mobilenet_v3_large_coco(
     pretrained=False, progress=True, num_classes=21, **kwargs
 ):
-    """Constructs a Lite R-ASPP Network model with a MobileNetV3-Large backbone.
+    """Constructs the Lite R-ASPP Network model with a MobileNetV3-Large backbone.
     Args:
         pretrained (bool): If True, returns a model pre-trained on COCO train2017 which
             contains the same classes as Pascal VOC