Docs updates for HUB, YOLOv4, YOLOv7, NAS (#3174)

Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

docs/reference/nn/autobackend.md

@@ -1,5 +1,6 @@
 ---
 description: Ensure class names match filenames for easy imports. Use AutoBackend to automatically rename and refactor model files.
+keywords: AutoBackend, ultralytics, nn, autobackend, check class names, neural network
 ---
 
 # AutoBackend
@@ -10,4 +11,4 @@ description: Ensure class names match filenames for easy imports. Use AutoBacken
 # check_class_names
 ---
 :::ultralytics.nn.autobackend.check_class_names
-<br><br>
+<br><br>

docs/reference/nn/autoshape.md

@@ -1,5 +1,6 @@
 ---
 description: Detect 80+ object categories with bounding box coordinates and class probabilities using AutoShape in Ultralytics YOLO. Explore Detections now.
+keywords: Ultralytics, YOLO, docs, autoshape, detections, object detection, customized shapes, bounding boxes, computer vision
 ---
 
 # AutoShape
@@ -10,4 +11,4 @@ description: Detect 80+ object categories with bounding box coordinates and clas
 # Detections
 ---
 :::ultralytics.nn.autoshape.Detections
-<br><br>
+<br><br>

docs/reference/nn/modules/block.md

@@ -1,5 +1,6 @@
 ---
 description: Explore ultralytics.nn.modules.block to build powerful YOLO object detection models. Master DFL, HGStem, SPP, CSP components and more.
+keywords: Ultralytics, NN Modules, Blocks, DFL, HGStem, SPP, C1, C2f, C3x, C3TR, GhostBottleneck, BottleneckCSP, Computer Vision
 ---
 
 # DFL
@@ -85,4 +86,4 @@ description: Explore ultralytics.nn.modules.block to build powerful YOLO object
 # BottleneckCSP
 ---
 :::ultralytics.nn.modules.block.BottleneckCSP
-<br><br>
+<br><br>

docs/reference/nn/modules/conv.md

@@ -1,5 +1,6 @@
 ---
 description: Explore convolutional neural network modules & techniques such as LightConv, DWConv, ConvTranspose, GhostConv, CBAM & autopad with Ultralytics Docs.
+keywords: Ultralytics, Convolutional Neural Network, Conv2, DWConv, ConvTranspose, GhostConv, ChannelAttention, CBAM, autopad
 ---
 
 # Conv
@@ -70,4 +71,4 @@ description: Explore convolutional neural network modules & techniques such as L
 # autopad
 ---
 :::ultralytics.nn.modules.conv.autopad
-<br><br>
+<br><br>

docs/reference/nn/modules/head.md

@@ -1,5 +1,6 @@
 ---
 description: 'Learn about Ultralytics YOLO modules: Segment, Classify, and RTDETRDecoder. Optimize object detection and classification in your project.'
+keywords: Ultralytics, YOLO, object detection, pose estimation, RTDETRDecoder, modules, classes, documentation
 ---
 
 # Detect
@@ -25,4 +26,4 @@ description: 'Learn about Ultralytics YOLO modules: Segment, Classify, and RTDET
 # RTDETRDecoder
 ---
 :::ultralytics.nn.modules.head.RTDETRDecoder
-<br><br>
+<br><br>

docs/reference/nn/modules/transformer.md

@@ -1,5 +1,6 @@
 ---
 description: Explore the Ultralytics nn modules pages on Transformer and MLP blocks, LayerNorm2d, and Deformable Transformer Decoder Layer.
+keywords: Ultralytics, NN Modules, TransformerEncoderLayer, TransformerLayer, MLPBlock, LayerNorm2d, DeformableTransformerDecoderLayer, examples, code snippets, tutorials
 ---
 
 # TransformerEncoderLayer
@@ -50,4 +51,4 @@ description: Explore the Ultralytics nn modules pages on Transformer and MLP blo
 # DeformableTransformerDecoder
 ---
 :::ultralytics.nn.modules.transformer.DeformableTransformerDecoder
-<br><br>
+<br><br>

docs/reference/nn/modules/utils.md

@@ -1,5 +1,6 @@
 ---
 description: 'Learn about Ultralytics NN modules: get_clones, linear_init_, and multi_scale_deformable_attn_pytorch. Code examples and usage tips.'
+keywords: Ultralytics, NN Utils, Docs, PyTorch, bias initialization, linear initialization, multi-scale deformable attention
 ---
 
 # _get_clones
@@ -25,4 +26,4 @@ description: 'Learn about Ultralytics NN modules: get_clones, linear_init_, and
 # multi_scale_deformable_attn_pytorch
 ---
 :::ultralytics.nn.modules.utils.multi_scale_deformable_attn_pytorch
-<br><br>
+<br><br>

docs/reference/nn/tasks.md

@@ -1,5 +1,6 @@
 ---
 description: Learn how to work with Ultralytics YOLO Detection, Segmentation & Classification Models, load weights and parse models in PyTorch.
+keywords: neural network, deep learning, computer vision, object detection, image segmentation, image classification, model ensemble, PyTorch
 ---
 
 # BaseModel
@@ -70,4 +71,4 @@ description: Learn how to work with Ultralytics YOLO Detection, Segmentation & C
 # guess_model_task
 ---
 :::ultralytics.nn.tasks.guess_model_task
-<br><br>
+<br><br>