Docs 1.0 refactor rs2 (#93)

* Updated pages to have links back to instruction pages; cleaned up a few broken links

* Update custom-integrations.mdx

* Update custom-integrations.mdx

* Update install.mdx

* Update deepsparse.mdx

* Update deploying.mdx

* Update deploying.mdx

* Update deploying.mdx

* Update deploying.mdx

* Update deploying.mdx

* Update benchmarking.mdx

* Update custom-integrations.mdx

* Update custom-integrations.mdx

Fixes https://app.asana.com/0/1203146234476221/1203094643835125/f

Author: robertgshaw2-redhat

src/content/details/faqs.mdx

@@ -14,6 +14,10 @@ The DeepSparse Server is a server wrapper around `Pipelines`, including the obje
 the server provides and HTTP interface that accepts images and image files as inputs and outputs the labeled predictions.
 With all of this built on top of the DeepSparse Engine, the simplicity of servable pipelines is combined with GPU-class performance on CPUs for sparse models.
 
+## Install Requirements
+
+This example requires [DeepSparse Server+YOLO Install](/get-started/install/deepsparse).
+
 ## Start the Server
 
 Before starting the server, the model must be set up in the format expected for DeepSparse `Pipelines`.

src/content/get-started/deploy-a-model/cv-object-detection.mdx

@@ -14,6 +14,10 @@ The DeepSparse Server is a server wrapper around `Pipelines`, including the sent
 the server provides an HTTP interface that accepts raw text sequences as inputs and responds with the labeled predictions.
 With all of this built on top of the DeepSparse Engine, the simplicity of servable pipelines is combined with GPU-class performance on CPUs for sparse models.
 
+## Install Requirements
+
+This example requires [DeepSparse Server Install](/get-started/install/deepsparse).
+
 ## Start the Server
 
 Before starting the server, the model must be set up in the format expected for DeepSparse `Pipelines`.

src/content/get-started/deploy-a-model/nlp-text-classification.mdx

@@ -17,7 +17,7 @@ It is recommended to install in a [virtual environment](https://docs.python.org/
 To begin using the Deep Sparse Platform, run the following commands which install standard setups for deployment with [DeepSparse](../../products/deepsparse) and model training/optimization with [SparseML](../../products/sparseml):
 
 ```bash
-pip install deepsparse[server] sparseml[torchvision]
+pip install deepsparse[server] sparseml[torch, torchvision]
 ```
 
 ## Installable Packages

src/content/get-started/install.mdx

@@ -8,11 +8,11 @@ index: 1000
 
 # DeepSparse Installation
 
-The [DeepSparse Engine](../../products/deepsparse) enables GPU-class performance on CPUs, leveraging sparsity within models to reduce FLOPs and the unique cache hierarchy on CPUs to reduce memory movement.
+The [DeepSparse Engine](/products/deepsparse) enables GPU-class performance on CPUs, leveraging sparsity within models to reduce FLOPs and the unique cache hierarchy on CPUs to reduce memory movement.
 The engine accepts models in the open-source [ONNX format](https://onnx.ai/), which are easily created from PyTorch and TensorFlow models.
 
 Currently, DeepSparse is tested on Python 3.7-3.9, ONNX 1.5.0-1.10.1, ONNX opset version 11+ and is [manylinux compliant](https://peps.python.org/pep-0513/).
-It is limited to [Linux systems](https://www.linux.org/) running on [X86 CPU architectures](https://en.wikipedia.org/wiki/X86).
+It is limited to Linux systems running on x86 CPU architectures.
 
 ## General Install
 
@@ -24,7 +24,7 @@ pip install deepsparse
 
 ## Server Install
 
-The [DeepSparse Server](../../use-cases/deploying-with-deepsparse/deepsparse-server) allows you to serve models and pipelines through an HTTP interface using the deepsparse.server CLI.
+The [DeepSparse Server](/use-cases/deploying-deepsparse/deepsparse-server) allows you to serve models and pipelines through an HTTP interface using the deepsparse.server CLI.
 To install, use the following extra option:
 
 ```bash
@@ -33,9 +33,10 @@ pip install deepsparse[server]
 
 ## YOLO Install
 
-The [Ultralytics YOLOv5](../../use-cases/ultralytics-yolov5) models require extra dependencies for deployment.
+The [Ultralytics YOLOv5](/use-cases/object-detection/deploying) models require extra dependencies for deployment.
 To use YOLO models, install with the following extra option:
 
 ```bash
-pip install deepsparse[yolo]
+pip install deepsparse[yolo]         # just yolo requirements
+pip install deepsparse[yolo, server] # both yolo + server requirements
 ```

src/content/get-started/install/deepsparse.mdx

@@ -10,7 +10,7 @@ index: 2000
 
 [SparseML](/products/sparseml) enables you to create sparse models trained on your data. It supports transfer learning from sparse models to new data and sparsifying dense models from scratch with state-of-the-art algorithms for pruning and quantization.
 
-Currently, SparseML is tested on Python 3.7-3.9 and is limited to [Linux](https://www.linux.org/) and [MacOS](https://www.apple.com/mac/) systems.
+Currently, SparseML is tested on Python 3.7-3.9 and is limited to Linux and MacOS systems.
 
 ## General Install
 

src/content/get-started/install/sparseml.mdx

@@ -15,6 +15,10 @@ In addition to supported integrations described on the prior page, SparseML is s
 This flexibility enables easy sparsification for any neural network architecture for custom models and use cases. Once SparseML is installed,
 the necessary code can be plugged into most PyTorch/Keras training pipelines with only a few lines of code.
 
+## Install Requirements
+
+This section requires [SparseML Torchvision Install](/get-started/install/sparseml) to run the Apply the Recipe section.
+
 ## Integrate SparseML
 
 To enable sparsification of models with recipes, a few edits to the training pipeline code need to be made.
@@ -41,19 +45,19 @@ A wrapped instance of the training optimizer is returned.
 
 A simple training example utilizing PyTorch and Torchvision with this SparseML integration is provided below:
 ```Python
-from torchvision.models import resnet50
+import torch
 from torch.nn import Linear
 from torch.utils.data import DataLoader
 from torch.nn import CrossEntropyLoss
 from torch.optim import SGD
 
+from sparseml.pytorch.models import resnet50
 from sparseml.pytorch.datasets import ImagenetteDataset, ImagenetteSize
 from sparseml.pytorch.optim import ScheduledModifierManager
 
 # Model creation
-model = resnet50(pretrained=True)
 NUM_CLASSES = 10  # number of imagenette classes
-model.fc = Linear(in_features=model.fc.in_features, out_features=NUM_CLASSES, bias=True)
+model = resnet50(pretrained=True, num_classes=NUM_CLASSES)
 
 # Dataset creation
 batch_size = 64
@@ -68,18 +72,24 @@ model.to(device)
 criterion = CrossEntropyLoss()
 optimizer = SGD(model.parameters(), lr=10e-6, momentum=0.9)
 
+# Recipe - in this case, we pull down a recipe from the SparseZoo for ResNet50
+# This can be a be a path to a local file
+recipe_path = "zoo:cv/classification/resnet_v1-50/pytorch/sparseml/imagenet/pruned95_quant-none?recipe_type=original"
+
 # SparseML Integration
 manager = ScheduledModifierManager.from_yaml(recipe_path)
 optimizer = manager.modify(model, optimizer, steps_per_epoch=len(train_loader))
 
 # Training Loop
 for epoch in range(manager.max_epochs):
-    for inputs, labels in dataloaders[phase]:
+    running_loss = 0.0
+    running_corrects = 0.0
+    for inputs, labels in train_loader:
         inputs = inputs.to(device)
         labels = labels.to(device)
         optimizer.zero_grad()
-        with torch.set_grad_enabled(true):
-            outputs = model(inputs)
+        with torch.set_grad_enabled(True):
+            outputs, _ = model(inputs)
             loss = criterion(outputs, labels)
             _, preds = torch.max(outputs, 1)
             loss.backward()
@@ -123,8 +133,7 @@ modifiers:
 
     - !QuantizationModifier
         start_epoch: 50.0
-        submodules: ['model']
-        freeze_bn_stats_epoch: 3.0
+        freeze_bn_stats_epoch: 53.0
 
     - !SetLearningRateModifier
         start_epoch: 50.0

src/content/get-started/sparsify-a-model/custom-integrations.mdx

@@ -14,6 +14,10 @@ SparseML has pre-made integrations with many popular model repositories, such as
 For these integrations, a sparsification recipe is all you need, and you can apply state-of-the-art sparsification algorithms, including
 pruning, distillation, and quantization, with a single command line call.
 
+## Install Requirements
+
+This section requires [SparseML Torchvision Install](/get-started/install/sparseml) to run the Apply the Recipe section.
+
 ## Pruning and Pruning Recipes
 
 Pruning is a systematic way of removing redundant weights and connections within a neural network. An applied pruning algorithm must determine which

src/content/get-started/sparsify-a-model/supported-integrations.mdx

@@ -12,10 +12,9 @@ This page walks through an example of fine-tuning a pre-sparsified model from th
 
 We will use SparseZoo to pull down a pre-sparsified YOLOv5l and will use SparseML to fine-tune onto the VOC dataset while preserving sparsity.
 
-Make sure you install SparseML with torchvision before getting started:
-```bash
-pip install sparseml[torchvision]
-```
+## Install Requirements
+
+This example requires [SparseML Torchvision Install](/get-started/install/sparseml).
 
 ## Transfer Learning
 

src/content/get-started/transfer-a-sparsified-model/cv-object-detection.mdx

@@ -19,10 +19,9 @@ If you already have a trained teacher model ready to go, you can skip step 1.
 
 An example of transfer learning without model distillation is in the [Use Cases Page](/use-cases/natural-language-processing/text-classification).
 
-Make sure you install SparseML before getting started:
-```bash
-pip install sparseml
-```
+## Install Requirements
+
+This example requires [SparseML General Install](/get-started/install/sparseml).
 
 ## Train a Teacher