[Cherry-pick] Docs fixes

src/deepsparse/image_classification/README.md

@@ -22,7 +22,7 @@ your machine is compatible with our [hardware requirements].
 
 ### Installation
 
-```pip install deepsparse```
+```pip install deepsparse[image_classification]```
 
 ### Model Format
 
@@ -122,7 +122,7 @@ pip install deepsparse[server]
 The following section includes example usage of the Pipeline and server APIs for
 various image classification models. 
 
-[List of Image Classification SparseZoo Models](https://sparsezoo.neuralmagic.com/?domain=cv&sub_domain=classification&page=1)
+[List of Image Classification SparseZoo Models](https://sparsezoo.neuralmagic.com/?useCase=classification)
 
 
 #### Python Pipeline
@@ -196,4 +196,4 @@ For Neural Magic Support, sign up or log in to our [Deep Sparse Community Slack]
 [ONNX]: https://onnx.ai/
 [SparseML]: https://github.com/neuralmagic/sparseml
 [SparseML Image Classification Documentation]: https://github.com/neuralmagic/sparseml/tree/main/src/sparseml/pytorch/image_classification/README_image_classification.md
-[SparseZoo]: https://sparsezoo.neuralmagic.com/
+[SparseZoo]: https://sparsezoo.neuralmagic.com/

src/deepsparse/transformers/README.md

@@ -100,7 +100,7 @@ for the `question` as a substring of the `context`.  The following examples use
 question answering BERT model trained on the `SQuAD` dataset downloaded by default from the SparseZoo.
 
 [List of available SparseZoo Question Answering Models](
-https://sparsezoo.neuralmagic.com/?page=1&domain=nlp&sub_domain=question_answering)
+https://sparsezoo.neuralmagic.com/?useCase=question_answering)
 
 #### Python Pipeline
 
@@ -144,7 +144,7 @@ uses a pruned and quantized text sentiment analysis BERT model trained on the `s
 from the SparseZoo. This `sst2` model classifies sentences as positive or negative.
 
 [List of available SparseZoo Sentiment Analysis Models](
-https://sparsezoo.neuralmagic.com/?domain=nlp&sub_domain=sentiment_analysis)
+https://sparsezoo.neuralmagic.com/?useCase=sentiment_analysis)
 
 #### Python Pipeline
 ```python
@@ -190,7 +190,7 @@ DistilBERT model trained on the `qqp` dataset downloaded from a SparseZoo stub.
 The `qqp` dataset takes pairs of questions and predicts if they are a duplicate or not.
 
 [List of available SparseZoo Text Classification Models](
-https://sparsezoo.neuralmagic.com/?page=1&domain=nlp&sub_domain=text_classification)
+https://sparsezoo.neuralmagic.com/?useCase=text_classification)
 
 #### Python Pipeline
 ```python
@@ -249,7 +249,7 @@ The following example uses a pruned and quantized token classification NER BERT
 trained on the `CoNLL` dataset downloaded from the SparseZoo.
 
 [List of available SparseZoo Token Classification Models](
-https://sparsezoo.neuralmagic.com/?page=1&domain=nlp&sub_domain=token_classification)
+https://sparsezoo.neuralmagic.com/?useCase=token_classification)
 
 #### Python Pipeline
 ```python

src/deepsparse/yolo/README.md

@@ -37,7 +37,7 @@ sparseml.yolov5.export_onnx \
     --weights path/to/your/model \
     --dynamic #Allows for dynamic input shape
 ```
-This creates `model.onnx` file, in the directory of your `weights` (e.g. `runs/train/weights/model.onnx`).
+This creates a DeepSparse_Deployment folder with a `model.onnx` file (e.g. `runs/train/exp/DeepSparse_Deployment/model.onnx`).
 
 ####  SparseZoo Stub
 Alternatively, you can skip the process of the ONNX model export by using Neural Magic's [SparseZoo](https://sparsezoo.neuralmagic.com/). The SparseZoo contains pre-sparsified models and SparseZoo stubs enable you to reference any model on the SparseZoo in a convenient and predictable way.
@@ -76,7 +76,7 @@ pip install deepsparse[yolo,server]
 The following example uses pipelines to run a pruned and quantized YOLOv5l model for inference, downloaded by default from the SparseZoo. As input the pipeline ingests a list of images and returns for each image the detection boxes in numeric form. 
 
 [List of the YOLOv5 SparseZoo Models](
-https://sparsezoo.neuralmagic.com/?domain=cv&sub_domain=detection&page=1)
+https://sparsezoo.neuralmagic.com/?useCase=detection&architectures=yolov5)
 
 If you don't have an image ready, pull a sample image down with