yolact readme fixes (#479)

Author: rahul-tuli

integrations/dbolya-yolact/README.md

@@ -35,7 +35,6 @@ The techniques include, but are not limited to:
 We recommend using a [virtual environment](https://docs.python.org/3/library/venv.html) to keep your project dependencies isolated.
 A virtual environment can be created using the following commands:
 
-Note: This integration needs `python>=3.7,<3.10` for it's requirements
 ```bash
 python3 -m venv venv # create a venv virtual environment
 source venv/bin/activate # activate venv
@@ -49,6 +48,8 @@ bash setup_integration.sh
 
 The `setup_integration.sh` file will clone the yolact-sparseml integration repository. After the repo has successfully cloned, all dependencies from the `yolact/requirements.txt` file will install in your current environment.
 
+Note: This integration requires `python>=3.7,<3.10`
+
 
 ## Quick Tour
 
@@ -101,14 +102,6 @@ python export.py --checkpoint ./quantized-yolact/model.pth \
     --name quantized-yolact.onnx
 ```
 
-To prevent the conversion of a QAT (Quantization-Aware Training) Graph to a
-Quantized Graph, pass in the `--no-qat` flag:
-
-```bash
-python export.py --checkpoint ./quantized-yolact/model.pth \
-    --name qat-yolact.onnx \
-    --skip-qat-convert
-```
 
 ### DeepSparse
 

integrations/dbolya-yolact/tutorials/sparsifying_yolact_using_recipes.md

@@ -189,7 +189,7 @@ The table below compares these tradeoffs and shows how to run them on the COCO d
     - When running quantized models, the memory footprint for training will significantly increase (roughly 3x). It is recommended to train at a high batch size at first. This will fail with an out-of-memory exception once quantization starts. Once this happens, use the weights from that run to resume training with lower batch size.
 
 3. To begin applying one of the recipes, use the `--recipe` argument within the YOLACT [train script](https://github.com/neuralmagic/yolact/blob/master/train.py).
-   The recipe argument is combined with our previous training command and COCO pre-trained weights to run the recipes over the model. For example, a command for YOLACT would look like this:
+   The recipe argument is combined with our previous training command and COCO pre-trained weights to run the recipes over the model. For example, a command for pruning YOLACT would look like this:
 ```bash
 python train.py \
 --recipe=../recipes/yolact.pruned.yaml \