ultralytics 8.0.196 instance-mean Segment loss (#5285)

Co-authored-by: Andy <39454881+yermandy@users.noreply.github.com>

docs/yolov5/tutorials/architecture_description.md

@@ -176,8 +176,7 @@ The revised formulas for calculating the predicted bounding box are as follows:
 ![bw](https://latex.codecogs.com/svg.image?b_w=p_w\cdot(2\cdot\sigma(t_w))^2)
 ![bh](https://latex.codecogs.com/svg.image?b_h=p_h\cdot(2\cdot\sigma(t_h))^2)
 
-Compare the center point offset before and after scaling. The center point offset range is adjusted from (0, 1) to (-0.5, 1.5).
-Therefore, offset can easily get 0 or 1.
+Compare the center point offset before and after scaling. The center point offset range is adjusted from (0, 1) to (-0.5, 1.5). Therefore, offset can easily get 0 or 1.
 
 <img src="https://user-images.githubusercontent.com/31005897/158508052-c24bc5e8-05c1-4154-ac97-2e1ec71f582e.png#pic_center" width=40%>
 

docs/yolov5/tutorials/clearml_logging_integration.md

@@ -64,8 +64,7 @@ pip install clearml>=1.2.0
 
 This will enable integration with the YOLOv5 training script. Every training run from now on, will be captured and stored by the ClearML experiment manager.
 
-If you want to change the `project_name` or `task_name`, use the `--project` and `--name` arguments of the `train.py` script, by default the project will be called `YOLOv5` and the task `Training`.
-PLEASE NOTE: ClearML uses `/` as a delimiter for subprojects, so be careful when using `/` in your project name!
+If you want to change the `project_name` or `task_name`, use the `--project` and `--name` arguments of the `train.py` script, by default the project will be called `YOLOv5` and the task `Training`. PLEASE NOTE: ClearML uses `/` as a delimiter for subprojects, so be careful when using `/` in your project name!
 
 ```bash
 python train.py --img 640 --batch 16 --epochs 3 --data coco128.yaml --weights yolov5s.pt --cache
@@ -92,8 +91,7 @@ This will capture:
 - Validation images per epoch
 - ...
 
-That's a lot right? 🤯
-Now, we can visualize all of this information in the ClearML UI to get an overview of our training progress. Add custom columns to the table view (such as e.g. mAP_0.5) so you can easily sort on the best performing model. Or select multiple experiments and directly compare them!
+That's a lot right? 🤯 Now, we can visualize all of this information in the ClearML UI to get an overview of our training progress. Add custom columns to the table view (such as e.g. mAP_0.5) so you can easily sort on the best performing model. Or select multiple experiments and directly compare them!
 
 There even more we can do with all of this information, like hyperparameter optimization and remote execution, so keep reading if you want to see how that works!
 
@@ -187,8 +185,7 @@ python utils/loggers/clearml/hpo.py
 
 ## 🤯 Remote Execution (advanced)
 
-Running HPO locally is really handy, but what if we want to run our experiments on a remote machine instead? Maybe you have access to a very powerful GPU machine on-site, or you have some budget to use cloud GPUs.
-This is where the ClearML Agent comes into play. Check out what the agent can do here:
+Running HPO locally is really handy, but what if we want to run our experiments on a remote machine instead? Maybe you have access to a very powerful GPU machine on-site, or you have some budget to use cloud GPUs. This is where the ClearML Agent comes into play. Check out what the agent can do here:
 
 - [YouTube video](https://youtu.be/MX3BrXnaULs)
 - [Documentation](https://clear.ml/docs/latest/docs/clearml_agent)

docs/yolov5/tutorials/comet_logging_integration.md

@@ -90,8 +90,7 @@ By default, Comet will log the following items
 
 # Configure Comet Logging
 
-Comet can be configured to log additional data either through command line flags passed to the training script
-or through environment variables.
+Comet can be configured to log additional data either through command line flags passed to the training script or through environment variables.
 
 ```shell
 export COMET_MODE=online # Set whether to run Comet in 'online' or 'offline' mode. Defaults to online
@@ -106,8 +105,7 @@ export COMET_LOG_PREDICTIONS=true # Set this to false to disable logging model p
 
 ## Logging Checkpoints with Comet
 
-Logging Models to Comet is disabled by default. To enable it, pass the `save-period` argument to the training script. This will save the
-logged checkpoints to Comet based on the interval value provided by `save-period`
+Logging Models to Comet is disabled by default. To enable it, pass the `save-period` argument to the training script. This will save the logged checkpoints to Comet based on the interval value provided by `save-period`
 
 ```shell
 python train.py \
@@ -240,8 +238,7 @@ python utils/loggers/comet/hpo.py \
   --comet_optimizer_config "utils/loggers/comet/optimizer_config.json"
 ```
 
-The `hpo.py` script accepts the same arguments as `train.py`. If you wish to pass additional arguments to your sweep simply add them after
-the script.
+The `hpo.py` script accepts the same arguments as `train.py`. If you wish to pass additional arguments to your sweep simply add them after the script.
 
 ```shell
 python utils/loggers/comet/hpo.py \

docs/yolov5/tutorials/model_ensembling.md

@@ -4,8 +4,7 @@ description: Learn how to ensemble YOLOv5 models for improved mAP and Recall! Cl
 keywords: YOLOv5, object detection, ensemble learning, mAP, Recall
 ---
 
-📚 This guide explains how to use YOLOv5 🚀 **model ensembling** during testing and inference for improved mAP and Recall.
-UPDATED 25 September 2022.
+📚 This guide explains how to use YOLOv5 🚀 **model ensembling** during testing and inference for improved mAP and Recall. UPDATED 25 September 2022.
 
 From [https://en.wikipedia.org/wiki/Ensemble_learning](https://en.wikipedia.org/wiki/Ensemble_learning):
 > Ensemble modeling is a process where multiple diverse models are created to predict an outcome, either by using many different modeling algorithms or using different training data sets. The ensemble model then aggregates the prediction of each base model and results in once final prediction for the unseen data. The motivation for using ensemble models is to reduce the generalization error of the prediction. As long as the base models are diverse and independent, the prediction error of the model decreases when the ensemble approach is used. The approach seeks the wisdom of crowds in making a prediction. Even though the ensemble model has multiple base models within the model, it acts and performs as a single model.

docs/yolov5/tutorials/model_export.md

@@ -6,8 +6,7 @@ keywords: Ultralytics, YOLOv5, model export, PyTorch, TorchScript, ONNX, OpenVIN
 
 # TFLite, ONNX, CoreML, TensorRT Export
 
-📚 This guide explains how to export a trained YOLOv5 🚀 model from PyTorch to ONNX and TorchScript formats.
-UPDATED 8 December 2022.
+📚 This guide explains how to export a trained YOLOv5 🚀 model from PyTorch to ONNX and TorchScript formats. UPDATED 8 December 2022.
 
 ## Before You Start
 
@@ -25,8 +24,7 @@ For [TensorRT](https://developer.nvidia.com/tensorrt) export example (requires G
 
 YOLOv5 inference is officially supported in 11 formats:
 
-💡 ProTip: Export to ONNX or OpenVINO for up to 3x CPU speedup. See [CPU Benchmarks](https://github.com/ultralytics/yolov5/pull/6613).
-💡 ProTip: Export to TensorRT for up to 5x GPU speedup. See [GPU Benchmarks](https://github.com/ultralytics/yolov5/pull/6963).
+💡 ProTip: Export to ONNX or OpenVINO for up to 3x CPU speedup. See [CPU Benchmarks](https://github.com/ultralytics/yolov5/pull/6613). 💡 ProTip: Export to TensorRT for up to 5x GPU speedup. See [GPU Benchmarks](https://github.com/ultralytics/yolov5/pull/6963).
 
 | Format                                                                     | `export.py --include` | Model                     |
 |:---------------------------------------------------------------------------|:----------------------|:--------------------------|

docs/yolov5/tutorials/model_pruning_and_sparsity.md

@@ -4,8 +4,7 @@ description: Improve YOLOv5 model efficiency by pruning with Ultralytics. Unders
 keywords: YOLOv5, YOLO, Ultralytics, model pruning, PyTorch, machine learning, deep learning, computer vision, object detection
 ---
 
-📚 This guide explains how to apply **pruning** to YOLOv5 🚀 models.
-UPDATED 25 September 2022.
+📚 This guide explains how to apply **pruning** to YOLOv5 🚀 models. UPDATED 25 September 2022.
 
 ## Before You Start
 

docs/yolov5/tutorials/multi_gpu_training.md

@@ -4,8 +4,7 @@ description: Learn how to train datasets on single or multiple GPUs using YOLOv5
 keywords: YOLOv5, multi-GPU Training, YOLOv5 training, deep learning, machine learning, object detection, Ultralytics
 ---
 
-📚 This guide explains how to properly use **multiple** GPUs to train a dataset with YOLOv5 🚀 on single or multiple machine(s).
-UPDATED 25 December 2022.
+📚 This guide explains how to properly use **multiple** GPUs to train a dataset with YOLOv5 🚀 on single or multiple machine(s). UPDATED 25 December 2022.
 
 ## Before You Start
 
@@ -103,8 +102,7 @@ python -m torch.distributed.run --nproc_per_node G --nnodes N --node_rank 0 --ma
 python -m torch.distributed.run --nproc_per_node G --nnodes N --node_rank R --master_addr "192.168.1.1" --master_port 1234 train.py --batch 64 --data coco.yaml --cfg yolov5s.yaml --weights ''
 ```
 
-where `G` is number of GPU per machine, `N` is the number of machines, and `R` is the machine number from `0...(N-1)`.
-Let's say I have two machines with two GPUs each, it would be `G = 2` , `N = 2`, and `R = 1` for the above.
+where `G` is number of GPU per machine, `N` is the number of machines, and `R` is the machine number from `0...(N-1)`. Let's say I have two machines with two GPUs each, it would be `G = 2` , `N = 2`, and `R = 1` for the above.
 
 Training will not start until <b>all </b> `N` machines are connected. Output will only be shown on master machine!
 

docs/yolov5/tutorials/neural_magic_pruning_quantization.md

@@ -30,8 +30,7 @@ DeepSparse is an inference runtime with exceptional performance on CPUs. For ins
   <img width="60%" src="https://github.com/neuralmagic/deepsparse/raw/main/examples/ultralytics-yolo/ultralytics-readmes/performance-chart-5.8x.png">
 </p>
 
-For the first time, your deep learning workloads can meet the performance demands of production without the complexity and costs of hardware accelerators.
-Put simply, DeepSparse gives you the performance of GPUs and the simplicity of software:
+For the first time, your deep learning workloads can meet the performance demands of production without the complexity and costs of hardware accelerators. Put simply, DeepSparse gives you the performance of GPUs and the simplicity of software:
 
 - **Flexible Deployments**: Run consistently across cloud, data center, and edge with any hardware provider from Intel to AMD to ARM
 - **Infinite Scalability**: Scale vertically to 100s of cores, out with standard Kubernetes, or fully-abstracted with Serverless
@@ -41,10 +40,7 @@ Put simply, DeepSparse gives you the performance of GPUs and the simplicity of s
 
 DeepSparse takes advantage of model sparsity to gain its performance speedup.
 
-Sparsification through pruning and quantization is a broadly studied technique, allowing order-of-magnitude reductions in the size and compute needed to
-execute a network, while maintaining high accuracy. DeepSparse is sparsity-aware, meaning it skips the zeroed out parameters, shrinking amount of compute
-in a forward pass. Since the sparse computation is now memory bound, DeepSparse executes the network depth-wise, breaking the problem into Tensor Columns,
-vertical stripes of computation that fit in cache.
+Sparsification through pruning and quantization is a broadly studied technique, allowing order-of-magnitude reductions in the size and compute needed to execute a network, while maintaining high accuracy. DeepSparse is sparsity-aware, meaning it skips the zeroed out parameters, shrinking amount of compute in a forward pass. Since the sparse computation is now memory bound, DeepSparse executes the network depth-wise, breaking the problem into Tensor Columns, vertical stripes of computation that fit in cache.
 
 <p align="center">
   <img width="60%" src="https://github.com/neuralmagic/deepsparse/raw/main/examples/ultralytics-yolo/ultralytics-readmes/tensor-columns.png">
@@ -96,8 +92,7 @@ wget -O basilica.jpg https://raw.githubusercontent.com/neuralmagic/deepsparse/ma
 
 #### Python API
 
-`Pipelines` wrap pre-processing and output post-processing around the runtime, providing a clean interface for adding DeepSparse to an application.
-The DeepSparse-Ultralytics integration includes an out-of-the-box `Pipeline` that accepts raw images and outputs the bounding boxes.
+`Pipelines` wrap pre-processing and output post-processing around the runtime, providing a clean interface for adding DeepSparse to an application. The DeepSparse-Ultralytics integration includes an out-of-the-box `Pipeline` that accepts raw images and outputs the bounding boxes.
 
 Create a `Pipeline` and run inference:
 
@@ -127,9 +122,7 @@ apt-get install libgl1-mesa-glx
 
 #### HTTP Server
 
-DeepSparse Server runs on top of the popular FastAPI web framework and Uvicorn web server. With just a single CLI command, you can easily setup a model
-service endpoint with DeepSparse. The Server supports any Pipeline from DeepSparse, including object detection with YOLOv5, enabling you to send raw
-images to the endpoint and receive the bounding boxes.
+DeepSparse Server runs on top of the popular FastAPI web framework and Uvicorn web server. With just a single CLI command, you can easily setup a model service endpoint with DeepSparse. The Server supports any Pipeline from DeepSparse, including object detection with YOLOv5, enabling you to send raw images to the endpoint and receive the bounding boxes.
 
 Spin up the Server with the pruned-quantized YOLOv5s:
 

docs/yolov5/tutorials/pytorch_hub_model_loading.md

@@ -4,8 +4,7 @@ description: Detailed guide on loading YOLOv5 from PyTorch Hub. Includes example
 keywords: Ultralytics, YOLOv5, PyTorch, loading YOLOv5, PyTorch Hub, inference, multi-GPU inference, training
 ---
 
-📚 This guide explains how to load YOLOv5 🚀 from PyTorch Hub at [https://pytorch.org/hub/ultralytics_yolov5](https://pytorch.org/hub/ultralytics_yolov5).
-UPDATED 26 March 2023.
+📚 This guide explains how to load YOLOv5 🚀 from PyTorch Hub at [https://pytorch.org/hub/ultralytics_yolov5](https://pytorch.org/hub/ultralytics_yolov5). UPDATED 26 March 2023.
 
 ## Before You Start
 

docs/yolov5/tutorials/roboflow_datasets_integration.md

@@ -6,8 +6,7 @@ keywords: Ultralytics, YOLOv5, Roboflow, data organization, data labelling, data
 
 # Roboflow Datasets
 
-You can now use Roboflow to organize, label, prepare, version, and host your datasets for training YOLOv5 🚀 models. Roboflow is free to use with YOLOv5 if you make your workspace public.
-UPDATED 7 June 2023.
+You can now use Roboflow to organize, label, prepare, version, and host your datasets for training YOLOv5 🚀 models. Roboflow is free to use with YOLOv5 if you make your workspace public. UPDATED 7 June 2023.
 
 !!! warning
 

docs/yolov5/tutorials/running_on_jetson_nano.md

@@ -6,8 +6,7 @@ keywords: TensorRT, NVIDIA Jetson, DeepStream SDK, deployment, Ultralytics, YOLO
 
 # Deploy on NVIDIA Jetson using TensorRT and DeepStream SDK
 
-📚 This guide explains how to deploy a trained model into NVIDIA Jetson Platform and perform inference using TensorRT and DeepStream SDK. Here we use TensorRT to maximize the inference performance on the Jetson platform.
-UPDATED 18 November 2022.
+📚 This guide explains how to deploy a trained model into NVIDIA Jetson Platform and perform inference using TensorRT and DeepStream SDK. Here we use TensorRT to maximize the inference performance on the Jetson platform. UPDATED 18 November 2022.
 
 ## Hardware Verification
 

docs/yolov5/tutorials/test_time_augmentation.md

@@ -6,8 +6,7 @@ keywords: YOLOv5, Ultralytics, Test-Time Augmentation, TTA, mAP, Recall, model p
 
 # Test-Time Augmentation (TTA)
 
-📚 This guide explains how to use Test Time Augmentation (TTA) during testing and inference for improved mAP and Recall with YOLOv5 🚀.
-UPDATED 25 September 2022.
+📚 This guide explains how to use Test Time Augmentation (TTA) during testing and inference for improved mAP and Recall with YOLOv5 🚀. UPDATED 25 September 2022.
 
 ## Before You Start
 

docs/yolov5/tutorials/tips_for_best_training_results.md

@@ -4,8 +4,7 @@ description: Our comprehensive guide provides insights on how to train your YOLO
 keywords: Ultralytics, YOLOv5, Training guide, dataset preparation, model selection, training settings, mAP results, Machine Learning, Object Detection
 ---
 
-📚 This guide explains how to produce the best mAP and training results with YOLOv5 🚀.
-UPDATED 25 May 2022.
+📚 This guide explains how to produce the best mAP and training results with YOLOv5 🚀. UPDATED 25 May 2022.
 
 Most of the time good results can be obtained with no changes to the models or training settings, **provided your dataset is sufficiently large and well labelled**. If at first you don't get good results, there are steps you might be able to take to improve, but we always recommend users **first train with all default settings** before considering any changes. This helps establish a performance baseline and spot areas for improvement.
 

docs/yolov5/tutorials/train_custom_data.md

@@ -4,8 +4,7 @@ description: Learn how to train your data on custom datasets using YOLOv5. Simpl
 keywords: YOLOv5, train on custom dataset, image collection, model training, object detection, image labelling, Ultralytics, PyTorch, machine learning
 ---
 
-📚 This guide explains how to train your own **custom dataset** with [YOLOv5](https://github.com/ultralytics/yolov5) 🚀.
-UPDATED 7 June 2023.
+📚 This guide explains how to train your own **custom dataset** with [YOLOv5](https://github.com/ultralytics/yolov5) 🚀. UPDATED 7 June 2023.
 
 ## Before You Start
 
@@ -49,35 +48,27 @@ Once you have collected images, you will need to annotate the objects of interes
 
 <p align="center"><a href="https://app.roboflow.com/?model=yolov5&ref=ultralytics" title="Create a Free Roboflow Account"><img width="450" src="https://uploads-ssl.webflow.com/5f6bc60e665f54545a1e52a5/6152a275ad4b4ac20cd2e21a_roboflow-annotate.gif" /></a></p>
 
-[Roboflow Annotate](https://roboflow.com/annotate?ref=ultralytics) is a simple
-web-based tool for managing and labeling your images with your team and exporting
-them in [YOLOv5's annotation format](https://roboflow.com/formats/yolov5-pytorch-txt?ref=ultralytics).
+[Roboflow Annotate](https://roboflow.com/annotate?ref=ultralytics) is a simple web-based tool for managing and labeling your images with your team and exporting them in [YOLOv5's annotation format](https://roboflow.com/formats/yolov5-pytorch-txt?ref=ultralytics).
 
 ### 1.3 Prepare Dataset for YOLOv5
 
 Whether you [label your images with Roboflow](https://roboflow.com/annotate?ref=ultralytics) or not, you can use it to convert your dataset into YOLO format, create a YOLOv5 YAML configuration file, and host it for importing into your training script.
 
 [Create a free Roboflow account](https://app.roboflow.com/?model=yolov5&ref=ultralytics)
-and upload your dataset to a `Public` workspace, label any unannotated images,
-then generate and export a version of your dataset in `YOLOv5 Pytorch` format.
+and upload your dataset to a `Public` workspace, label any unannotated images, then generate and export a version of your dataset in `YOLOv5 Pytorch` format.
 
-Note: YOLOv5 does online augmentation during training, so we do not recommend
-applying any augmentation steps in Roboflow for training with YOLOv5. But we
-recommend applying the following preprocessing steps:
+Note: YOLOv5 does online augmentation during training, so we do not recommend applying any augmentation steps in Roboflow for training with YOLOv5. But we recommend applying the following preprocessing steps:
 
 <p align="center"><img width="450" src="https://uploads-ssl.webflow.com/5f6bc60e665f54545a1e52a5/6152a273477fccf42a0fd3d6_roboflow-preprocessing.png" title="Recommended Preprocessing Steps" /></p>
 
 * **Auto-Orient** - to strip EXIF orientation from your images.
 * **Resize (Stretch)** - to the square input size of your model (640x640 is the YOLOv5 default).
 
-Generating a version will give you a point in time snapshot of your dataset so
-you can always go back and compare your future model training runs against it,
-even if you add more images or change its configuration later.
+Generating a version will give you a point in time snapshot of your dataset so you can always go back and compare your future model training runs against it, even if you add more images or change its configuration later.
 
 <p align="center"><img width="450" src="https://uploads-ssl.webflow.com/5f6bc60e665f54545a1e52a5/6152a2733fd1da943619934e_roboflow-export.png" title="Export in YOLOv5 Format" /></p>
 
-Export in `YOLOv5 Pytorch` format, then copy the snippet into your training
-script or notebook to download your dataset.
+Export in `YOLOv5 Pytorch` format, then copy the snippet into your training script or notebook to download your dataset.
 
 <p align="center"><img width="450" src="https://uploads-ssl.webflow.com/5f6bc60e665f54545a1e52a5/6152a273a92e4f5cb72594df_roboflow-snippet.png" title="Roboflow dataset download snippet" /></p>
 

docs/yolov5/tutorials/transfer_learning_with_frozen_layers.md

@@ -4,8 +4,7 @@ description: Learn to freeze YOLOv5 layers for efficient transfer learning. Opti
 keywords: YOLOv5, freeze layers, transfer learning, model retraining, Ultralytics
 ---
 
-📚 This guide explains how to **freeze** YOLOv5 🚀 layers when **transfer learning**. Transfer learning is a useful way to quickly retrain a model on new data without having to retrain the entire network. Instead, part of the initial weights are frozen in place, and the rest of the weights are used to compute loss and are updated by the optimizer. This requires less resources than normal training and allows for faster training times, though it may also result in reductions to final trained accuracy.
-UPDATED 25 September 2022.
+📚 This guide explains how to **freeze** YOLOv5 🚀 layers when **transfer learning**. Transfer learning is a useful way to quickly retrain a model on new data without having to retrain the entire network. Instead, part of the initial weights are frozen in place, and the rest of the weights are used to compute loss and are updated by the optimizer. This requires less resources than normal training and allows for faster training times, though it may also result in reductions to final trained accuracy. UPDATED 25 September 2022.
 
 ## Before You Start