# Custom training parameters used for Fall\_Detection Project **URL:** \ **Category:** 🤝 Community Help\ **Created:** [July 19, 2023, 2:28am UTC](https://discuss.roboflow.com/t/custom-training-parameters-used-for-fall-detection-project/2700 "2023-07-19T02:28:48Z")\ **Posts on this page:** 7\ **Page:** 1
**Author:** ![Muhammad\_Nauman](https://yyz1.discourse-cdn.com/flex029/user_avatar/discuss.roboflow.com/muhammad_nauman/32/2415_2.png) [@Muhammad\_Nauman](https://discuss.roboflow.com/u/Muhammad_Nauman)\ **Post date:** [July 19, 2023, 2:28am UTC](https://discuss.roboflow.com/t/custom-training-parameters-used-for-fall-detection-project/2700/1 "2023-07-19T02:28:48Z")
Hey Everyone! I wanted to ask if anybody knows what training parameters were used for this specific model generation (mAP 88.6%, Precision 85.1%, Recall 86.1%): > **[How to Use the Fall Detection Object Detection API](https://universe.roboflow.com/roboflow-universe-projects/fall-detection-ca3o8/model/4)** > > Learn how to use the Fall Detection Object Detection API (v4, resized640\_aug3x-ACCURATE), created by Roboflow Universe Projects I mean the training parameters given while starting the training like: yolo task=detect mode=train model=yolov8s.pt data={dataset.location}/data.yaml epochs=25 imgsz=800 plots=True Because when I follow the above for the same dataset, I get much lower values of mAP, Precision and Recall. Why is that so **Project Type** : Object detection **Operating System & Browser** : Windows and Google Chrome **Project Link** : [How to Use the Fall Detection Object Detection API](https://universe.roboflow.com/roboflow-universe-projects/fall-detection-ca3o8/model/4) ---
**Author:** ![leo](https://yyz1.discourse-cdn.com/flex029/user_avatar/discuss.roboflow.com/leo/32/2228_2.png) [@leo](https://discuss.roboflow.com/u/leo)\ **Post date:** [July 19, 2023, 3:17am UTC](https://discuss.roboflow.com/t/custom-training-parameters-used-for-fall-detection-project/2700/2 "2023-07-19T03:17:56Z")
Hi @Muhammad_Nauman It looks like the model in the link you sent was trained on [Roboflow Train](https://docs.roboflow.com/train/train). You can learn how to use it in the link I attached. ---
**Author:** ![Muhammad\_Nauman](https://yyz1.discourse-cdn.com/flex029/user_avatar/discuss.roboflow.com/muhammad_nauman/32/2415_2.png) [@Muhammad\_Nauman](https://discuss.roboflow.com/u/Muhammad_Nauman)\ **Post date:** [July 19, 2023, 3:23am UTC](https://discuss.roboflow.com/t/custom-training-parameters-used-for-fall-detection-project/2700/3 "2023-07-19T03:23:36Z")
Thanks! Is there any way to know the specific parameters only if I want to train it locally on my GPU? ---
**Author:** ![leo](https://yyz1.discourse-cdn.com/flex029/user_avatar/discuss.roboflow.com/leo/32/2228_2.png) [@leo](https://discuss.roboflow.com/u/leo)\ **Post date:** [July 19, 2023, 3:29am UTC](https://discuss.roboflow.com/t/custom-training-parameters-used-for-fall-detection-project/2700/4 "2023-07-19T03:29:14Z")
Hi @Muhammad_Nauman We don’t publish what specific parameters are used for training a specific model on Roboflow Train. From the [dataset version](https://universe.roboflow.com/roboflow-universe-projects/fall-detection-ca3o8/dataset/3) that it was generated on, I see that it was resized to 640 x 640, but I don’t have more information beyond that. Would you mind sharing what your use case for training the model locally would be? ---
**Author:** ![Muhammad\_Nauman](https://yyz1.discourse-cdn.com/flex029/user_avatar/discuss.roboflow.com/muhammad_nauman/32/2415_2.png) [@Muhammad\_Nauman](https://discuss.roboflow.com/u/Muhammad_Nauman)\ **Post date:** [July 19, 2023, 3:37am UTC](https://discuss.roboflow.com/t/custom-training-parameters-used-for-fall-detection-project/2700/5 "2023-07-19T03:37:46Z")
I want to compare fall detection rates wrt age group for a survey ---
**Author:** ![Muhammad\_Nauman](https://yyz1.discourse-cdn.com/flex029/user_avatar/discuss.roboflow.com/muhammad_nauman/32/2415_2.png) [@Muhammad\_Nauman](https://discuss.roboflow.com/u/Muhammad_Nauman)\ **Post date:** [July 19, 2023, 3:42am UTC](https://discuss.roboflow.com/t/custom-training-parameters-used-for-fall-detection-project/2700/6 "2023-07-19T03:42:09Z")
I have another query. Can the Trained Model API for this project be used directly with an rtsp camera? ---
**Author:** ![leo](https://yyz1.discourse-cdn.com/flex029/user_avatar/discuss.roboflow.com/leo/32/2228_2.png) [@leo](https://discuss.roboflow.com/u/leo)\ **Post date:** [July 19, 2023, 3:57am UTC](https://discuss.roboflow.com/t/custom-training-parameters-used-for-fall-detection-project/2700/7 "2023-07-19T03:57:46Z")
We do have [a variety of deployment methods available](https://docs.roboflow.com/deploy/supported-deployment-devices), but we don’t have something to directly connect to a RTSP camera at the moment.