Procedure of training the model offline.

[nareshku397]

Search before asking

• I have searched the YOLOv5 issues and discussions and found no similar questions.

Question

Can you please tell the procedure which have to be followed to train model offline on pc. I have searched on the multiple sources but I am unable to find the procedure at all,

Additional

I have trained model in the older version. Currently I have annotated the images all the things are ready but I am stuck in finding a procedure from where I can start. Thanks

[glenn-jocher]

@nareshku397 see Train Custom Data tutorial:

Tutorials

• Train Custom Data  🚀 RECOMMENDED
• Tips for Best Training Results  ☘️ RECOMMENDED
• Multi-GPU Training
• PyTorch Hub 🌟 NEW
• TFLite, ONNX, CoreML, TensorRT Export 🚀
• Test-Time Augmentation (TTA)
• Model Ensembling
• Model Pruning/Sparsity
• Hyperparameter Evolution
• Transfer Learning with Frozen Layers
• Architecture Summary 🌟 NEW
• Weights & Biases Logging
• Roboflow for Datasets, Labeling, and Active Learning  🌟 NEW
• ClearML Logging 🌟 NEW
• Deci Platform 🌟 NEW
• Comet Logging 🌟 NEW

Good luck 🍀 and let us know if you have any other questions!

[nareshku397]

Hello Thank you very much that you help me but I have a question that when I am trying to train my custom model I have changed the dataset path in the file coco128.yaml and then i run train.py it is running but when i am trying to execute the detect.py it is actually working on the previous dataset even I am given testing data of my new dataset. so kindly help me out to resolve this issue. Thanks in advance.

…

On Thu, Oct 6, 2022 at 12:23 AM Glenn Jocher ***@***.***> wrote: @nareshku397 <https://github.com/nareshku397> see Train Custom Data tutorial: Tutorials - Train Custom Data <https://docs.ultralytics.com/yolov5/tutorials/train_custom_data> 🚀 RECOMMENDED - Tips for Best Training Results <https://docs.ultralytics.com/guides/model-training-tips/> ☘️ RECOMMENDED - Multi-GPU Training <https://docs.ultralytics.com/yolov5/tutorials/multi_gpu_training> - PyTorch Hub <https://docs.ultralytics.com/yolov5/tutorials/pytorch_hub_model_loading> 🌟 NEW - TFLite, ONNX, CoreML, TensorRT Export <https://docs.ultralytics.com/yolov5/tutorials/model_export> 🚀 - Test-Time Augmentation (TTA) <https://docs.ultralytics.com/yolov5/tutorials/test_time_augmentation> - Model Ensembling <https://docs.ultralytics.com/yolov5/tutorials/model_ensembling> - Model Pruning/Sparsity <https://docs.ultralytics.com/yolov5/tutorials/model_pruning_and_sparsity> - Hyperparameter Evolution <https://docs.ultralytics.com/yolov5/tutorials/hyperparameter_evolution> - Transfer Learning with Frozen Layers <https://docs.ultralytics.com/yolov5/tutorials/transfer_learning_with_frozen_layers> - Architecture Summary <https://docs.ultralytics.com/yolov5/tutorials/architecture_description> 🌟 NEW - Weights & Biases Logging <https://github.com/ultralytics/yolov5/issues/1289> - Roboflow for Datasets, Labeling, and Active Learning <https://docs.ultralytics.com/yolov5/tutorials/roboflow_datasets_integration> 🌟 NEW - ClearML Logging <https://docs.ultralytics.com/yolov5/tutorials/clearml_logging_integration> 🌟 NEW - Deci Platform <https://github.com/ultralytics/yolov5/wiki/Deci-Platform> 🌟 NEW - Comet Logging <https://docs.ultralytics.com/yolov5/tutorials/comet_logging_integration> 🌟 NEW Good luck 🍀 and let us know if you have any other questions! — Reply to this email directly, view it on GitHub <#9700 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AWN7S6EGZ3FN37U5ZNPD57DWBXIRPANCNFSM6AAAAAAQ5JREJI> . You are receiving this because you were mentioned.Message ID: ***@***.***>

[pderrenger]

@nareshku397 ensure you're loading the correct weights file in detect.py by specifying the path to your trained model using the --weights argument. If the issue persists, verify that your dataset paths are correctly configured.