models/

[giscus[bot]]

models/

Discover a variety of models supported by Ultralytics, including YOLOv3 to YOLOv10, NAS, SAM, and RT-DETR for detection, segmentation, and more.

https://docs.ultralytics.com/models/

[learningDude1]

I've already installed Ultralytics in a separate Conda environment and trained a YOLOv8 model. Now I want to use the YOLOv10 model. Do I need to create a new environment and set it up from scratch, or can I train or use YOLOv10 in the existing YOLOv8 environment?

[glenn-jocher]

You can use YOLOv10 in the same environment where you have YOLOv8 installed. Simply load the YOLOv10 model using the Ultralytics library and proceed with training or inference as needed. No need to create a new environment.

[huilin66]

is there a reference yaml for yolov7 and yolov4, like yolov6.yaml?

[glenn-jocher]

@huilin66 you can find the reference YAML files for YOLOv7 and YOLOv4 in the Ultralytics GitHub repository under the models directory. If you need further details, please refer to the Ultralytics documentation.

[ViniciusVViana]

I need help. I use this YOLO architecture in a university project, and to make the article i need to specify the numbem of hidden layers, and i don't how many there are.

[glenn-jocher]

@ViniciusVViana for details on the number of hidden layers in YOLO architectures, you can refer to the model configuration files in the Ultralytics repository. Each model's YAML file specifies its architecture, including layers. If you need further assistance, please check the documentation or community forums.

[Dileep-utl]

I am trying to train my yolov8s-worldv2.pt with custom data on colab with TPU as engine but getting error as "RuntimeError: Cannot set version_counter for inference tensor " tried with most possible version but even after setup TPU still facing same issue. I need help with it so i can you TPU to train models

!pip install cloud-tpu-client==0.10
!pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118
!pip install torch_xla --extra-index-url https://storage.googleapis.com/tpu-pytorch/wheels
!pip install ultralytics==8.3.24 # Install the latest version of Ultralytics

import torch
import torch_xla
import torch_xla.core.xla_model as xm

Print versions to confirm installation

print(f"PyTorch version: {torch.version}")
print(f"torch-xla version: {torch_xla.version}")
with output---->

PyTorch version: 2.5.0+cpu
torch-xla version: 2.5.0+libtpu

import torch_xla.core.xla_model as xm
device = xm.xla_device()
print(f"Using device: {device}")
with output---->
Using device: xla:0

results = model.train(data="lvis.yaml", epochs=2, imgsz=640, device=device)

output as error------->

RuntimeError: Cannot set version_counter for inference tensor

[glenn-jocher]

@Dileep-utl it seems like you're encountering a compatibility issue with TPU and PyTorch versions. Ensure that your PyTorch and torch-xla versions are compatible with TPU. You might want to check the official PyTorch XLA documentation for the correct setup. If the issue persists, consider using a GPU instead for training.

[Dileep-utl]

I am trying to train my yolov8s-worldv2.pt with custom data on colab with TPU as engine but getting error as "RuntimeError: Cannot set version_counter for inference tensor " tried with most possible version but even after setup TPU still facing same issue. I need help with it so i can you TPU to train models

!pip install cloud-tpu-client==0.10
!pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118
!pip install torch_xla --extra-index-url https://storage.googleapis.com/tpu-pytorch/wheels
!pip install ultralytics==8.3.24 # Install the latest version of Ultralytics

import torch
import torch_xla
import torch_xla.core.xla_model as xm

Print versions to confirm installation

print(f"PyTorch version: {torch.version}")
print(f"torch-xla version: {torch_xla.version}")
with output---->

PyTorch version: 2.5.0+cpu
torch-xla version: 2.5.0+libtpu

import torch_xla.core.xla_model as xm
device = xm.xla_device()
print(f"Using device: {device}")
with output---->
Using device: xla:0

results = model.train(data="lvis.yaml", epochs=2, imgsz=640, device=device)

output as error------->

RuntimeError: Cannot set version_counter for inference tensor

[glenn-jocher]

@Dileep-utl it seems you're encountering an issue with TPU compatibility. Currently, YOLO models are optimized for GPU usage. For TPU support, you might need to explore alternative configurations or consider using a GPU environment. For more details, please refer to our documentation: https://docs.ultralytics.com/models/.