# Convert PyTorch YOLOv5s model to ONNX or tensorflow format from google colab

**URL:** https://forum.opencv.org/t/convert-pytorch-yolov5s-model-to-onnx-or-tensorflow-format-from-google-colab/4984
**Category:** Uncategorized
**Tags:** dnn
**Created:** [August 30, 2021, 5:12pm UTC](https://forum.opencv.org/t/convert-pytorch-yolov5s-model-to-onnx-or-tensorflow-format-from-google-colab/4984 "2021-08-30T17:12:25Z")
**Posts on this page:** 2
**Page:** 1

<div class="post-metadata">

### Author: ![Alex\_Bilityuk](https://sea2.discourse-cdn.com/flex020/user_avatar/forum.opencv.org/alex_bilityuk/32/2949_2.png) [@Alex\_Bilityuk](https://forum.opencv.org/u/Alex_Bilityuk)
#### Post date: [August 30, 2021, 5:12pm UTC](https://forum.opencv.org/t/convert-pytorch-yolov5s-model-to-onnx-or-tensorflow-format-from-google-colab/4984/1 "2021-08-30T17:12:25Z")

</div>

Hi, i successfully trained a YOLOv5s model (.pt) in google colab. Could anyone please help me to find a way of how to convert PyTorch model weight format (.pt) to ONNX or tensorflow format using google colab?

Here is my colab code i try:

```auto
from torch.autograd import Variable

import torch.onnx

import torchvision

import torch

dummy_input = Variable(torch.randn(16, 3, 416, 416))

model = torch.load('/content/yolov5/runs/train/yolov5s_results2/weights/best.pt')

torch.onnx.export(model, dummy_input, "/content/yolov5/runs/train/yolov5s_results2/weights/pytorch_model.onnx")

```

But after run the code i’ve got some errors:

```auto
AttributeError Traceback (most recent call last)

<ipython-input-18-cef2b6adb415> in <module>()
      6 dummy_input = Variable(torch.randn(16, 3, 416, 416))
      7 model = torch.load('/content/yolov5/runs/train/yolov5s_results/weights/best.pt')
----> 8 torch.onnx.export(model,dummy_input,"/content/yolov5/runs/train/yolov5s_results/weights/pytorch_model.onnx")

4 frames

/usr/local/lib/python3.7/dist-packages/torch/onnx/utils.py in select_model_mode_for_export(model, mode)
     36 def select_model_mode_for_export(model, mode):
     37 if not isinstance(model, torch.jit.ScriptFunction):
---> 38 is_originally_training = model.training
     39 
     40 if mode is None:

AttributeError: 'dict' object has no attribute 'training'

```

What am i doing wrong?

---

<div class="post-metadata">

### Author: ![berak](https://avatars.discourse-cdn.com/v4/letter/b/85f322/32.png) [@berak](https://forum.opencv.org/u/berak)
#### Post date: [August 30, 2021, 5:34pm UTC](https://forum.opencv.org/t/convert-pytorch-yolov5s-model-to-onnx-or-tensorflow-format-from-google-colab/4984/2 "2021-08-30T17:34:13Z")

</div>

> [@Alex\_Bilityuk](#):
>
> `model = torch.load('/content/yolov5/runs/train/yolov5s_results/weights/best.pt')`

torch.load() only loads the “state\_dict”, this is NOT the actual model.

but i’m a bit confused here, there is some code like:

```
model = torch.load("weights/yolov5s.pt")['model']

```

on the other hand, the usual way to load a pytorch model is:

```
model = SomeNetwork() # first construct an empty nn from *code*
model.load_state_dict( torch.load("my.pth")) # fill in data

```