# Transfer learning with ResNet: very low accuracy

**URL:** <https://discuss.pytorch.org/t/transfer-learning-with-resnet-very-low-accuracy/50694>\
**Category:** Uncategorized\
**Created:** [July 16, 2019, 4:40am UTC](https://discuss.pytorch.org/t/transfer-learning-with-resnet-very-low-accuracy/50694 "2019-07-16T04:40:44Z")\
**Posts on this page:** 1\
**Showing post:** 2

<div class="post-metadata">

**Author:** ![tree33](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/tree33/32/10609_2.png) [@tree33](https://discuss.pytorch.org/u/tree33)\
**Post date:** [July 16, 2019, 6:21am UTC](https://discuss.pytorch.org/t/transfer-learning-with-resnet-very-low-accuracy/50694/2 "2019-07-16T06:21:18Z")

</div>

What about the performance if you do not use a pretrained model?  
If that’s all right, then the problem is probably about imput normalization

Please check the following post for more details.

> [@What's the range of the input value desired to use pretrained resnet152 and vgg19?](https://discuss.pytorch.org/t/whats-the-range-of-the-input-value-desired-to-use-pretrained-resnet152-and-vgg19/1683/2):
>
> input image is first loaded to range [0, 1] and then this normalization is applied to RGB image as described here: All pre-trained models expect input images normalized in the same way, i.e. mini-batches of 3-channel RGB images of shape (3 x H x W), where H and W are expected to be atleast 224. The images have to be loaded in to a range of [0, 1] and then normalized using mean=[0.485, 0.456, 0.406] and std=[0.229, 0.224, 0.225] An example of such normalization can be found in the imagenet …

---

_[View the full topic](https://discuss.pytorch.org/t/transfer-learning-with-resnet-very-low-accuracy/50694)._