Architecture: Resnet-18 with two modifications.
- 1 channel Conv2D as the first layer.
- 2-way output on FC layer.
Training procedure:
- Pre-trained in ImageNet.
- Further training on FashionMNIST.
- Final training on the task of predicting if Fashion-MNIST images are flipped vertically or not.
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no library tag.