Commit
·
b0518d1
1
Parent(s):
b25ac90
Update the READ.me
Browse filesAdded information on the source of the model, the dataset used to create the model and a link to an example to use the model.
README.md
CHANGED
|
@@ -1,3 +1,13 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
---
|
| 4 |
+
A simple single label classification model, ResNet18, to predict the cat or dog breed from the provided image. The model was created in Fast.ai
|
| 5 |
+
and exported to ONNX using PyTorch's ONNX export capabilities.
|
| 6 |
+
|
| 7 |
+
The source dataset is the OXFORD-IIIT PET. Omkar M Parkhi, Andrea Vedaldi, Andrew Zisserman and C. V. Jawahar
|
| 8 |
+
We have created a 37 category pet dataset with roughly 200 images for each class.
|
| 9 |
+
The images have a large variations in scale, pose and lighting. All images havean
|
| 10 |
+
associated ground truth annotation of breed, head ROI, and pixel level trimap segmentation.
|
| 11 |
+
|
| 12 |
+
The ONNX model can be used in other frameworks like Elixir's Axon. An example of converting the ONNX model into Axon can be found at:
|
| 13 |
+
https://github.com/elixir-nx/axon/tree/main/notebooks/onnx_to_axon.livemd.
|