Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,62 @@
+---
+license: apache-2.0
+library_name: mlx-image
+tags:
+- mlx
+- mlx-image
+- vision
+- image-classification
+datasets:
+- imagenet-1k
+---
+# regnet_y_8gf
+
+A RegNetY-8GF image classification model. Pretrained in ImageNet by torchvision contributors (see ImageNet1K-V2 weight details https://github.com/pytorch/vision/issues/3995#new-recipe).
+
+Disclaimer: This is a porting of the torch model weights to Apple MLX Framework.
+
+## How to use
+```bash
+pip install mlx-image
+```
+
+Here is how to use this model for image classification:
+
+```python
+from mlxim.model import create_model
+from mlxim.io import read_rgb
+from mlxim.transform import ImageNetTransform
+
+transform = ImageNetTransform(train=False, img_size=224)
+x = transform(read_rgb("cat.png"))
+x = mx.expand_dims(x, 0)
+
+model = create_model("regnet_y_8gf")
+model.eval()
+
+logits = model(x)
+```
+
+You can also use the embeds from layer before head:
+```python
+from mlxim.model import create_model
+from mlxim.io import read_rgb
+from mlxim.transform import ImageNetTransform
+
+transform = ImageNetTransform(train=False, img_size=224)
+x = transform(read_rgb("cat.png"))
+x = mx.expand_dims(x, 0)
+
+# first option
+model = create_model("regnet_y_8gf", num_classes=0)
+model.eval()
+
+embeds = model(x)
+
+# second option
+model = create_model("regnet_y_8gf")
+model.eval()
+
+embeds = model.get_features(x)
+```
+