README.md

metadata

{}

---
license: apache-2.0
tags:
- mlx
- mlx-image
- vision
- image-classification
datasets:
- imagenet-1k
library_name: mlx-image
---
# regnet_y_800mf

A RegNetY-800MF 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_800mf")
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_800mf", num_classes=0)
model.eval()

embeds = model(x)

# second option
model = create_model("regnet_y_800mf")
model.eval()

embeds = model.get_features(x)
```