Update README.md with new model card content

README.md

@@ -1,13 +1,124 @@
 ---
 library_name: keras-hub
 ---
-This is a [`SegFormer` model](https://keras.io/api/keras_hub/models/seg_former) uploaded using the KerasHub library and can be used with JAX, TensorFlow, and PyTorch backends.
-This model is related to a `ImageSegmenter` task.
+### Model Overview
+The SegFormer model was proposed in SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers by Enze Xie, Wenhai Wang, Zhiding Yu, Anima Anandkumar, Jose M. Alvarez, Ping Luo. The model consists of a hierarchical Transformer encoder and a lightweight all-MLP decode head to achieve great results on image segmentation benchmarks such as ADE20K and Cityscapes.
 
-Model config:
-* **name:** seg_former_backbone
-* **trainable:** True
-* **projection_filters:** 768
-* **image_encoder:** {'module': 'keras_hub.src.models.mit.mit_backbone', 'class_name': 'MiTBackbone', 'config': {'name': 'mi_t_backbone', 'trainable': True, 'layerwise_depths': [3, 4, 18, 3], 'hidden_dims': [64, 128, 320, 512], 'image_shape': [512, 512, 3], 'num_layers': 4, 'layerwise_num_heads': [1, 2, 5, 8], 'layerwise_sr_ratios': [8, 4, 2, 1], 'max_drop_path_rate': 0.1, 'layerwise_patch_sizes': [7, 3, 3, 3], 'layerwise_strides': [4, 2, 2, 2]}, 'registered_name': 'keras_hub>MiTBackbone'}
+`
+Weights are released under the [MIT License](https://opensource.org/license/mit). Keras model code is released under the [Apache 2 License](https://github.com/keras-team/keras-hub/blob/master/LICENSE).
 
-This model card has been generated automatically and should be completed by the model author. See [Model Cards documentation](https://huggingface.co/docs/hub/model-cards) for more information.
+## Links
+
+* [Segmentation Quickstart Notebook](https://www.kaggle.com/code/divyasss/deeplabv3plus-quickstart)
+* [SegFormer API Documentation](https://keras.io/api/keras_cv/models/tasks/segformer_b0)
+* [SegFormer Model Card](https://huggingface.co/docs/transformers/en/model_doc/segformer)
+
+
+## Installation
+
+Keras and KerasCV can be installed with:
+
+```
+pip install -U -q keras-cv
+pip install -U -q keras>=3
+```
+
+Jax, TensorFlow, and Torch come preinstalled in Kaggle Notebooks. For instructions on installing them in another environment see the [Keras Getting Started](https://keras.io/getting_started/) page.
+
+## Presets
+
+The following model checkpoints are provided by the Keras team. Full code examples for each are available below.
+| Preset name           | Parameters | Description                                       |
+|-----------------------|------------|---------------------------------------------------|
+| segformer_b0_imagenet | 3.72M      | SegFormer model with a pretrained MiTB0 backbone. |
+| segformer_b0          | 3.72M      | SegFormer model with MiTB0 backbone.              |
+| segformer_b1          | 13.68M     | SegFormer model with MiTB1 backbone.              |
+| segformer_b2          | 24.73M     | SegFormer model with MiTB2 backbone.              |
+| segformer_b3          | 44.60M     | SegFormer model with MiTB3 backbone.              |
+| segformer_b4          | 61.37M     | SegFormer model with MiTB4 backbone.              |
+| segformer_b5          | 81.97M     | SegFormer model with MiTB5 backbone.              |
+
+## Example code
+
+```Python
+import keras_cv
+
+images = np.ones(shape=(1, 224, 224, 3))
+labels = np.zeros(shape=(1, 224, 224, 1))
+
+
+model = keras_cv.models.SegFormer.from_preset(
+            "segformer_b0", num_classes=2
+        )
+# Evaluate model
+model(images)
+```
+
+## Example Usage
+```python
+import keras_cv
+import  keras
+import numpy as np
+```
+
+
+
+Using the class with a `backbone`:
+
+```python
+import tensorflow as tf
+import keras_cv
+
+images = np.ones(shape=(1, 96, 96, 3))
+labels = np.zeros(shape=(1, 96, 96, 1))
+backbone = keras_cv.models.MiTBackbone.from_preset("segformer_b3_ade20k_512")
+model = keras_cv.models.segmentation.SegFormer(
+    num_classes=1, backbone=backbone,
+)
+
+# Evaluate model
+model(images)
+
+# Train model
+model.compile(
+    optimizer="adam",
+    loss=keras.losses.BinaryCrossentropy(from_logits=False),
+    metrics=["accuracy"],
+)
+model.fit(images, labels, epochs=3)
+```
+
+## Example Usage with Hugging Face URI
+
+```python
+import keras_cv
+import  keras
+import numpy as np
+```
+
+
+
+Using the class with a `backbone`:
+
+```python
+import tensorflow as tf
+import keras_cv
+
+images = np.ones(shape=(1, 96, 96, 3))
+labels = np.zeros(shape=(1, 96, 96, 1))
+backbone = keras_cv.models.MiTBackbone.from_preset("hf://keras/segformer_b3_ade20k_512")
+model = keras_cv.models.segmentation.SegFormer(
+    num_classes=1, backbone=backbone,
+)
+
+# Evaluate model
+model(images)
+
+# Train model
+model.compile(
+    optimizer="adam",
+    loss=keras.losses.BinaryCrossentropy(from_logits=False),
+    metrics=["accuracy"],
+)
+model.fit(images, labels, epochs=3)
+```