Update README.md with new model card content

README.md

@@ -1,17 +1,35 @@
 ---
 library_name: keras-hub
 ---
-This is a [`BASNet` model](https://keras.io/api/keras_hub/models/bas_net) uploaded using the KerasHub library and can be used with JAX, TensorFlow, and PyTorch backends.
-This model is related to a `ImageSegmenter` task.
-
-Model config:
-* **name:** bas_net_backbone
-* **trainable:** True
-* **image_encoder:** {'module': 'keras_hub.src.models.resnet.resnet_backbone', 'class_name': 'ResNetBackbone', 'config': {'name': 'res_net_backbone', 'trainable': True, 'input_conv_filters': [64], 'input_conv_kernel_sizes': [7], 'stackwise_num_filters': [64, 128, 256, 512], 'stackwise_num_blocks': [3, 4, 6, 3], 'stackwise_num_strides': [1, 2, 2, 2], 'block_type': 'basic_block', 'use_pre_activation': False, 'image_shape': [None, None, 3]}, 'registered_name': 'keras_hub>ResNetBackbone'}
-* **num_classes:** 1
-* **image_shape:** [None, None, 3]
-* **projection_filters:** 64
-* **prediction_heads:** [{'module': 'keras', 'class_name': 'Sequential', 'config': {'name': 'sequential', 'trainable': True, 'dtype': {'module': 'keras', 'class_name': 'DTypePolicy', 'config': {'name': 'float32'}, 'registered_name': None}, 'layers': [{'module': 'keras.layers', 'class_name': 'InputLayer', 'config': {'batch_shape': [None, None, None, 512], 'dtype': 'float32', 'sparse': False, 'name': 'input_layer_2'}, 'registered_name': None}, {'module': 'keras.layers', 'class_name': 'Conv2D', 'config': {'name': 'conv2d', 'trainable': True, 'dtype': {'module': 'keras', 'class_name': 'DTypePolicy', 'config': {'name': 'float32'}, 'registered_name': None}, 'filters': 1, 'kernel_size': [3, 3], 'strides': [1, 1], 'padding': 'same', 'data_format': 'channels_last', 'dilation_rate': [1, 1], 'groups': 1, 'activation': 'linear', 'use_bias': True, 'kernel_initializer': {'module': 'keras.initializers', 'class_name': 'GlorotUniform', 'config': {'seed': None}, 'registered_name': None}, 'bias_initializer': {'module': 'keras.initializers', 'class_name': 'Zeros', 'config': {}, 'registered_name': None}, 'kernel_regularizer': None, 'bias_regularizer': None, 'activity_regularizer': None, 'kernel_constraint': None, 'bias_constraint': None}, 'registered_name': None, 'build_config': {'input_shape': [None, None, None, 512]}}], 'build_input_shape': [None, None, None, 512]}, 'registered_name': None, 'build_config': {'input_shape': [None, None, None, 512]}}, {'module': 'keras', 'class_name': 'Sequential', 'config': {'name': 'sequential_1', 'trainable': True, 'dtype': {'module': 'keras', 'class_name': 'DTypePolicy', 'config': {'name': 'float32'}, 'registered_name': None}, 'layers': [{'module': 'keras.layers', 'class_name': 'InputLayer', 'config': {'batch_shape': [None, None, None, 512], 'dtype': 'float32', 'sparse': False, 'name': 'input_layer_3'}, 'registered_name': None}, {'module': 'keras.layers', 'class_name': 'Conv2D', 'config': {'name': 'conv2d_1', 'trainable': True, 'dtype': {'module': 'keras', 'class_name': 'DTypePolicy', 'config': {'name': 'float32'}, 'registered_name': None}, 'filters': 1, 'kernel_size': [3, 3], 'strides': [1, 1], 'padding': 'same', 'data_format': 'channels_last', 'dilation_rate': [1, 1], 'groups': 1, 'activation': 'linear', 'use_bias': True, 'kernel_initializer': {'module': 'keras.initializers', 'class_name': 'GlorotUniform', 'config': {'seed': None}, 'registered_name': None}, 'bias_initializer': {'module': 'keras.initializers', 'class_name': 'Zeros', 'config': {}, 'registered_name': None}, 'kernel_regularizer': None, 'bias_regularizer': None, 'activity_regularizer': None, 'kernel_constraint': None, 'bias_constraint': None}, 'registered_name': None, 'build_config': {'input_shape': [None, None, None, 512]}}, {'module': 'keras.layers', 'class_name': 'UpSampling2D', 'config': {'name': 'up_sampling2d', 'trainable': True, 'dtype': {'module': 'keras', 'class_name': 'DTypePolicy', 'config': {'name': 'float32'}, 'registered_name': None}, 'size': [2, 2], 'data_format': 'channels_last', 'interpolation': 'bilinear'}, 'registered_name': None, 'build_config': {'input_shape': [None, None, None, 1]}}], 'build_input_shape': [None, None, None, 512]}, 'registered_name': None, 'build_config': {'input_shape': [None, None, None, 512]}}, {'module': 'keras', 'class_name': 'Sequential', 'config': {'name': 'sequential_2', 'trainable': True, 'dtype': {'module': 'keras', 'class_name': 'DTypePolicy', 'config': {'name': 'float32'}, 'registered_name': None}, 'layers': [{'module': 'keras.layers', 'class_name': 'InputLayer', 'config': {'batch_shape': [None, None, None, 512], 'dtype': 'float32', 'sparse': False, 'name': 'input_layer_4'}, 'registered_name': None}, {'module': 'keras.layers', 'class_name': 'Conv2D', 'config': {'name': 'conv2d_2', 'trainable': True, 'dtype': {'module': 'keras', 'class_name': 'DTypePolicy', 'config': {'name': 'float32'}, 'registered_name': None}, 'filters': 1, 'kernel_size': [3, 3], 'strides': [1, 1], 'padding': 'same', 'data_format': 'channels_last', 'dilation_rate': [1, 1], 'groups': 1, 'activation': 'linear', 'use_bias': True, 'kernel_initializer': {'module': 'keras.initializers', 'class_name': 'GlorotUniform', 'config': {'seed': None}, 'registered_name': None}, 'bias_initializer': {'module': 'keras.initializers', 'class_name': 'Zeros', 'config': {}, 'registered_name': None}, 'kernel_regularizer': None, 'bias_regularizer': None, 'activity_regularizer': None, 'kernel_constraint': None, 'bias_constraint': None}, 'registered_name': None, 'build_config': {'input_shape': [None, None, None, 512]}}, {'module': 'keras.layers', 'class_name': 'UpSampling2D', 'config': {'name': 'up_sampling2d_1', 'trainable': True, 'dtype': {'module': 'keras', 'class_name': 'DTypePolicy', 'config': {'name': 'float32'}, 'registered_name': None}, 'size': [4, 4], 'data_format': 'channels_last', 'interpolation': 'bilinear'}, 'registered_name': None, 'build_config': {'input_shape': [None, None, None, 1]}}], 'build_input_shape': [None, None, None, 512]}, 'registered_name': None, 'build_config': {'input_shape': [None, None, None, 512]}}, {'module': 'keras', 'class_name': 'Sequential', 'config': {'name': 'sequential_3', 'trainable': True, 'dtype': {'module': 'keras', 'class_name': 'DTypePolicy', 'config': {'name': 'float32'}, 'registered_name': None}, 'layers': [{'module': 'keras.layers', 'class_name': 'InputLayer', 'config': {'batch_shape': [None, None, None, 512], 'dtype': 'float32', 'sparse': False, 'name': 'input_layer_5'}, 'registered_name': None}, {'module': 'keras.layers', 'class_name': 'Conv2D', 'config': {'name': 'conv2d_3', 'trainable': True, 'dtype': {'module': 'keras', 'class_name': 'DTypePolicy', 'config': {'name': 'float32'}, 'registered_name': None}, 'filters': 1, 'kernel_size': [3, 3], 'strides': [1, 1], 'padding': 'same', 'data_format': 'channels_last', 'dilation_rate': [1, 1], 'groups': 1, 'activation': 'linear', 'use_bias': True, 'kernel_initializer': {'module': 'keras.initializers', 'class_name': 'GlorotUniform', 'config': {'seed': None}, 'registered_name': None}, 'bias_initializer': {'module': 'keras.initializers', 'class_name': 'Zeros', 'config': {}, 'registered_name': None}, 'kernel_regularizer': None, 'bias_regularizer': None, 'activity_regularizer': None, 'kernel_constraint': None, 'bias_constraint': None}, 'registered_name': None, 'build_config': {'input_shape': [None, None, None, 512]}}, {'module': 'keras.layers', 'class_name': 'UpSampling2D', 'config': {'name': 'up_sampling2d_2', 'trainable': True, 'dtype': {'module': 'keras', 'class_name': 'DTypePolicy', 'config': {'name': 'float32'}, 'registered_name': None}, 'size': [8, 8], 'data_format': 'channels_last', 'interpolation': 'bilinear'}, 'registered_name': None, 'build_config': {'input_shape': [None, None, None, 1]}}], 'build_input_shape': [None, None, None, 512]}, 'registered_name': None, 'build_config': {'input_shape': [None, None, None, 512]}}, {'module': 'keras', 'class_name': 'Sequential', 'config': {'name': 'sequential_4', 'trainable': True, 'dtype': {'module': 'keras', 'class_name': 'DTypePolicy', 'config': {'name': 'float32'}, 'registered_name': None}, 'layers': [{'module': 'keras.layers', 'class_name': 'InputLayer', 'config': {'batch_shape': [None, None, None, 512], 'dtype': 'float32', 'sparse': False, 'name': 'input_layer_6'}, 'registered_name': None}, {'module': 'keras.layers', 'class_name': 'Conv2D', 'config': {'name': 'conv2d_4', 'trainable': True, 'dtype': {'module': 'keras', 'class_name': 'DTypePolicy', 'config': {'name': 'float32'}, 'registered_name': None}, 'filters': 1, 'kernel_size': [3, 3], 'strides': [1, 1], 'padding': 'same', 'data_format': 'channels_last', 'dilation_rate': [1, 1], 'groups': 1, 'activation': 'linear', 'use_bias': True, 'kernel_initializer': {'module': 'keras.initializers', 'class_name': 'GlorotUniform', 'config': {'seed': None}, 'registered_name': None}, 'bias_initializer': {'module': 'keras.initializers', 'class_name': 'Zeros', 'config': {}, 'registered_name': None}, 'kernel_regularizer': None, 'bias_regularizer': None, 'activity_regularizer': None, 'kernel_constraint': None, 'bias_constraint': None}, 'registered_name': None, 'build_config': {'input_shape': [None, None, None, 512]}}, {'module': 'keras.layers', 'class_name': 'UpSampling2D', 'config': {'name': 'up_sampling2d_3', 'trainable': True, 'dtype': {'module': 'keras', 'class_name': 'DTypePolicy', 'config': {'name': 'float32'}, 'registered_name': None}, 'size': [16, 16], 'data_format': 'channels_last', 'interpolation': 'bilinear'}, 'registered_name': None, 'build_config': {'input_shape': [None, None, None, 1]}}], 'build_input_shape': [None, None, None, 512]}, 'registered_name': None, 'build_config': {'input_shape': [None, None, None, 512]}}, {'module': 'keras', 'class_name': 'Sequential', 'config': {'name': 'sequential_5', 'trainable': True, 'dtype': {'module': 'keras', 'class_name': 'DTypePolicy', 'config': {'name': 'float32'}, 'registered_name': None}, 'layers': [{'module': 'keras.layers', 'class_name': 'InputLayer', 'config': {'batch_shape': [None, None, None, 512], 'dtype': 'float32', 'sparse': False, 'name': 'input_layer_7'}, 'registered_name': None}, {'module': 'keras.layers', 'class_name': 'Conv2D', 'config': {'name': 'conv2d_5', 'trainable': True, 'dtype': {'module': 'keras', 'class_name': 'DTypePolicy', 'config': {'name': 'float32'}, 'registered_name': None}, 'filters': 1, 'kernel_size': [3, 3], 'strides': [1, 1], 'padding': 'same', 'data_format': 'channels_last', 'dilation_rate': [1, 1], 'groups': 1, 'activation': 'linear', 'use_bias': True, 'kernel_initializer': {'module': 'keras.initializers', 'class_name': 'GlorotUniform', 'config': {'seed': None}, 'registered_name': None}, 'bias_initializer': {'module': 'keras.initializers', 'class_name': 'Zeros', 'config': {}, 'registered_name': None}, 'kernel_regularizer': None, 'bias_regularizer': None, 'activity_regularizer': None, 'kernel_constraint': None, 'bias_constraint': None}, 'registered_name': None, 'build_config': {'input_shape': [None, None, None, 512]}}, {'module': 'keras.layers', 'class_name': 'UpSampling2D', 'config': {'name': 'up_sampling2d_4', 'trainable': True, 'dtype': {'module': 'keras', 'class_name': 'DTypePolicy', 'config': {'name': 'float32'}, 'registered_name': None}, 'size': [32, 32], 'data_format': 'channels_last', 'interpolation': 'bilinear'}, 'registered_name': None, 'build_config': {'input_shape': [None, None, None, 1]}}], 'build_input_shape': [None, None, None, 512]}, 'registered_name': None, 'build_config': {'input_shape': [None, None, None, 512]}}, {'module': 'keras', 'class_name': 'Sequential', 'config': {'name': 'sequential_6', 'trainable': True, 'dtype': {'module': 'keras', 'class_name': 'DTypePolicy', 'config': {'name': 'float32'}, 'registered_name': None}, 'layers': [{'module': 'keras.layers', 'class_name': 'InputLayer', 'config': {'batch_shape': [None, None, None, 512], 'dtype': 'float32', 'sparse': False, 'name': 'input_layer_8'}, 'registered_name': None}, {'module': 'keras.layers', 'class_name': 'Conv2D', 'config': {'name': 'conv2d_6', 'trainable': True, 'dtype': {'module': 'keras', 'class_name': 'DTypePolicy', 'config': {'name': 'float32'}, 'registered_name': None}, 'filters': 1, 'kernel_size': [3, 3], 'strides': [1, 1], 'padding': 'same', 'data_format': 'channels_last', 'dilation_rate': [1, 1], 'groups': 1, 'activation': 'linear', 'use_bias': True, 'kernel_initializer': {'module': 'keras.initializers', 'class_name': 'GlorotUniform', 'config': {'seed': None}, 'registered_name': None}, 'bias_initializer': {'module': 'keras.initializers', 'class_name': 'Zeros', 'config': {}, 'registered_name': None}, 'kernel_regularizer': None, 'bias_regularizer': None, 'activity_regularizer': None, 'kernel_constraint': None, 'bias_constraint': None}, 'registered_name': None, 'build_config': {'input_shape': [None, None, None, 512]}}, {'module': 'keras.layers', 'class_name': 'UpSampling2D', 'config': {'name': 'up_sampling2d_5', 'trainable': True, 'dtype': {'module': 'keras', 'class_name': 'DTypePolicy', 'config': {'name': 'float32'}, 'registered_name': None}, 'size': [32, 32], 'data_format': 'channels_last', 'interpolation': 'bilinear'}, 'registered_name': None, 'build_config': {'input_shape': [None, None, None, 1]}}], 'build_input_shape': [None, None, None, 512]}, 'registered_name': None, 'build_config': {'input_shape': [None, None, None, 512]}}]
-* **refinement_head:** {'module': 'keras', 'class_name': 'Sequential', 'config': {'name': 'sequential_7', 'trainable': True, 'dtype': {'module': 'keras', 'class_name': 'DTypePolicy', 'config': {'name': 'float32'}, 'registered_name': None}, 'layers': [{'module': 'keras.layers', 'class_name': 'InputLayer', 'config': {'batch_shape': [None, None, None, 64], 'dtype': 'float32', 'sparse': False, 'name': 'input_layer_9'}, 'registered_name': None}, {'module': 'keras.layers', 'class_name': 'Conv2D', 'config': {'name': 'conv2d_7', 'trainable': True, 'dtype': {'module': 'keras', 'class_name': 'DTypePolicy', 'config': {'name': 'float32'}, 'registered_name': None}, 'filters': 1, 'kernel_size': [3, 3], 'strides': [1, 1], 'padding': 'same', 'data_format': 'channels_last', 'dilation_rate': [1, 1], 'groups': 1, 'activation': 'linear', 'use_bias': True, 'kernel_initializer': {'module': 'keras.initializers', 'class_name': 'GlorotUniform', 'config': {'seed': None}, 'registered_name': None}, 'bias_initializer': {'module': 'keras.initializers', 'class_name': 'Zeros', 'config': {}, 'registered_name': None}, 'kernel_regularizer': None, 'bias_regularizer': None, 'activity_regularizer': None, 'kernel_constraint': None, 'bias_constraint': None}, 'registered_name': None, 'build_config': {'input_shape': [None, None, None, 64]}}], 'build_input_shape': [None, None, None, 64]}, 'registered_name': None}
-
-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.
+### Model Overview
+# Model Summary
+
+Deep semantic segmentation algorithms have improved a lot recently, but still fails to correctly predict pixels around object boundaries.We implement Boundary-Aware Segmentation Network (BASNet), using two stage predict and refine architecture, and a hybrid loss it can predict highly accurate boundaries and fine structures for image segmentation. This model is supported in both KerasCV and KerasHub. KerasCV will no longer be actively developed, so please try to use KerasHub. Weights are released under the [MIT License](https://www.mit.edu/~amini/LICENSE.md) . Keras model code is released under the [Apache 2 License](https://github.com/keras-team/keras-hub/blob/master/LICENSE).
+
+## Links
+
+* [BASNet Quickstart Notebook](https://www.kaggle.com/code/laxmareddypatlolla/basnet-quickstart-notebook/notebook)
+* [BASNet API Documentation](coming soon)
+* [BASNet Model Card](https://arxiv.org/abs/2101.04704)
+* [KerasHub Beginner Guide](https://keras.io/guides/keras_hub/getting_started/)
+* [KerasHub Model Publishing Guide](https://keras.io/guides/keras_hub/upload/)
+
+## Installation
+
+Keras and KerasHub can be installed with:
+
+```
+pip install -U -q keras-hub
+pip install -U -q keras
+```
+
+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                                                                                                  |
+|---------------------------------------|------------|--------------------------------------------------------------------------------------------------------------|
+| basnet_duts | 108.89M  | BASNet model with a 34-layer ResNet backbone, pre-trained on the DUTS image dataset at a 288x288 resolution. |
+