markrodrigo/fire-fuel-vegetation-image-segmentation-1.0

Model Information - fire火-fuel薪-vegetation植被-image-segmentation-1.0

Red Green Blue (RGB) binary segmentation of particular vegetation in leaf. Shrub or tree applications.
植被叶片的红、绿、蓝二元分割。
Likely medical applications as the model was originally designed for.
该模型最初很可能是为医疗应用而设计的。
Originally trained to specific species. Semantically segmented for accuracy.
最初针对特定物种进行训练。为了提高准确性，进行了语义分割。
Keras / Tensorflow .h5 supervised model.
Opportunities are to transfer learn or further fine-tune with LoRA, etc.
使用 LoRA 进行迁移学习或进一步微调的机会
Data sources are proprietary via hand drawn masked samples.
数据源是通过手绘的掩蔽样本专有的。
Some extrapolation of source data to synthetic data.
将一些源数据推断为合成数据。
Novel applications – require specific vegetation imagery.
新颖的应用——需要特定的植被图像。
Other applications - Vegetation 2D area calculations. Wildfire / fire fuel. Land Cover change. Medical. Line clearing. Noxious weeds. Environmental assessments. Camouflage object detection.
其他应用 - 植被 2D 面积计算。野火/火灾燃料。土地覆盖变化。医疗。线路清理。有害杂草。环境评估。伪装物体检测。

Forest Fire Fuel

Model developer: Mark Rodrigo

Associated code: https://github.com/mprodrigo - coming soon

Model Architecture: Modified U-Net

Model Input / Output Overview:

Input: 256, 256, 3
Output: 256, 256, 1

Further Reference

TODO

Example Code

Keras
import keras model = keras.models.load_model('../model/image-segmentation-vegetation-1.0.keras')
model.summary()
or
import keras loaded_model = keras.models.load_model('/home/phantom/Projects/agverde/data/product/Agverde/z1/model/image-segmentation-vegetation-1.0.h5')
loaded_model.summary()

TensorFlow
https://www.tensorflow.org/tutorials/keras/save_and_load

Evaluation / Accuracy of Target Vegetation

Rand Index: .92 - .96 (geographic latitude and regional vegetation color variations)

Training and Validation data

3840 256x256 RGB images and corresponding 256x256 binary mask images
~ 1/3 allocated to validation
Separate test sets by latitude and region. Target species has regional color variations.

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 1e-04
train_batch_size: 8
eval_batch_size: 3
distributed_type: multi-GPU
num_devices: 2
batch steps: 60
eval steps: 9
optimizer: Adam
num_epochs: 8

Training results

| Training Loss | Epoch  | Training Accuracy |
|:-------------:|:------:|:-----------------:|
| 0.4718        |   1    | 0.8227            |
| 0.3869        |   2    | 0.8328            |
| 0.3770        |   3    | 0.8403            |
| 0.2557        |   4    | 0.8562            |
| 0.2432        |   5    | 0.8587            |
| 0.0856        |   6    | 0.9557            |
| 0.0338        |   7    | 0.9870            |
| 0.0303        |   8    | 0.9891            |

Framework versions

Keras 3.6.0
Tensorflow 2.16.2