Instructions to use otainfo/esp32-process-success-predictor with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use otainfo/esp32-process-success-predictor with Keras:
# !pip install -U keras tensorflow huggingface_hub # Keras needs TensorFlow installed to read "hf://" paths, so the tensorflow backend is selected here; # "jax" and "torch" also work for computation once TensorFlow is installed. import os os.environ["KERAS_BACKEND"] = "tensorflow" import keras model = keras.saving.load_model("hf://otainfo/esp32-process-success-predictor") - Notebooks
- Google Colab
- Kaggle
Help user onboard using sample code
Browse files
README.md
CHANGED
|
@@ -1,3 +1,48 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
---
|
| 4 |
+
🤖 esp32-process-success-predictor
|
| 5 |
+
Tagline: Lightweight neural network for predicting process success on ESP32-based systems.
|
| 6 |
+
|
| 7 |
+
🧠 Model Summary
|
| 8 |
+
This model is designed for microcontrollers like the ESP32. It predicts the likelihood of success or failure for embedded tasks or processes based on sensor input or operational parameters.
|
| 9 |
+
|
| 10 |
+
Framework: TensorFlow Lite
|
| 11 |
+
|
| 12 |
+
Optimized for: Embedded deployment (ESP32, low-memory environments)
|
| 13 |
+
|
| 14 |
+
Input: Vector of process/task-specific features (e.g., Heap values, Default cpu temperature, Wifi attributes etc.)
|
| 15 |
+
|
| 16 |
+
Output: Score based prediction
|
| 17 |
+
|
| 18 |
+
🏗️ Intended Use
|
| 19 |
+
Predict process outcomes in automation, robotics, or real-time control systems.
|
| 20 |
+
|
| 21 |
+
Deploy in constrained environments (under 1.2MB flash, < 300KB RAM).
|
| 22 |
+
|
| 23 |
+
Integrate with OTA update strategies and on-device decision-making.
|
| 24 |
+
|
| 25 |
+
🚀 How to Use
|
| 26 |
+
Checkout the flowwoing link:
|
| 27 |
+
|
| 28 |
+
https://github.com/OTAINFO/Downloads/tree/main/predictor_models/ESP-IDF/esp32
|
| 29 |
+
Note: Variable name in esp32-process-success-predictor-model.cc may differ on the sample code.
|
| 30 |
+
|
| 31 |
+
📦 Files Included
|
| 32 |
+
esp32-process-success-predictor.keras: Full Keras model
|
| 33 |
+
|
| 34 |
+
esp32-process-success-predictor.tflite: TensorFlow Lite version for microcontroller inference
|
| 35 |
+
|
| 36 |
+
esp32-process-success-predictor-model.cc: This can be directly used in ESP-IDF environment.
|
| 37 |
+
|
| 38 |
+
🧪 Training Info
|
| 39 |
+
Epochs: 5
|
| 40 |
+
|
| 41 |
+
Accuracy: ~98.9%
|
| 42 |
+
|
| 43 |
+
Loss: ~0.025 on validation set
|
| 44 |
+
|
| 45 |
+
Dataset: Synthetic data set based on 3 years of data internally generated.
|
| 46 |
+
|
| 47 |
+
📝 License
|
| 48 |
+
Apache 2.0
|