| --- |
| license: mit |
| tags: [esp32-c3, e-paper, gan, flowers, int8, embedded] |
| pipeline_tag: unconditional-image-generation |
| --- |
| |
| # Flower GAN on an ePaper badge |
|
|
| A **3.42-million-parameter INT8 flower generator** running entirely on the |
| Espruino ESP32-C3 ePaper Badge. Images generate in about **48 seconds**, with the next generation |
| overlapping the four-color screen refresh. |
|
|
| The model generates 320 × 176 RGB. The original 320 × 172 crop is enlarged to |
| 800 × 430 and dithered to black, white, yellow, and red. Small borders show timing, |
| free RAM, image number, and seed. Hardware: ESP32-C3, 4 MiB flash, 800 × 480 panel, |
| maker's rev 1.2 pin mapping. Other ESP32 boards need their own port. |
|
|
| ## Easiest flash: your browser |
|
|
| **This replaces the original app and saved badge data.** Back up first if you want |
| to preserve your photo, contacts, and settings; see [backup instructions](BACKUP.md). |
|
|
| 1. Download [firmware.bin](firmware.bin?download=true). It includes the application |
| and all model weights. |
| 2. Connect a USB data cable. In the original summit app, hold the rear **SHARE** |
| button until the LEDs stay solid blue, then release. Close other serial apps. |
| 3. In desktop Chrome or Edge, open [Espressif's ESP Tool](https://espressif.github.io/esptool-js/). |
| Click **Connect** in the Program section and select the badge's USB serial/JTAG |
| device. It should identify as **ESP32-C3**; leave WebUSB (CH340) unchecked. |
| 4. Choose `firmware.bin` in one file row at **Flash Address `0x0`**. Set flash mode, |
| frequency, and size to **keep**. Leave Erase all unchecked and click **Program**. |
| 5. Wait for verification and automatic reset. The first flower appears in about |
| one minute; subsequent images advance automatically. Both buttons are unassigned. |
|
|
| No custom installer scripts or build tools are required. For terminal users: |
|
|
| ```sh |
| python -m pip install esptool==5.6.0 |
| python -m esptool --chip esp32c3 --port PORT --baud 460800 --before usb-reset --after hard-reset write-flash 0x0 firmware.bin |
| ``` |
|
|
| Replace `PORT` with your device's port. If it does not appear, check the cable, |
| solid-blue mode, and whether another app has the port open. |
|
|
| ## Code, weights, and data |
|
|
| | Path | Contents | |
| | --- | --- | |
| | [source/](source/) | Native C inference, display driver, and ESP-IDF project | |
| | [training/](training/) | Original PyTorch architecture, training, data preparation, and export code | |
| | [data/](data/) | Exact INT8 weights, tensor layout, original model export, and reference tensors | |
| | [data/dataset.json](data/dataset.json) | Training dataset source, pinned revision, and preprocessing metadata | |
| | [BUILD.md](BUILD.md) | Build versions and commands | |
| | [release.json](release.json) / [SHA256SUMS](SHA256SUMS) | Flash layout, versions, and file hashes | |
|
|
| Training used all **8,189 Oxford Flowers102 images**, from the |
| [pufanyi/flowers102 mirror](https://huggingface.co/datasets/pufanyi/flowers102), |
| revision `b61e48cb66625272ca3bf36442062362587fa9bb`. Images are not mirrored here; |
| the source and preparation code are included. The original floating-point training |
| checkpoint was not in the supplied bundle; the original INT8 export is included. |
|
|
| Original project code and trained weights are released under [MIT](LICENSE). |
| Third-party code and dataset terms remain separate; see [NOTICE.md](NOTICE.md). |
| The release contains no private badge data. The inference implementation matched |
| its reference byte for byte across seven seeds and ran successfully on the badge. |
|
|
