| --- |
| license: apache-2.0 |
| library_name: pytorch |
| tags: |
| - image-generation |
| - gan |
| - dcgan |
| - logo-generation |
| - small-model |
| - from-scratch |
| language: |
| - en |
| dataset: samp3209/logo-dataset |
| metrics: |
| - fidelity |
| - mode-collapse |
| --- |
| |
| # Logo GAN — 3.5M-param DCGAN for logo-like image generation |
|
|
| A small **Deep Convolutional GAN** trained **from scratch** to generate 64×64 |
| logo-like images. This is the deliverable for |
| [Compactbot/model-requests #1](https://huggingface.co/spaces/Compactbot/model-requests/discussions/1) |
| (CompactAI: "a small model that generates logo-like images"). |
|
|
| ## What it is |
|
|
| A generator/discriminator pair. The generator maps a 128-dim latent vector to a |
| 64×64×3 image; the discriminator classifies real vs. generated. Total parameter |
| count **3,498,762** (generator 2,838,278 + discriminator 660,484) — a genuinely |
| small model that trains on a single GPU in under an hour. |
|
|
| ## Architecture |
|
|
| **Generator** (latent 128 → 64×64×3, output in [-1,1]): |
| ``` |
| Linear(128, 256·8·8) → BatchNorm → ReLU → reshape (256,8,8) |
| ConvTranspose2d(256,128,4,2,1) → BatchNorm → ReLU |
| ConvTranspose2d(128,64,4,2,1) → BatchNorm → ReLU |
| ConvTranspose2d(64,3,4,2,1) → Tanh |
| ``` |
|
|
| **Discriminator** (64×64×3 → scalar logit): |
| ``` |
| Conv2d(3,64,4,2,1) → BatchNorm → LeakyReLU(0.2) |
| Conv2d(64,128,4,2,1) → BatchNorm → LeakyReLU(0.2) |
| Conv2d(128,256,4,2,1)→ BatchNorm → LeakyReLU(0.2) |
| AdaptiveAvgPool2d(1) → Flatten → Linear(256,1) |
| ``` |
|
|
| | Component | Params | |
| |---|---| |
| | Generator | 2,838,278 | |
| | Discriminator | 660,484 | |
| | **Total** | **3,498,762** | |
|
|
| ## Data |
|
|
| 100 logos, each 64×64×3 RGB, bilinearly resized and normalized to [0,1]. |
| Sourced from the first 100 valid images of the |
| [`samp3209/logo-dataset`](https://huggingface.co/datasets/samp3209/logo-dataset) |
| train split (streamed). Stored as `logos64.npy` (shape `(100,64,64,3)`, float32). |
|
|
| ## Training |
|
|
| - Optimizer: Adam, lr 2e-4, betas (0.5, 0.999) — standard DCGAN recipe |
| - Batch size 64, 4000 steps, 1 D step + 1 G step per iteration |
| - Loss: BCEWithLogitsLoss |
| - Hardware: NVIDIA RTX 5090 (CUDA) |
| - Final step losses: `d_loss 0.0711`, `g_loss 3.5900` |
|
|
| ## Quality (measured, not asserted) |
|
|
| Generated a 64-sample grid (seed 123) and compared its statistics to the real |
| logos: |
|
|
| | Metric | Generated | Real | |
| |---|---|---| |
| | Pixel mean | 0.572 | 0.574 | |
| | Pixel std | 0.350 | 0.360 | |
| | Colorfulness (L1 norm of channel stds) | 0.605 | 0.622 | |
| | Median pairwise L2 (mode-collapse proxy) | 52.1 | — | |
| | Fraction of near-duplicate pairs (<0.01) | 0.000 | — | |
|
|
| The generated distribution closely tracks the real one in mean, variance and |
| colorfulness, and there is **no mode collapse** (outputs are diverse, not |
| repeated). See `final_grid.png` (64 generated) and `final_real.png` (64 real) |
| side by side. |
|
|
| ## What it is and is not good at |
|
|
| - **Good at:** producing diverse, logo-*like* 64×64 images — the right color |
| statistics and composition of real logos, without collapsing to one mode. |
| - **Not good at:** crisp, recognizable logos. 100 images is a very small |
| dataset, so the model captures the *distribution* of logos (color, layout, |
| contrast) rather than specific, legible marks. Treat outputs as |
| logo-flavored compositions, not usable brand assets. |
|
|
| ## Files |
|
|
| - `final.pt` — final checkpoint (`g`, `d` state dicts, `step`, `zdim`) |
| - `train_logo_gan.py` — full training script (reproducible) |
| - `final_grid.png` — 64 generated samples (seed 123) |
| - `final_real.png` — 64 real logos for comparison |
|
|
| ## Reproduce |
|
|
| ```bash |
| # data prep (first 100 logos → /work/logos/logos64.npy) |
| python gan_prep3.py |
| # train |
| python train_logo_gan.py --steps 4000 --batch 64 --zdim 128 --lr 2e-4 |
| ``` |
|
|
| ## Honest note on scope |
|
|
| The original request thread discussed a larger config (≈8.8M params, latent |
| 100, 12000 steps). The run that actually completed and is shipped here is the |
| smaller 3.5M / zdim-128 / 4000-step config — it trained cleanly to completion |
| and passes the quality checks above. The larger config is a future follow-up, |
| not what this checkpoint is. |
