Downloads · 30 days
0
mnist-cgan
Shushunya/mnist-cgan
mnist-cgan is a machine learning model from Shushunya. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
Model Type: Conditional Generative Adversarial Network (cGAN) - Generator Only Task: Conditional Image Generation Dataset: MNIST (Grayscale handwritten digits, 0-9) Image Size: 32x32 pixels (upscaled from original 28x…
Access
Public
Updated Mar 27, 2026
Parameters
822K
11 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pth3.3 MB · 50%
At a glance
- License
- mit
- Access
- Public
- Created
- Mar 24, 2026
- Updated
- Mar 27, 2026
- SHA
- a08aaa5d
Model card
From the Hugging Face model README
MNIST Conditional DCGAN Generator
- Model Type: Conditional Generative Adversarial Network (cGAN) - Generator Only
- Task: Conditional Image Generation
- Dataset: MNIST (Grayscale handwritten digits, 0-9)
- Image Size: 32x32 pixels (upscaled from original 28x28)
- Framework: PyTorch
Architecture
The model is a Deep Convolutional Generator (DCGAN) modified for conditional generation.
- Inputs: A 100-dimensional random latent vector ($z$) and a class label (integer 0-9).
- Conditioning: The class label is passed through an
nn.Embeddinglayer (10 classes $ ightarrow$ 10 dimensions) and concatenated with the latent noise vector. - Blocks: 4 layers of
nn.ConvTranspose2dwithBatchNorm2dandReLUactivations. - Output: A
Tanhactivation producing a 1x32x32 tensor with values normalized between [-1, 1].
Limitations & Biases
- Resolution: The output is strictly limited to 32x32 resolution.
- Domain: The model can only generate MNIST-style digits. It cannot generalize to alphabets, symbols, or real-world photographs.
- Artifacts: Standard Transposed Convolution artifacts (checkerboard patterns) may occasionally be visible upon close inspection.
- License
- mit
- Created
- Mar 24, 2026
- Updated
- Mar 27, 2026