README.md

metadata

tags:
  - unet
  - pix2pix
  - pytorch
library_name: pytorch

Pix2Pix UNet Model

Model Description

Custom UNet model for Pix2Pix image translation.

• Image Size: 1024
• Model Type: Big (1024)

Usage

import torch
from small_256_model import UNet as small_UNet
from big_1024_model import UNet as big_UNet

# Load the model
checkpoint = torch.load('model_weights.pth')
model = big_UNet() if checkpoint['model_config']['big'] else small_UNet()
model.load_state_dict(checkpoint['model_state_dict'])
model.eval()

Model Architecture

UNet(
  (encoder): Sequential(
    (0): Conv2d(3, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
    (1): ReLU(inplace=True)
    (2): Conv2d(64, 128, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
    (3): ReLU(inplace=True)
    (4): Conv2d(128, 256, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
    (5): ReLU(inplace=True)
    (6): Conv2d(256, 512, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
    (7): ReLU(inplace=True)
    (8): Conv2d(512, 1024, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
    (9): ReLU(inplace=True)
  )
  (decoder): Sequential(
    (0): ConvTranspose2d(1024, 512, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
    (1): ReLU(inplace=True)
    (2): ConvTranspose2d(512, 256, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
    (3): ReLU(inplace=True)
    (4): ConvTranspose2d(256, 128, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
    (5): ReLU(inplace=True)
    (6): ConvTranspose2d(128, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
    (7): ReLU(inplace=True)
    (8): ConvTranspose2d(64, 3, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
    (9): Tanh()
  )
)