深度学习笔记56_GAN也很简单_GAN模型的训练(4)
2023-03-16 来源:你乐谷
img.save(os.path.join(save_dir,
generated_frog str(step) .jpg))
# 保存一张真实图像,用于对比
img = image.array_to_img(real_images[0] * 255., scale=False)
img.save(os.path.join(save_dir,
real_frog str(step) .jpg))
discriminator loss: 0.66969573
adversarial loss: 0.6532642
discriminator loss: 0.5475507
adversarial loss: 1.3109558
discriminator loss: 0.6699523
adversarial loss: 0.7478587
discriminator loss: 0.70896524
adversarial loss: 0.8421527
discriminator loss: 0.9083044
adversarial loss: 1.5422354
discriminator loss: 0.65306413
adversarial loss: 0.847822
最后自动生成的图片案例如下:个人觉得效果不是很好,应该还有优化的空间
分享关于人工智能,机器学习,深度学习以及计算机视觉的好文章,同时自己对于这个领域学习心得笔记。想要一起深入学习人工智能的小伙伴一起结伴学习吧!扫码上车!
generated_frog str(step) .jpg))
# 保存一张真实图像,用于对比
img = image.array_to_img(real_images[0] * 255., scale=False)
img.save(os.path.join(save_dir,
real_frog str(step) .jpg))
discriminator loss: 0.66969573
adversarial loss: 0.6532642
discriminator loss: 0.5475507
adversarial loss: 1.3109558
discriminator loss: 0.6699523
adversarial loss: 0.7478587
discriminator loss: 0.70896524
adversarial loss: 0.8421527
discriminator loss: 0.9083044
adversarial loss: 1.5422354
discriminator loss: 0.65306413
adversarial loss: 0.847822
最后自动生成的图片案例如下:个人觉得效果不是很好,应该还有优化的空间
分享关于人工智能,机器学习,深度学习以及计算机视觉的好文章,同时自己对于这个领域学习心得笔记。想要一起深入学习人工智能的小伙伴一起结伴学习吧!扫码上车!