diff --git a/BE2_GAN_and_Diffusion_colab_3.ipynb b/BE2_GAN_and_Diffusion_colab_3.ipynb index f4a2eee10a00c604cc4d7c86196f1a685893b2c3..6d75e774e424d1373e899b2cb86aab3c1eb3c7a8 100644 --- a/BE2_GAN_and_Diffusion_colab_3.ipynb +++ b/BE2_GAN_and_Diffusion_colab_3.ipynb @@ -44738,16 +44738,11 @@ "source": [ "<font color='red'>Question</font> \n", "What are the differences between the UNet used for the cGAN generator and the one defined above ? \n", - "Indicate the differences in the architecture by analyzing both models \\_\\_str\\_\\_." + "Indicate the differences in the architecture by analyzing both models \\_\\_str\\_\\_.\n", + "\n", + "The UNet2DModel uses a 1 channel input and the UNet from before a 3 channels input. Furthermore UNet2dModel uses a conditioning on time steps as it is necessary for diffusion. Also it uses SiLu activations instead of LeakyRelu/Relu/tanh. On top of that UNet2dModel uses GroupNorm and the other model uses BatchNorm2d " ] }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - }, { "cell_type": "markdown", "metadata": {