We lifted 6 functions out of this paper's own repositories and ran 3 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| ShengjiaZhao/Generalized-PixelVAE | canonical | 3 of 6 |
| Function | Status | Where it lives |
|---|---|---|
| concat_elu | Ran | ShengjiaZhao/Generalized-PixelVAE/pixel_cnn_pp/nn.py code served (permissive licence) · get_code("c2617c0e25b5f26a") |
| int_shape | Ran | ShengjiaZhao/Generalized-PixelVAE/pixel_cnn_pp/nn.py code served (permissive licence) · get_code("3ba6aec873833b39") |
| lrelu | Ran | ShengjiaZhao/Generalized-PixelVAE/pixel_cnn_pp/encoder.py code served (permissive licence) · get_code("4661a1e5a82037d4") |
| fc_lrelu | Not yet run | ShengjiaZhao/Generalized-PixelVAE/pixel_cnn_pp/encoder.py code served (permissive licence) · get_code("b0dceb387145ee42") |
| log_sum_exp | Not yet run | ShengjiaZhao/Generalized-PixelVAE/pixel_cnn_pp/nn.py code served (permissive licence) · get_code("ad066f5de5f84073") |
| mlp_discriminator | Not yet run | ShengjiaZhao/Generalized-PixelVAE/pixel_cnn_pp/encoder.py code served (permissive licence) · get_code("a66320a04203e090") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
We propose a new family of optimization criteria for variational auto-encoding models, generalizing the standard evidence lower bound. We provide conditions under which they recover the data distribution and learn latent features, and formally show that common issues such as blurry samples and uninformative latent features arise when these conditions are not met. Based on these new insights, we propose a new sequential VAE model that can generate sharp samples on the LSUN image dataset based on pixel-wise reconstruction loss, and propose an optimization criterion that encourages unsupervised learning of informative latent features.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1702.08658")
get_code_for_paper("1702.08658")
have("1702.08658")
Connect an agent — have() is free.