Conditional Image Generation with PixelCNN Decoders
Authors: Aaron van den Oord, Nal Kalchbrenner, Lasse Espeholt, koray kavukcuoglu, Oriol Vinyals, Alex Graves
NeurIPS 2016 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Table 1 compares Gated Pixel CNN with published results on the CIFAR-10 dataset. These architectures were all optimized for the best possible validation score, meaning that models that get a lower score actually generalize better. Gated Pixel CNN outperforms the Pixel CNN by 0.11 bits/dim, which has a very significant effect on the visual quality of the samples produced, and which is close to the performance of Pixel RNN. |
| Researcher Affiliation | Industry | Aäron van den Oord Google Deep Mind EMAIL Nal Kalchbrenner Google Deep Mind EMAIL Oriol Vinyals Google Deep Mind EMAIL Lasse Espeholt Google Deep Mind EMAIL Alex Graves Google Deep Mind EMAIL Koray Kavukcuoglu Google Deep Mind EMAIL |
| Pseudocode | No | No pseudocode or clearly labeled algorithm block was found in the paper. |
| Open Source Code | No | The paper does not provide an explicit statement about open-sourcing the code for the described methodology or a link to a code repository. |
| Open Datasets | Yes | Table 1 compares Gated Pixel CNN with published results on the CIFAR-10 dataset. |
| Dataset Splits | No | The paper reports 'Test' and '(Train)' performance in tables, but does not explicitly provide specific percentages, sample counts, or detailed methodology for training/validation/test splits, beyond implying the existence of these sets. |
| Hardware Specification | No | The paper mentions '60 hours using 32 GPUs' for training, but does not specify the exact model or type of GPUs, CPU, memory, or other detailed hardware specifications. |
| Software Dependencies | No | The paper mentions 'Tensor Flow [1]' but does not provide a specific version number for it or other software dependencies. |
| Experiment Setup | Yes | For the results in Table 2 we trained a larger model with 20 layers (Figure 2), each having 384 hidden units and filter size of 5 5. We used 200K synchronous updates over 32 GPUs in Tensor Flow [1] using a total batch size of 128. |