Pablo Ruiz

Hi @bamos, According to the paper, the number of channels is twice the grow_rate only for the BC type DenseNets. Since you are giving room to not have bottleneck, we...

Hi Dmitry, I have one question. Why using ((0.5, 0.5, 0.5), (0.5, 0.5, 0.5)) for the Normalize in the SVHN? That values are the ones you want your input to...

What is the minimum GPU memory required? Still breaks for me in a single GPU

1

**Amazon p3.2xlarge: 1 GPUs - Tesla V100 -- GPU Memory: 16GB -- Batch Size = 64** If efficient = False: Error: RuntimeError: CUDA out of memory. Tried to allocate 1024.00...

Hi, why are you using Conv2d module? The author in the paper uses to 1D convolutions. Thanks, Pablo

This architecture is not following the paper for CIFAR-10

3

Hi, In the ResNet publication they propose a different architecture where it comes to CIFAR-10 right? > The plain/residual architectures follow the form in Fig. 3 (middle/right). The network inputs...

What is the point of tracking the loss and accuracy iterating over the test set? If your model is already trained, why don't you simple compute the accuracy over the...

The ResNets from the authors on the original paper change the sizes when applied to CIFAR10. It just don't match the dimensions you specified here: ResNets for CIFAR10 are 2+6n...

Dataset

1

Hola Hugo, en primer lugar felicitarte, he leído tu TFG y es increíble. Espero que te pusieran la MH que te mereces. Con respecto al dataset, ¿dónde puedes descargar el...