DenseNet

DenseNet copied to clipboard

DenseNet on ImageNet

20

I've just read your paper which is really interesting. I was wondering whether you tried learning a DenseNet version on ImageNet ? Thank you

AlexandreBriot

Question on channel before entering the first block

2

Hello, I want to reproduce the results on densenet-cifar10/cifar100, but got lower accuracy on tensorflow implementation. There is one question on model architecture, In the paper Implementation Details part: "Before...

Sirius083

I take the liberty to bother you. I want to ask you a question about image classification, but images are not images in the usual sense. The experiment is to...

ewwll

Hi, What's the receptive field of `densenet121` and `densenet161`? The [Distill blog post](https://distill.pub/2019/computing-receptive-fields/) doesn't mention it. Is it more than that of resnet101 (RF: 1027)?

kHarshit

Hi! Thank you for publishing this. I'm following pytorch implementation of DenseNet, specifically I'm using densenet161 for extracting features from images. I'm wondering, in your implementation here, why after the...

zlenyk

Jason-Cooke

Question on impede information flow

1

Hi, Thanks for your great work In section 3 in paper "However, the identity function and the output of H_l are combined by summation, which may impede the information flow"...

Sirius083

cifar validation loss decrease than increase after learning rate change

4

Hello, I have one question when training denseNet: the validation loss get a sharp decrease than increase after learning rate changed from 0.1 to 0.01 I trained the densenet (depth_40_k_12)...

Sirius083

validation top1 error is odd

1

Hi I trained a densenet according the paper on cifar10.The top1 error of test set is odd. The result is saved in this file. [net-train.pdf](https://github.com/liuzhuang13/DenseNet/files/1618831/net-train.pdf) How can i make the...

Itsanewday

Why is composite function BN-ReLU-Conv3x3 ?

1

Hello, The composite function of other models is Conv3x3-BN-ReLU. Why is DenseNet special? Looking forward to your answer. Thanks

RDShi