cnn-models
cnn-models copied to clipboard
cvjena
ImageNet pre-trained models with batch normalization for the Caffe framework
Hi， Thanks for your sharing！ But I cannot find the VGG16 pretrained models with BN. I'm very appreciated it if you release it.
When I load the [ResNet10 model](https://github.com/cvjena/cnn-models/blob/master/ResNet_preact/ResNet10_cvgj/deploy.prototxt) and the associated weights ([from here](https://drive.google.com/file/d/0B6VgjAr4t_oTdUhaclljRWlPSVU/view?usp=sharing)) into [DIGITS](https://github.com/NVIDIA/DIGITS) for training on a custom image dataset I get the following output: ``` ERROR: Check failed:...
Using the link provided [here](https://github.com/cvjena/cnn-models/blob/master/ResNet_preact/ResNet10_cvgj/model_download_link.txt) I was unable to download the pre-trained weights for the ResNet10 model: ``` $ wget https://upload.uni-jena.de/data/58493041de6f79.63214979/resnet10_cvgj_iter_320000.caffemodel --2019-09-03 18:36:32-- https://upload.uni-jena.de/data/58493041de6f79.63214979/resnet10_cvgj_iter_320000.caffemodel Resolving upload.uni-jena.de (upload.uni-jena.de)... 141.35.105.30, 2001:638:1558:2369:1:5ee:bad:c0de Connecting...
Hi, I tried to finetune with your model. It works well on single gpu but not on multi gpus. Is it a inhere limitation or there is something I need...
Hi, since the pretrained model is trained with ImageNet, Is it ok to release it as a commercial model without the permission from ImageNet?
On ImageNet, I only get a top-5 accuracy of 83.86%. Any idea what's wrong?
Hi thanks for your sharing, I running VGG19_BN caffemodel in py-faster-rcnn , the input size is 550, the wierd thing is GPU memory reaching up to 10G. VGG19_BN need more...
Hi there, Thanks for sharing the pre-trained models. I am learning the ResNets50 and have a question about the architecture. It sames that there are quite few places different with...
