I tried to reproduce the accuracy values (top1 and top5) for the reference ImageNet model (CaffeNet). However, I only get a top5 accuracy of ~67% which is lower than the reported 80% here.
Steps to reproduce
I used the model definition and weights from GitHub. I evaluated the model using this simple script. I used the pre-processing (transforming from RGB to BGR, image resizing, center cropping, and ImageNet mean subtraction) indicated in the ImageNet examples of Caffe.
I uploaded the predicted classes and the ground-truth labels as a python list here, in case someone wants to take a look at them,
Tried solutions
I redownloaded the network weights and verified the preprocessing.
Issue summary
I tried to reproduce the accuracy values (top1 and top5) for the reference ImageNet model (CaffeNet). However, I only get a top5 accuracy of ~67% which is lower than the reported 80% here.
Steps to reproduce
I used the model definition and weights from GitHub. I evaluated the model using this simple script. I used the pre-processing (transforming from RGB to BGR, image resizing, center cropping, and ImageNet mean subtraction) indicated in the ImageNet examples of Caffe.
I uploaded the predicted classes and the ground-truth labels as a python list here, in case someone wants to take a look at them,
Tried solutions
I redownloaded the network weights and verified the preprocessing.
System configuration
I used the latest gpu docker container.
Issue checklist