Closed albertxavier001 closed 8 years ago
I download http://dl.caffe.berkeleyvision.org/bvlc_reference_caffenet.caffemodel and it can be parsed. But I cannot train since my GPU memory is too small (3GB). I set bach_size to 1 but still out of memory.
You should use this file and ensure you reference it in the correct directory http://www.robots.ox.ac.uk/~vgg/software/very_deep/caffe/VGG_ILSVRC_16_layers.caffemodel
Thanks. I finally found my caffemodel was imcomplete.
Hi, I download weights of VGG and use the 3rd command
./SegNet/caffe-segnet/build/tools/caffe train -gpu 0 -solver /SegNet/Models/segnet_solver.prototxt -weights /SegNet/Models/VGG_ILSVRC_16_layers.caffemodel # This will begin training SegNet on GPU 0 with a pretrained encoder
, but I got this error: