marifnst

Hi @tim9510019 you can follow this solution [https://github.com/rbgirshick/py-faster-rcnn/issues/237](url) From my experience, i only get problem Faster R CNN in TX1 using VGG16 net (memory problem i thought). thanks

@Austriker thank you for your information. i will visit the thread. my code running well and i intend to compare learning result in GPU mode. because i intend to train...

thanks @yuanyuanli85 any sample to convert compressed model to fp32 ? i'm still search how to implement your solution. thanks

hi @yuanyuanli85 after search and try many time, i can compress my caffemodel. this is link of my sample code [SampleCaffeModelCompression](https://github.com/marifnst/SampleCaffeModelCompression) thank you very much for your code. thanks

@yuanyuanli85 okay, thank you very much for your code. it really help me a lot. best regards

hi @WangLei-UESTC my caffe is used on 32 bit OS, please kindly check your OS. or you may use your own caffe. Thanks

hi @eswears my answers: 1. Yes, you can use your own caffe. 2. Deploy.prototxt and deploy_compressed is the structure between original caffemodel and new format caffemodel. 3. Thanks four your...