add googlenet results?

Question

add googlenet results?

hengck23 opened this issue 8 years ago · 6 comments

Thank you very much for the results. Is there any plan to add results of gogglenet v1,v2,v3,v4? or even squeeze and caffenet (alexnet with lrn layer replaced)?

Answer 1 · 2016-08-11T12:22:54.000Z

+1.

I think GoogleNet is still very well used in many cases.
It would be great if Justin could bring them in.

Answer 2 · 2016-08-11T17:14:02.000Z

CaffeNet would be pretty easy to add since it can be loaded into torch with loadcaffe.

GoogLeNet v1 is doable using soumith/inception.torch and v3 from Moodstocks/inception-v3.torch; I'm not aware of any Torch port of v2 or v4.

I will try and add these benchmarks this weekend.

Answer 3 · 2016-08-26T15:17:16.000Z

@jcjohnson Have you had a chance to benchmark Inception v1 (GoogLeNet) and Inception v3? I'm looking forward to your results if/when they become available. Thanks

Answer 4 · 2016-08-26T17:57:59.000Z

@vimalthilak GoogleNet v1 is easy, but I ran into a snag with v3; they don't provide dumped weights and their weight-dumping script depends on TensorFlow; I opened an issue but haven't gotten a response (Moodstocks/inception-v3.torch#7).

I wasted several hours trying to build TensorFlow from source to support CUDA 8.0 RC so I could use my Pascal Titan X, but couldn't get it to work and gave up.

If someone can provide the dumped weights for GoogLeNet v3 then I can add both benchmarks tomorrow.

Answer 5 · 2016-08-31T07:15:58.000Z

@vimalthilak I've added Inception-v1 results.

Answer 6 · 2017-05-24T02:46:30.000Z

@jcjohnson
Hi, I have the dumped Torch file of inception v3 (https://drive.google.com/drive/folders/0B-XjOBwS-l8sRXRxRW45U3kybjQ). Hope that you can add it as the benchmark.