batch_size idea about icnet-tensorflow HOT 9 OPEN

Can you tell me the resolution of your input images? 1024*2048 size image give me 0.04 sec on GTX1080. Yes, you can change the code to feed batch of images as input, and this might be much faster.

from icnet-tensorflow.

On my machine with the gtx 1080 for an image of 1920x1080 is .18 sec ... hmm almost 4 times slower, isnthere any settings I need to do?

from icnet-tensorflow.

Oh, my graphic card is gtx 1080 ti, but I don't think gtx 1080 will 4 times slower than it. Can you try with single input image with following code?

for i in range(10):
    start_time = time.time()
    preds = sess.run(pred, feed_dict={x: img})
    print(time.time() - start_time)

from icnet-tensorflow.

Yes that’s the way I outputed as well

from icnet-tensorflow.

GPU: gtx 1080 (not a TI)
Tensorflow: (r1.6 from the source)
Libcuda: 8.0
Libcnn: 5.0
gpu decide version: 6.1
python: 2.7
Even I played with the blaze build option to re-compile tensorflow but still I don't get 0.04 sec as your machine. still around 0.17-0.18 second per frame 1920x1080...

from icnet-tensorflow.

@aliericcantona , when I install r1.6, it recommended cuda 9.0, I don't know whether this is a problem or not. However, I use tf 1.4 instead of tf 1.6, maybe you can try on tf 1.4? I think 0.17 is really slow for gtx 1080, really strange.

from icnet-tensorflow.

still I can't get less than 0.16 sec. Even I have the new image on my centos 7 machine. Is there any trick (OS) wise that you get that number? 4 times faster than mine.

from icnet-tensorflow.

BTW, I installed cuda 9.1 and cudnn 7.0 with tensorflow r1.6 on gpu 1080ti, stil the same number. 0.16seconds per frame of 1920x1080 size.
I installed tensorflow from the source. Is there any special trick you may know of when ./configure?

from icnet-tensorflow.

Can you list your machine installed packages list, mine is as the following:

1. protobuf == 3.5.2
2. python 2.7.5
3. gcc 4.8.5
4. nvidia cuda 9.0
5. nvidia cudann 7.0
6. protobuf
7. OS (Centos 7)

from icnet-tensorflow.