Mohamed Amine

can you provide where the error is coming from? specific file name or trace stack ?

HI thank you for your reply i got those times on a GPU : gtx850m 4GB ddr3 on CPU (i7-4710HQ/Intel HD4600) a get about 850ms/image and weirdly less predictions ?...

@MikeShi42 you can remove BatchNorm layers from the model as they are not needed for inference(i think) i managed to do it but i am not very sure about the...

https://github.com/TheHidden1/tiny-yolo-noBatch i am not sure about the Perfs impact but this definitively uses less memory right now i think the post processing is messy , from what i can uderstand...

@justadudewhohacks how exactly do you slice beforehand ?? and how do you do nms on gpu ? I managed ~20ms forward time +pre/post processing on tinyyolov2 and tinyyolov3 on a...

@justadudewhohacks @MikeShi42 i tried measuring the timings with [tf.time](https://js.tensorflow.org/api/0.11.1/#time) and i am still getting the same results (i think) the downloadWaitMs is still the major bottleneck while kernelMs is fine...

@MikeShi42 the timing are for the whole inference pipeline(pre-processing +prediction +post-processing) i know the KernelMs times look weird but the docs says >kernelMs: Kernel execution time, ignoring data transfer. and...

@MikeShi42 can you try and do the benchmark yourself to see if you can get similar results ?

this is on the full yolov3  ithink there is something wrong with tf.time() or i am doing something wrong

ehehehhehehe https://groups.google.com/a/tensorflow.org/forum/?utm_medium=email&utm_source=footer#!msg/tfjs/YfH5_GTnx3E/Xx95BT4SAgAJ >Right now tf.time() is totally busted. The GPU timer we use was turned off in chrome recently because of Spectre / Meltdown.