Jiajun Liu
Jiajun Liu
@Zehaos 您好，我运行python tools/time_benchmark.py 得到的结果大概是0.04 htop看到的cpu利用率大概560%，但是当我用下面代码去测试mobilenet的时候得到的速度是0.07左右，两个的区别是什么？ `import tensorflow as tf import mobilenet import time batch_size = 100 height = 224 width = 224 with tf.Session() as sess: inputs = tf.random_uniform((batch_size, height,...
@Zehaos 谢谢回复！请问如何做warm up，还有warm up的作用会这么明显吗？刚才我跑了100次做平均时间没太大变化。
@Zehaos 嗯好的谢谢
@KleinYuan Thanks for your reply, I have drag my model in the target and build successfully. But when I add statement to the function `classifier` in staticDetectorVC.swift like this `var...
@ManjeeraJagiri Have you ever changed your gt?
@D3lt4lph4 Hi,thanks for your reply. I have used watch nvidia-smi to see the gpu utilization, and I found that it jump to 100% and then jump to 0%, I guess...
@ManjeeraJagiri You should check whether gt has "frame02579.png" this key
@D3lt4lph4 Ok, I will try it tomorrow,but why 2875 batches of size 16 ? from the generate() function, we can see that I should have 2875 / 16 batches of...
@ManjeeraJagiri I think you should `print gt["frame02579.png"]` to see whether your gt has this key. If not I think it should not search for this image, and you can put...
@D3lt4lph4 Yes, It solves my problem. And my generator output imgs and targets, the targets' shape is (7308,14) do you know what does 14 mean? from fucntion "assign_boxes" in ssd_utils.py...