May 2019 – Xiaoxu Meng

Numpy Precision

value = 0.0205862828046875
print("%.16f" % value)
value = value.astype(np.float32)
print("%.16f" % value)

value = 0.0205862828046875

print("%.16f" % value)

value = value.astype(np.float32)

print("%.16f" % value)

#output
0.0205862828046875
0.0205862820148468

#output

0.0205862828046875

0.0205862820148468

Precision changed!

Another sad experience with cuda.

Tensorflow compiling with cuda just doesn’t work when I suspend my machine. (Error: GPU cannot be found.)
1. Tried to reinstall tensorflow again…FAILED!
2. Tried to restart the PC…WORKED!
However, I met this error again:https://github.com/zengarden/light_head_rcnn/issues/9
1. Tried to change:
  1. /home/xiaoxu/Documents/tf_install/venv/lib/python3.6/site-packages/tensorflow/include/tensorflow/core/util/cuda_device_functions.h
    1. line 32:
      1. -#”cuda/include/cuda.h”
      2. +#include “cuda.h”
  2. /home/xiaoxu/Documents/tf_install/venv/lib/python3.6/site-packages/tensorflow/include/tensorflow/core/util/cuda_kernel_helper.h
    1. line 24:
      1. -#”cuda/include/cuda_fp16.h”
      2. +#include “cuda_fp16.h”
Then, I recompiled cuda functions, and got all-zero outputs.
1. I forgot to switch cuda9.0(default) to cuda 10.0, switch to cuda 10.0…WORKED!