MagicSource

Dynamic RNN for time series prediction issue

1

In tutorial about rnn, using toy data implements classify 2 classes dummy series, what if we predict on time series data with only one series? Say: ``` [1.2, 1.1, 1.1,...

FLOPs can not reveal real latency of model, but MACs can?

3

from the last table only saw MACs and params, is that FLOPs doesn't needed a record? While some paper still report their FLOPs/G for comparasion.

such as change an icon?

Question about one function

1

``` def bbox_transform_inv(boxes, deltas): if boxes.shape[0] == 0: return np.zeros((0, deltas.shape[1]), dtype=deltas.dtype) boxes = boxes.astype(deltas.dtype, copy=False) widths = boxes[:, 2] - boxes[:, 0] + 1.0 heights = boxes[:, 3] -...

做的很不错

5

两个问题： 1. 为什么最下面的对于全面屏手机会有一条黑线 2. 打开可不可以加一个checkbox，或者直接再日历视图打卡，因为大部分情况下打卡的周期都是最小是天的单位。这样就很方便打卡，同时也强制不能在一天内打完所有的卡

//lib/x86_64-linux-gnu/libpthread.so.0: error adding symbols: DSO missing from command line

3

what is the error: ``` [100%] Linking CXX executable run_net /usr/bin/ld: CMakeFiles/run_net.dir/tests/run_net.cpp.o: undefined reference to symbol 'pthread_create@@GLIBC_2.2.5' //lib/x86_64-linux-gnu/libpthread.so.0: error adding symbols: DSO missing from command line collect2: error: ld returned...

wondeful work, but a dumb question

2

TensoRF looks like small and very fast traning, is that possible to make the final RGBD result merged into a single point cloud? If so, how? that would be very...

16.0 beta3 support?

6

16.0 beta3 support?

Any examples on real human picture rather than gan generated one?

1

it looks like gan generated picture are obviously faked.

Feature enchancement: draw rectangle on image

2

Does bild support for draw now? Strongly recommend add drawing module such as draw a simple rectangle on image.