cfanyyx
cfanyyx
+1, I already trained more than 100000 steps but still got blank outputs.
It seems the input channel after adaptive_avg_pooling in light mode can't be set too small. ``` if self.light: FC = [nn.Linear(ngf * mult, ngf * mult, bias=False), nn.ReLU(True), nn.Linear(ngf *...
Thanks for your reply! There remains a question that I don't understand. In the save_batchnorm_weights() function in https://github.com/pjreddie/darknet/blob/master/src/parser.c, there are only scales, rolling_mean, rolling_variance, I am curious that how they...
@mmreza79 Hi, thanks for replying. I used the default params and trained without label map or instance map. The targets of my training are something like beautifying pictures, removing spots...
How to use SampleEqually(IterableDataset, wds.Shorthands, wds.Composable) under new API? @tmbdev
Also need to add the following line in the makefile and use tf_lib in the link flags. TF_LIB ?= `python -c 'import tensorflow as tf; print(tf.sysconfig.get_lib())'`
@mgharbi Thanks for your reply. Yes, it is! Here are some of the results below. The left one is processed by pretrained model of hdrp, and the right one is...
@mgharbi Only partial test output results are bad and the others are good. There is no problem on the output of the sample image. In addition, I found that the...
@mgharbi @cortes93 After testing, it seems that there is something wrong with ccm, the part of curve looks normal, and the conv2d also has something wrong, but the problem of...
Maybe you need update your gcc version, for example, update to 7.3.