ares89

中文输入法怎么弄呢

黏贴中文是可以的

https://www.jianshu.com/p/2167eb257429

我 设置batchsize为卡个数的倍数 就解决了

Perhaps you can create two ACDATs, one for all words (10 million keywords) and one for temporary words (added keywords). The end result is to merge from the entire word...

使用了3.1.2依然不一样

使用了3.1.2依然报错哦

you need upgrade the pytorch_java_only.jar to version 1.5.0.

> [https://download.pytorch.org/libtorch/cu102/libtorch-shared-with-deps-1.5.0.zip，](https://download.pytorch.org/libtorch/cu102/libtorch-shared-with-deps-1.5.0.zip%EF%BC%8C) is not 1.5.0? yes,libtorch version is 1.5.0, but what's the version of your pytorch_java_only.jar ?

@Jean332 @brade31919 in the model.py https://github.com/brade31919/SRGAN-tensorflow/blob/2e3766a273caae19ecce99afa01a77b5402b6faf/lib/model.py#L199 modify im = sic.imread(name).astype(np.float32) to im = sic.imread(name,mode="RGB").astype(np.float32) to fix the problem. that is because some png file has an alpha channel.