haithink

现在用微信小程序了，掌上图书管理系统

Thank you. The error is "CUDA error 29 at /home/githubCode/TensorRT-Yolov3/tensorRTWrapper/code/src/YoloLayer.cu:22CUDA error 29 at /home/githubCode/TensorRT-Yolov3/tensorRTWrapper/code/src/YoloLayer.cu:25(base)

> 硬件决定，265的输出也可以配成16对齐，但是效率会低一些 请问怎么配成16对齐呢？谢谢！

我下载了[Release v1.8.6](https://gitee.com/lizongying/my-tv/releases/tag/v1.8.6)，直接就没有CCTV6

Here it is assumed that Vj and Vi are very close, so dirG will be close to g.

同样的问题，正说提个issue呢

我在窗口模式也碰到这个问题阿

```python vocab_size = len(word_to_id) contexts, target = create_contexts_target(corpus, window_size) target = convert_one_hot(target, vocab_size) contexts = convert_one_hot(contexts, vocab_size) model = SimpleSkipGram(vocab_size, hidden_size) optimizer = Adam() trainer = Trainer(model, optimizer) trainer.fit(contexts, target,...

I also encounttered this problem. But in some cases, there was not this problem And the only difference is the version of some thirdparty libraries such as boost or opencv.