CastleDream
CastleDream
> hello ！there is no embed.npy in dir data. The author supply a link in readme,it's https://github.com/indiejoseph/chinese-char-rnn,but there are no .npy file,you need to train by yourself.Good luck!
@yanue 好使了，谢谢，🥳🥳🥳🥳
> RGB2Gray actually takes weights=(0.299, 0.587, 0.114) as argument because these are the coefficients needed to convert an RGB image to a Grayscale one (https://en.wikipedia.org/wiki/Grayscale). However, the default process of...
看这个文档 上图所示数据流仅适用于当用户没有自定义 Runner 中的 TrainLoop、ValLoop 和 TestLoop，并且没有在其自定义模型中覆写 train_step、val_step 和 test_step 方法时。MMSegmentation 中 loop 的默认设置如下：使用IterBasedTrainLoop 训练模型，共计 20000 次迭代，并且在每 2000 次迭代后进行一次验证 ...... 蓝色线表示 [val_step](https://github.com/open-mmlab/mmsegmentation/blob/c685fe6767c4cadf6b051983ca6208f1b9d1ccb8/docs/zh_cn/advanced_guides/models.md#val_step) 和 [test_step](https://github.com/open-mmlab/mmsegmentation/blob/c685fe6767c4cadf6b051983ca6208f1b9d1ccb8/docs/zh_cn/advanced_guides/models.md#test_step)。这两个过程的数据流除了模型输出与 train_step 不同外，其余均和 train_step 类似。由于在评估时模型参数会被冻结，因此模型的输出将被传递给 [Evaluator](https://github.com/open-mmlab/mmsegmentation/blob/c685fe6767c4cadf6b051983ca6208f1b9d1ccb8/docs/zh_cn/advanced_guides/evaluation.md#ioumetric)。 来计算指标。...
you can look this flow image in [document](https://github.com/open-mmlab/mmsegmentation/blob/main/docs/zh_cn/advanced_guides/data_flow.md):  and when you in test and val stage, you just evaluator model, don't receive loss, and can't get val loss if...
> Hi @HAOCHENYE, is there anything else which needs to be done for this PR? Can you please elaborate? Your PR is not run correctly, you need to see the...
> thanks > […](#) > ---- 回复的原邮件 ---- | 发件人 | ***@***.***> | | 日期 | 2024年02月13日 20:06 | | 收件人 | ***@***.***> | | 抄送至 | ***@***.***>***@***.***> | |...
https://github.com/CastleDream/openMMLabCampusLearn/tree/master/Exercise_4
https://github.com/CastleDream/openMMLabCampusLearn/tree/master/Exercise_3 表格里登记了 忘记在这里评论了 代码的提交时间是符合截止日。。。
https://github.com/CastleDream/openMMLabCampusLearn/tree/master/Exercise_5