Programmer

> without the bias term ( as in the repo), I get 10.954855 +- 0.4320521 inception score on CIFAR-10(using test images). > > with the bias term ( as in...

> @Adherer I think you can take a look at [here](https://easydl.readthedocs.io/en/latest/modules/easydl.tf.html?highlight=inception_score#easydl.tf.evaluation.get_inception_score). But it seems that the model file of that link has changed. Fortunately, I have saved a copy of...

> Sorry, at present, we only have the TensorFlow implementation. Thank you for your reply!

能方便告知一下如何修改的吗？

在P40显卡下也是一样的情况，以下是我的实验记录： * 不启用fp16，load_in_8bit True bs == 2，占用显存18G左右 * 不启用fp16，load_in_8bit True bs == 1，占用显存12G左右 * 不启用fp16，load_in_8bit False bs == 1，RuntimeError: expected scalar type Half but found Float * 启用fp16，load_in_8bit False bs...

> 最终的loss降到了多少？ 默认配置： {"epoch": 1.0, "learning_rate": 1.0384615384615385e-08, "loss": 1.4521, "step": 52000}

> > > 在P40显卡下也是一样的情况，以下是我的实验记录： > > > > > > * 不启用fp16，load_in_8bit True bs == 2，占用显存18G左右 > > > * 不启用fp16，load_in_8bit True bs == 1，占用显存12G左右 > > > * 不启用fp16，load_in_8bit...

have the same question

我用P40训练，batch_size等于1时，loss也是0，请问您解决了吗？ {"epoch": 0.0, "learning_rate": 1.9980769230769233e-05, "loss": 0.0, "step": 50}, {"epoch": 0.0, "learning_rate": 1.9961538461538464e-05, "loss": 0.0, "step": 100}, {"epoch": 0.0, "learning_rate": 1.9942307692307695e-05, "loss": 0.0, "step": 150} 更新：batch_size等于2时，step=50时，loss不为0，后续都是0，感觉像是个bug {"epoch":0.0,"learning_rate":1.9980769230769233e-05,"loss":1.6446,"step":50}, {"epoch":0.0,"learning_rate":1.9961538461538464e-05,"loss":0.0,"step":100}, {"epoch":0.01,"learning_rate":1.9942307692307695e-05,"loss":0.0,"step":150}, {"epoch":0.01,"learning_rate":1.9923076923076926e-05,"loss":0.0,"step":200}

> 我用P40训练，batch_size等于1时，loss也是0，请问您解决了吗？ {"epoch": 0.0, "learning_rate": 1.9980769230769233e-05, "loss": 0.0, "step": 50}, {"epoch": 0.0, "learning_rate": 1.9961538461538464e-05, "loss": 0.0, "step": 100}, {"epoch": 0.0, "learning_rate": 1.9942307692307695e-05, "loss": 0.0, "step": 150} > > 更新：batch_size等于2时，step=50时，loss不为0，后续都是0，感觉像是个bug {"epoch":0.0,"learning_rate":1.9980769230769233e-05,"loss":1.6446,"step":50},...