biuleung

@pren1 Thank you for you tutorial. It's really helpful. But I have encountered some error messages during fine tuning the self-pretraining model. It said there were a graph.phtxt and a...

@terrifyzhao Loss超过1是不是不正常? INFO:tensorflow:global_step/sec: 0.617078 INFO:tensorflow:loss = 1.3920796, step = 8895 (162.055 sec)

@terrifyzhao 跑完extract_features一次之後會得到一個類似tmp30_c_o0j名稱的檔， 請問 在fine tuning時，哪裏會引用到這個檔？是否把它放在checkpoint同一個目錄就好？ 而使用官方的extract_features，會產生個json檔，這點也令我很疑惑