Anyone who achieve reported performance ? Run successfully, 0.78ccuracy gained

[JingyunLiang]

To prepare for the lmdb data, I first resize the short side to 448 with original ratio in Matlab, and save them on the disk. Then I use official caffe code to generate test_shortside448.lmdb. However, I failed at last.

I tried two different settings: class label starts from 0 and class label starts from 1. None of then worked. Is there any other detail I messed?

 I0427 20:00:13.632690  7424 net.cpp:255] Network initialization done.
[libprotobuf WARNING google/protobuf/io/coded_stream.cc:505] Reading dangerously large protocol message.  If the message turns out to be larger than 2147483647 bytes, parsing will be halted for security reasons.  To increase the limit (or to disable these warnings), see CodedInputStream::SetTotalBytesLimit() in google/protobuf/io/coded_stream.h.
[libprotobuf WARNING google/protobuf/io/coded_stream.cc:78] The total number of bytes read was 1064471629
I0427 20:00:15.885128  7424 caffe.cpp:291] Running for 50 iterations.
I0427 20:00:16.072052  7424 caffe.cpp:314] Batch 0, accuracy1+2 = 0
I0427 20:00:16.072088  7424 caffe.cpp:314] Batch 0, accuracy1+2+3 = 0
...
I0427 20:00:18.361052  7424 caffe.cpp:314] Batch 49, accuracy1+2 = 0
I0427 20:00:18.361081  7424 caffe.cpp:314] Batch 49, accuracy1+2+3 = 0
I0427 20:00:18.361088  7424 caffe.cpp:319] Loss: 0
I0427 20:00:18.361097  7424 caffe.cpp:331] accuracy1+2 = 0
I0427 20:00:18.361104  7424 caffe.cpp:331] accuracy1+2+3 = 0.02```

[JingyunLiang]

Problem solved. The authors use Common_Yellowthroat as the 0 class, which is different to most of us: use Common_Yellowthroat as the 200 class.
However, I still don't achieve reported accuracy. I got train acc of 100% and test acc of only 78% (supposed to be 85.3%). I follow the official instruction.
README.txt

[Ostnie]

@MichaelLiang12 Hello, I'm trying to begin my experient according to this paper in TensorFlow , but the code link are unavailabel . Do you have download it ?Only code is very well ,I want to know more details in it .Could you please send it to me ? My mailbox is [email protected] .Thank you very much !

[JingyunLiang]

The link is still available now. Maybe you should turn to a VPN tool like Lantern. For convenience, I uploaded the resource to BaiduYun.

[suhuijia]

@MichaelLiang12 Hello, I'm trying to training... Could you please send the train.prototxt to me? Thank you very much.

[JingyunLiang]

I don't have train.prototxt neither. Even for testing, I failed to reproduce.

[ProblemTryer]

@MichaelLiang12 Hi, can you leave a contact to me (maybe qq)?
I am confused about training the model on windows. Could you give me some instructions? My email address is [email protected]
thank you very much!

[JingyunLiang]

@ProblemTryer Sorry, I didn't try to train the model. I just tested the model with given files, but achieved inferior results.

[mmmxl6]

The link is still available now. Maybe you should turn to a VPN tool like Lantern. For convenience, I uploaded the resource to BaiduYun.

百度云链接失效了请问还可以分享一下链接嘛，或者我的邮箱是[email protected]，非常感谢