Mr_One

跟原版的有无区别

5

你好，原文在 iiit5k 上的准确率是达到了８１．７，但是经过测验只有６５．６左右，请问是因为pytorch 跟torch有什么区别吗，在这上面的调整有可能达到原文的状态吗

hello, i have readed you paper "casual inference for recommendation",but i really don't know how to set the training data, can you provide the code of making skew dataset?

Didn't see the correct folder

6


accurary

1

There is another code using pytorch with the same process as your paper https://github.com/meijieru/crnn.pytorch The parameter in the CNN,RNN is just copy from your paper.And since the frame of torch...

Dear Sir.I am a student .I have finished your paper name"An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition".Since I have the experience...

I want to know if you have the sanme code which is used in tensorflow?

运行season one中的xgb.py出现问题

3

这是什么问题呢？？？ Traceback (most recent call last): File "xgb.py", line 58, in dataset3_preds.label = MinMaxScaler().fit_transform(dataset3_preds.label)#区间缩放到[0,1] File "/home/cxy/anaconda3/lib/python3.6/site-packages/sklearn/base.py", line 518, in fit_transform return self.fit(X, **fit_params).transform(X) File "/home/cxy/anaconda3/lib/python3.6/site-packages/sklearn/preprocessing/data.py", line 308, in fit return...

Loss always be nan

8

Hi, I'm trying to use the code to train my data, but it can not work Sometimes in the first print_log, loss is not nan: [session 1][epoch 1][iter 0/ 300]...

Thanking you for provide the code,it works perfect. But I got a problem when I check the file crowd_count.py, it gota parameter names self.training without define,but it didn't cause any...