ygean

alink1.5.2 getOutputTable().to_pandas() raise ERROR

3

sample code as below: ``` input_users = [[617127], [4841758], [382730], [1399180]] df_users = pd.DataFrame(input_users) sdata = StreamOperator.fromDataframe(df_users, schemaStr='user bigint') predictor = ItemCfItemsPerUserRecommStreamOp(model)\ .setUserCol("user")\ .setReservedCols(["user"])\ .setK(3)\ .setRecommCol("prediction_result"); b = predictor.linkFrom(sdata).getOutputTable() StreamOperator.execute()...

Anchor boxes visualization

9

@yangze0930 Hi, I get self.top_n_cdds in model.py/attention_net and then I pad image to 896 x 896 size, draw anchor boxes in padded image. Have I done something wrong in this...

How to calculate out five dedicated aspect ratios on own dataset

2

Thank you for your greateful work, as the title asks, how can I calculate out five dedicated aspect ratios on own dataset? @JingChaoLiu

pytorch 0.4.1 support?

1

Have anybody tested on pytorch 0.4.1? I need some advice, thank you.

Thank you for your excellent work,but have you ever test your code detecting images, and make a speed and accurancy report

It needs all guys to run codes and report bugs, and then fix them.

What's your pytorch's version?

1

What's your pytorch's version?

Code checking

4

`from net.refinenet.blocks import un_pool, ResidualConvUnit, RefineNetBlock, RefineNetBlockImprovedPooling ImportError: cannot import name 'RefineNetBlockImprovedPooling'` Happy new year and thank for sharing. I met this fatal issue when I ran train.py, error infos...

How is it going? @jinfagang