IMN-E2E-ABSA

IMN-E2E-ABSA copied to clipboard

why can't use the gpu to train?

4

Hello, when i use the command-- "CUDA_VISIBLE_DEVICES=0 python train.py --domain res_15" to run the process. First,it occurs the warning-- "UserWarning: Converting sparse IndexedSlices to a dense Tensor of unknown shape....

JBoRu

Hello, where is the res_only_A_norm0.5.pkl in the dataset？

lilililisa1998

I have read files .xml from SemEval datasets but in those files, there are only ASPECT and SENTIMENT labels. So, my question is how you generate labels for OPINION? Are...

HariWu1995

Hi @ruidan , Thanks for this repo. Can the trained model be used for getting inference on new data ? If so , please let me know how to. Thanks

vivektop

Validation and Test Results Didn't Change

2

Hi @ruidan , I have run the training and validating scripts with the default setting but the validation result and test result still same in all epoch.  Do you...

bigredbug47

loss=0

1

为什么训练集loss一直为0？ Why is the Train set loss always 0?

dongyang12138

请问您的结果是怎么取的

2

请问您的结果是取的是测试集loss最小值时候的结果还是取的F1-I最高的时候的结果？ 还是其他的取值方式，或者多次试验取平均？

dongyang12138

您好，请问gold labels表示什么含义？ Hello, what does gold labels mean?

dongyang12138

TypeError: Layer sequential_1_input does not support masking, but was passed an input_mask: Tensor("concatenate_1/All:0", shape=(?, 78), dtype=bool)

7

Hi, I am interested in your work. I run your code, but I encountered the error which is "TypeError: Layer sequential_1_input does not support masking, but was passed an input_mask:...

ConnieTong

return 0.01 * np.random.standard_normal(size=shape) File "mtrand.pyx", line 1545, in mtrand.RandomState.standard_normal File "mtrand.pyx", line 167, in mtrand.cont0_array TypeError: 'float' object cannot be interpreted as an integer

3

return 0.01 * np.random.standard_normal(size=shape) File "mtrand.pyx", line 1545, in mtrand.RandomState.standard_normal File "mtrand.pyx", line 167, in mtrand.cont0_array TypeError: 'float' object cannot be interpreted as an integer 请问怎么改正这个bug

dongyang12138