tianhongtao / id-daml Goto Github PK

作者您好，我在尝试运行您的DAML代码过程中，出现了以下问题，想向您请教下解决方法。
Traceback (most recent call last):
File "D:\ID-DAML-master\reappearance\DAML.py", line 412, in
main(path)
File "D:\ID-DAML-master\reappearance\DAML.py", line 364, in main
train_loss.backward()
File "D:\anaconda3\envs\pytorch\lib\site-packages\torch_tensor.py", line 396, in backward
torch.autograd.backward(self, gradient, retain_graph, create_graph, inputs=inputs)
File "D:\anaconda3\envs\pytorch\lib\site-packages\torch\autograd_init_.py", line 175, in backward
allow_unreachable=True, accumulate_grad=True) # Calls into the C++ engine to run the backward pass
RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [24, 32]], which is output 0 of ReluBackward0, is at version 1; expected version 0 instead. Hint: enable anomaly detection to find the operation that failed to compute its gradient, with torch.autograd.set_detect_anomaly(True).

你好，非常感谢你们在文本辅助推荐上做的大量工作并开源代码，我运行程序的时候一直报错，能否帮忙调试一下。
word_model = Word2Vec.load(path.replace('.json', '.model'))
word_model.wv.add("", np.zeros(word_model.vector_size))

AttributeError: 'Word2VecKeyedVectors' object has no attribute 'add'

作者你好，我跑了这个开源项目中的DeepCoNN模型，但是我跑出来的结果MSE是一直在增加的，不知道是不是我哪里跑错了，作者跑代码的过程中对应的MSE是多少呢？

您好，非常感谢您开源代码。我是一名初学者，NRPA复现代码运行生成相应文件时总是出现错误，能否帮忙调试一下。
Traceback (most recent call last):
File "D:\ID-DAML-master\Utils\AWS.py", line 149, in
main(DATA_PATH_MUSIC)
File "D:\ID-DAML-master\Utils\AWS.py", line 43, in main
data_test, data_train = save_rating(data, path)
File "D:\ID-DAML-master\Utils\AWS.py", line 48, in save_rating
data = numerize(data)
File "D:\ID-DAML-master\Utils\AWS.py", line 143, in numerize
data['user_id'] = list(uid)
File "D:\ID-DAML-master\Utils\AWS.py", line 140, in
uid = map(lambda x: user2id[x], data['user_id'])
KeyError: 'A2TYZ821XXK2YZ'

谢谢作者的代码，代码中有多处的dropout设置为1，这个让我很疑惑。请问在跑代码时，需要调整dropout参数嘛？

作者你好，我尝试运行你的代码时遇到困难，因为我没有你运行时对应的文件，包括.json,.model,.para, rating_train.json, rating_test.json文件。因为我想要得到和你一样的结果，如果你能分享这些文件，我会非常感谢你的帮助。同时也非常感谢你所做的工作