linzh92/deepicf

TensorFlow Implementation of Deep Item-based Collaborative Filtering Model for Top-N Recommendation

deepicf's Issues

Move to keras?

Implement Deep ICF using Keras. I am curious why Keras wasn't used in the first place?

how much time will this code cost?

it seems that this code runs forever on my cpu...

When restoring pre trained variables, why not restore model.weights and mode.biases as well?

Load model.biases and model.weights here

TypeError: 'range' object does not support item assignment

Error Details:

Traceback (most recent call last):
File "DeepICF_a.py", line 322, in
best_hr, best_ndcg = training(args.pretrain, model, dataset, args.epochs, args.num_neg)
File "DeepICF_a.py", line 283, in training
np.random.shuffle(batch_index)
File "mtrand.pyx", line 4852, in mtrand.RandomState.shuffle
File "mtrand.pyx", line 4855, in mtrand.RandomState.shuffle
TypeError: 'range' object does not support item assignment

Running on AWS EC2 - tensorflow_p36 environment

Pre-training

Dear linzh92,

Do you have the pre-training code? I want to run DeepICF on a different data set, but I cannot replicate your pre-training.

I look forward to your response! If you can, please send me an e-mail at [email protected]

Thanks a lot!

Sem

Dependency Dashboard

This issue lists Renovate updates and detected dependencies. Read the Dependency Dashboard docs to learn more.

This repository currently has no open or pending branches.

Detected dependencies

None detected

---

• Check this box to trigger a request for Renovate to run again on this repository

代码里是如何让导入数据的

您好，我是推荐系统的初学者，看您的代码的时候，没发现有导入数据文件的代码，请问应该在什么位置导入，还有我运行您的代码时候，出现了SystemExit: 2 的问题，请问应该怎么解决，我是小白，希望能帮忙解答，谢谢

Test Loss behaviour

When training, the test loss does not decrease (as it should), but the Hit Ratio keeps increasing. Doesn't this suggest that the loss function being used is incorrect?
For example here when training DeepICF (with attention, same config params as the README) -

Epoch 0 [153.6s + 600.3s]: HR = 0.5296, NDCG = 0.2971, loss = 0.2525 [54.1s] train_loss = 0.3235 [184.5s]
Epoch 1 [173.1s + 594.7s]: HR = 0.5957, NDCG = 0.3382, loss = 0.2550 [49.2s] train_loss = 0.2908 [152.5s]
Epoch 2 [163.4s + 541.1s]: HR = 0.6270, NDCG = 0.3589, loss = 0.2763 [48.7s] train_loss = 0.2734 [168.5s]
Epoch 3 [165.3s + 540.0s]: HR = 0.6444, NDCG = 0.3757, loss = 0.2468 [49.2s] train_loss = 0.2640 [169.9s]
Epoch 4 [167.5s + 522.3s]: HR = 0.6526, NDCG = 0.3818, loss = 0.2376 [49.0s] train_loss = 0.2592 [162.8s]
Epoch 5 [166.1s + 528.3s]: HR = 0.6588, NDCG = 0.3868, loss = 0.2655 [42.5s] train_loss = 0.2539 [149.1s]
Epoch 6 [163.5s + 491.9s]: HR = 0.6596, NDCG = 0.3893, loss = 0.2553 [44.8s] train_loss = 0.2512 [151.7s]
Epoch 7 [164.6s + 456.7s]: HR = 0.6666, NDCG = 0.3938, loss = 0.2512 [36.5s] train_loss = 0.2488 [125.5s]

And so on...
Do you know what might be causing this or if there is a way to make the test loss decrease consistently as well (like the training loss)?