chenchongthu / deepconn Goto Github PK

Can I ask you why you use drop rate with 1.0??

I am new to tensorflow, and I found that it means you make all your feature goes to zero.

I don't understand why you choose this..

with tf.name_scope("dropout"):
            self.h_drop_u = tf.nn.dropout(self.h_pool_flat_u, 1.0)
            self.h_drop_i= tf.nn.dropout(self.h_pool_flat_i, 1.0)

in model/deepconn.py

Thanks,

hello,
When I read 'google.bin',I also got 'memory error'.i change the google.bin file to a smaller one ,but got the same error ,how can i fix it?

感谢您开源代码，对我帮助很大。在data processing里面发现一个问题。clean_str(string)这个函数里面第一行代码只会保留英文字符，所以后面的代码基本没用了。我访问了您提供的链接，发现那部分参考代码更新了。你留意一下就知道我在说啥了。哈哈。

Hi chenchong, after reading your project. I noticed this part 'DeepCoNN++', this part is related to the yelp data set. But after I downloaded yelp's data set, I didn't find the same data set as in ur code like :
yelp.valid, yelp.test, yelp.train, user_review, item_review

My dataset is downloaded from this link 'https://www.yelp.com/dataset/download' and contains like :
business.json, photos.json, review.json and etc..

Could u tell me where can I find ur dataset? Best Wishes! Thank u :)

hello,
When I read 'google.bin',I got 'memory error'.
Can I use other smaller data in “.bin” file format instead of this data?Can you provide download link?

Thank you!

你好，把代码改成python3的版本相应的tensorflow应该用什么版本呢？

是内存不够吗。

Loading data...
I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
I tensorflow/core/common_runtime/gpu/gpu_device.cc:885] Found device 0 with properties:
name: GeForce GTX 950M
major: 5 minor: 0 memoryClockRate (GHz) 1.124
pciBusID 0000:01:00.0
Total memory: 3.95GiB
Free memory: 3.21GiB
I tensorflow/core/common_runtime/gpu/gpu_device.cc:906] DMA: 0
I tensorflow/core/common_runtime/gpu/gpu_device.cc:916] 0: Y
I tensorflow/core/common_runtime/gpu/gpu_device.cc:975] Creating TensorFlow device (/gpu:0) -> (device: 0, name: GeForce GTX 950M, pci bus id: 0000:01:00.0)
Tensor("fm/Sum:0", shape=(?, 1), dtype=float32)
Tensor("fm/add_1:0", shape=(?, 1), dtype=float32)
WARNING:tensorflow:From train.py:149 in .: initialize_all_variables (from tensorflow.python.ops.variables) is deprecated and will be removed after 2017-03-02.
Instructions for updating:
Use tf.global_variables_initializer instead.
Load word2vec u file ../data/google.bin

Load word2vec i file ../data/google.bin

518
Traceback (most recent call last):
File "train.py", line 223, in
pkl_file = open(FLAGS.valid_data, 'rb')
IOError: [Errno 2] No such file or directory: '../data/music/music.valid'
(.venv) mldl@ub1604:~/ub16_prj/DeepCoNN/model$

hi author,
Do you have shared the dataset of this project?

Hello authors:
After I run your code , some errors happened . my running environment is python2.7 and Tensorflow 0.12.1
, Here are some basic errors:

Load word2vec u file ../data/google.bin
File "/home/zxj/PycharmProjects/DeepCoNN/model/train.py", line 157, in
with open(FLAGS.word2vec, "rb") as f:
IOError: [Errno 2] No such file or directory: '../data/google.bin'

你好， 你的实现中针对user，item使用了不同的lookup 矩阵，也就是说，同一个单词在user中对应的词向量，跟item中对应的词向量是不一样的；
这似乎有点说不通。

大佬，这个google.bin是在哪里下载的

前辈您好，
您在代码里注释的
#tf.flags.DEFINE_string("word2vec", "./data/rt-polaritydata/google.bin", "Word2vec file with pre-trained embeddings (default: None)")
这个google.bin文件就是谷歌的GoogleNews-vectors-negative300.bin文件是么？

I have read both DeepCoNN and DeepCoNN++ code, as well as the corresponding papers. But I didn't find the attention review pooling part in DeepCoNN++ code. Actually, there's no attention. So is it the final code version for your WWW 2018 paper ?

DeepCoNN/pro_data/loaddata.py 运行不了，报的是pickle 错误
print(item_reviews[11])
pickle.dump(user_reviews, open(os.path.join(TPS_DIR, 'user_review'), 'wb'))

写一个dataloader方法

厉害，多谢分享

Hello i want to ask if your results are overfitting on the test set,but the train loss has been decreasing.

大佬，您好
我想问一下，你当时训练时候机器的内存是多少呢。我目前训练这个机器的内存是22g，然后虚拟内存是55g，最后还是内存爆满。