aim-se / dif-sr Goto Github PK
View Code? Open in Web Editor NEWLicense: Apache License 2.0
License: Apache License 2.0
Could you upload this code?
Thank the author for your contribution. After reading your paper, I began to learn your network structure. How to download the implementation code? Thank you for sharing
Line 1 in b600052
Here it should be Yelp I guess.
selected_features长度大于1会出现下面错误:
[copy.deepcopy(FeatureSeqEmbLayer(dataset,self.attribute_hidden_size[],[self.selected_features[]],self.pooling_mode,self.device)) for _
IndexError: list index out of range
The AAP operation mentioned in the article, I don't seem to see it implemented in code. Can you give me the specific part where it is implemented, and can you give me the specific code?
Hello, thank you for the code you posted.
There is a multi-GPU setting in the code, so I set the config like below
...
gpu_id: '0,1,2,3'
multi_gpus: True
...
In order to use multi-gpu, I used torchrun to run. I put the command as shown below.
torchrun run_recbole.py --model=SASRecD --dataset='Amazon_Beauty' --config_files='configs/Amazon_Beauty.yaml' --nproc=4
However, this kind of error occurs, which doesn't happen in a single GPU setting.
Can you tell me how can I use multi-gpu setting properly?
Does Multi-GPU setting not finished yet?
Thank you for the great code that you provide.
I wanted to give a float-type feature like a rating in the training step.
I checked your code and it seems it only considers token-type features.
Did I understand correctly?
Thank you
Hi, Thanks for your great work.
I would like to ask about the specific label used by AAP in DIF-SR ?
For example, in the Beauty dataset, I print out the categories label of each sample through the code, which is a sample corresponding to a 14-dimensional categories.
Does this ‘categories’ refer to the multi-level categories of the target item?
Whether the category used in the sequence level is a single value or the same 14 dimension value ?
And why ?
hi,
Thank you for providing such good work!
The download url address of the current datasets has a lot of new data. The Amazon and Yelp datasets include different versions in the link. which version of the datasets are you using? Can you provide a more detailed url?
Thank you!
when I use amazon beauty datasets
error:
Traceback (most recent call last):
File "run_recbole.py", line 36, in
run_recbole(model=args.model, dataset=args.dataset, config_file_list=config_file_list,config_dict=parameter_dict)
File "/mnt/workspace/myf/DIF_SR/recbole/quick_start/quick_start.py", line 60, in run_recbole
model = get_model(config['model'])(config, train_data.dataset).to(config['device'])
File "/mnt/workspace/myf/DIF_SR/recbole/model/sequential_recommender/sasrecd.py", line 61, in init
in range(len(self.selected_features))])
File "/mnt/workspace/myf/DIF_SR/recbole/model/sequential_recommender/sasrecd.py", line 60, in
[copy.deepcopy(FeatureSeqEmbLayer(dataset,self.attribute_hidden_size[],[self.selected_features[]],self.pooling_mode,self.device)) for _
File "/home/pai/lib/python3.6/copy.py", line 180, in deepcopy
y = _reconstruct(x, memo, *rv)
File "/home/pai/lib/python3.6/copy.py", line 280, in _reconstruct
state = deepcopy(state, memo)
File "/home/pai/lib/python3.6/copy.py", line 150, in deepcopy
y = copier(x, memo)
File "/home/pai/lib/python3.6/copy.py", line 240, in _deepcopy_dict
y[deepcopy(key, memo)] = deepcopy(value, memo)
File "/home/pai/lib/python3.6/copy.py", line 180, in deepcopy
y = _reconstruct(x, memo, *rv)
File "/home/pai/lib/python3.6/copy.py", line 280, in _reconstruct
state = deepcopy(state, memo)
File "/home/pai/lib/python3.6/copy.py", line 150, in deepcopy
y = copier(x, memo)
File "/home/pai/lib/python3.6/copy.py", line 240, in _deepcopy_dict
y[deepcopy(key, memo)] = deepcopy(value, memo)
File "/home/pai/lib/python3.6/copy.py", line 180, in deepcopy
y = _reconstruct(x, memo, *rv)
File "/home/pai/lib/python3.6/copy.py", line 280, in _reconstruct
state = deepcopy(state, memo)
File "/home/pai/lib/python3.6/copy.py", line 150, in deepcopy
y = copier(x, memo)
File "/home/pai/lib/python3.6/copy.py", line 240, in _deepcopy_dict
y[deepcopy(key, memo)] = deepcopy(value, memo)
File "/home/pai/lib/python3.6/copy.py", line 150, in deepcopy
y = copier(x, memo)
File "/home/pai/lib/python3.6/copy.py", line 215, in _deepcopy_list
append(deepcopy(a, memo))
File "/home/pai/lib/python3.6/copy.py", line 180, in deepcopy
y = _reconstruct(x, memo, *rv)
File "/home/pai/lib/python3.6/copy.py", line 280, in _reconstruct
state = deepcopy(state, memo)
File "/home/pai/lib/python3.6/copy.py", line 150, in deepcopy
y = copier(x, memo)
File "/home/pai/lib/python3.6/copy.py", line 240, in _deepcopy_dict
y[deepcopy(key, memo)] = deepcopy(value, memo)
File "/home/pai/lib/python3.6/copy.py", line 169, in deepcopy
rv = reductor(4)
TypeError: can't pickle _thread.RLock objects
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.