PyTorch library for recommender systems
Project description
Requirements:
Python == 3.9 | PyTorch == 1.12.1 | TorchData == 0.4.1 | PyG
Installation
pip install freerec
Help
optional arguments:
-h, --help show this help message and exit
--root ROOT data
--config CONFIG config.yml
--optimizer {sgd,adam}
--nesterov nesterov for SGD
-mom MOMENTUM, --momentum MOMENTUM
the momentum used for SGD
-beta1 BETA1, --beta1 BETA1
the first beta argument for Adam
-beta2 BETA2, --beta2 BETA2
the second beta argument for Adam
-wd WEIGHT_DECAY, --weight-decay WEIGHT_DECAY
weight for 'l1|l2|...' regularzation
-lr LR, --lr LR, --LR LR, --learning-rate LR
-b BATCH_SIZE, --batch-size BATCH_SIZE
--epochs EPOCHS
--eval-valid evaluate validset
--eval-test evaluate testset
--eval-freq EVAL_FREQ
the evaluation frequency
--num-workers NUM_WORKERS
--buffer-size BUFFER_SIZE
buffer size for datapipe
--seed SEED calling --seed=-1 for a random seed
--benchmark cudnn.benchmark == True ?
--verbose show the progress bar if true
--resume resume the training from the recent checkpoint
--fmt FMT
-m DESCRIPTION, --description DESCRIPTION
-eb EMBEDDING_DIM, --embedding_dim EMBEDDING_DIM
-neg NUM_NEGS, --num_negs NUM_NEGS
Reference Code
- TorchRec: https://github.com/pytorch/torchrec
- DeepCTR-Torch: https://github.com/shenweichen/DeepCTR-Torch
- FuxiCTR: https://github.com/xue-pai/FuxiCTR
- BARS: https://github.com/openbenchmark/BARS
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
freerec-0.1.1.tar.gz
(40.6 kB
view hashes)