fvcore庫的簡介
fvcore是一個輕量級的核心庫,它提供了在各種計算機視覺架構(如Detectron2)中共享的最常見和最基本的功能。這個庫基于Python 3.6+和PyTorch。這個庫中的所有元件都經過了類型注釋、測試和基準測試。Facebook 的人工智能實驗室即FAIR的計算機視覺組負責維護這個庫。
github位址:
https://github.com/facebookresearch/fvcorefvcore庫的安裝
pip install -U 'git+https://github.com/facebookresearch/fvcore'
![](https://img.laitimes.com/img/__Qf2AjLwojIjJCLyojI0JCLicmbw5yM5Y2MmhDO3UWZ2UmN0gjY3EGM0UWZ3kDMihDZmFTZi9CX5d2bs92Yl1iclB3bsVmdlR2LcNWaw9CXt92Yu4GZjlGbh5yYjV3Lc9CX6MHc0RHaiojIsJye.png)
fvcore庫的使用方法
1、基礎用法
"""Configs."""
from fvcore.common.config import CfgNode
# -----------------------------------------------------------------------------
# Config definition
_C = CfgNode()
# ---------------------------------------------------------------------------- #
# Batch norm options
_C.BN = CfgNode()
# BN epsilon.
_C.BN.EPSILON = 1e-5
# BN momentum.
_C.BN.MOMENTUM = 0.1
# Precise BN stats.
_C.BN.USE_PRECISE_STATS = False
# Number of samples use to compute precise bn.
_C.BN.NUM_BATCHES_PRECISE = 200
# Weight decay value that applies on BN.
_C.BN.WEIGHT_DECAY = 0.0
# Training options.
_C.TRAIN = CfgNode()
# If True Train the model, else skip training.
_C.TRAIN.ENABLE = True
# Dataset.
_C.TRAIN.DATASET = "kinetics"
# Total mini-batch size.
_C.TRAIN.BATCH_SIZE = 64
# Evaluate model on test data every eval period epochs.
_C.TRAIN.EVAL_PERIOD = 1
# Save model checkpoint every checkpoint period epochs.
_C.TRAIN.CHECKPOINT_PERIOD = 1
# Resume training from the latest checkpoint in the output directory.
_C.TRAIN.AUTO_RESUME = True
# Path to the checkpoint to load the initial weight.
_C.TRAIN.CHECKPOINT_FILE_PATH = ""
# Checkpoint types include `caffe2` or `pytorch`.
_C.TRAIN.CHECKPOINT_TYPE = "pytorch"
# If True, perform inflation when loading checkpoint.
_C.TRAIN.CHECKPOINT_INFLATE = False