标签：line blob and 汇总 展开 dir benchmark number including
作者|facebookresearch
编译|Flin
来源|Github
在这里,我们以一些其他流行的开源Mask R-CNN实现为基准,对Detectron2中Mask R-CNN的训练速度进行了基准测试。
硬件：8个带有NVLink的NVIDIA V100。
软件: Python 3.7, CUDA 10.0, cuDNN 7.6.4, PyTorch 1.3.0 (链接(https://download.pytorch.org/whl/nightly/cu100/torch-1.3.0%2Bcu100-cp37-cp37m-linux_x86_64.whl)),
TensorFlow 1.15.0rc2, Keras 2.2.5, MxNet 1.6.0b20190820.
模型：端到端R-50-FPN Mask-RCNN模型,使用与Detectron基线配置(https://github.com/facebookresearch/Detectron/blob/master/configs/12_2017_baselines/e2e_mask_rcnn_R-50-FPN_1x.yaml)相同的超参数 。
指标：我们使用100-500次迭代中的平均吞吐量来跳过GPU预热时间。请注意,对于R-CNN样式的模型,模型的吞吐量通常会在训练期间发生变化,因为它取决于模型的预测。因此,该指标不能直接与model zoo中的"训练速度"相比较,后者是整个训练过程的平均速度。
| 工具 | 吞吐率(img / s) |
| Detectron2 | 59 |
| maskrcnn-benchmark | 51 |
| tensorpack | 50 |
| mmdetection | 41 |
| simpledet | 39 |
| Detectron | 19 |
| matterport/Mask_RCNN | 14 |
每个实现的详细信息：
Detectron2:
python tools/train_net.py --config-file configs/Detectron1-Comparisons/mask_rcnn_R_50_FPN_noaug_1x.yaml --num-gpus 8
maskrcnn-benchmark: 通过sed -i ‘s/torch.uint8/torch.bool/g’ **/*.py使用commit 0ce8f6f与使其与最新的PyTorch兼容。然后,运行
python -m torch.distributed.launch --nproc_per_node=8 tools/train_net.py --config-file configs/e2e_mask_rcnn_R_50_FPN_1x.yaml
我们观察到的速度比其model zoo快,这可能是由于软件版本不同所致。
tensorpack: 在提交caafda,export TF_CUDNN_USE_AUTOTUNE=0, 然后运行
mpirun -np 8 ./train.py --config DATA.BASEDIR=/data/coco TRAINER=horovod BACKBONE.STRIDE_1X1=True TRAIN.STEPS_PER_EPOCH=50 --load ImageNet-R50-AlignPadding.npz
mmdetection: commit 4d9a5f,应用以下diff,然后运行
./tools/dist_train.sh configs/mask_rcnn_r50_fpn_1x.py 8
我们观察到的速度比其model zoo快,这可能是由于软件版本不同所致。
diff --git i/configs/mask_rcnn_r50_fpn_1x.py w/configs/mask_rcnn_r50_fpn_1x.py
index 04f6d22..ed721f2 100644
--- i/configs/mask_rcnn_r50_fpn_1x.py
+++ w/configs/mask_rcnn_r50_fpn_1x.py
@@ -1,14 +1,15 @@
# model settings
model = dict(
type=‘MaskRCNN‘,
- pretrained=‘torchvision://resnet50‘,
+ pretrained=‘open-mmlab://resnet50_caffe‘,
backbone=dict(
type=‘ResNet‘,
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
- style=‘pytorch‘),
+ norm_cfg=dict(type="BN", requires_grad=False),
+ style=‘caffe‘),
neck=dict(
type=‘FPN‘,
in_channels=[256, 512, 1024, 2048],
@@ -115,7 +116,7 @@ test_cfg = dict(
dataset_type = ‘CocoDataset‘
data_root = ‘data/coco/‘
img_norm_cfg = dict(
- mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+ mean=[123.675, 116.28, 103.53], std=[1.0, 1.0, 1.0], to_rgb=False)
train_pipeline = [
dict(type=‘LoadImageFromFile‘),
dict(type=‘LoadAnnotations‘, with_bbox=True, with_mask=True),
SimpleDet: 在commit9187a1时运行
python detection_train.py --config config/mask_r50v1_fpn_1x.py
Detectron: 运行
python tools/train_net.py --cfg configs/12_2017_baselines/e2e_mask_rcnn_R-50-FPN_1x.yaml
请注意,它的许多操作都在CPU上运行,因此性能受到限制。
matterport/Mask_RCNN:在commit时3deaec,应用以下diff ,export TF_CUDNN_USE_AUTOTUNE=0, 然后运行
python coco.py train --dataset=/data/coco/ --model=imagenet
请注意,此实现中的许多小细节可能与Detectron的标准不同。
diff --git i/mrcnn/model.py w/mrcnn/model.py
index 62cb2b0..61d7779 100644
--- i/mrcnn/model.py
+++ w/mrcnn/model.py
@@ -2367,8 +2367,8 @@ class MaskRCNN():
epochs=epochs,
steps_per_epoch=self.config.STEPS_PER_EPOCH,
callbacks=callbacks,
- validation_data=val_generator,
- validation_steps=self.config.VALIDATION_STEPS,
+ #validation_data=val_generator,
+ #validation_steps=self.config.VALIDATION_STEPS,
max_queue_size=100,
workers=workers,
use_multiprocessing=True,
diff --git i/mrcnn/parallel_model.py w/mrcnn/parallel_model.py
index d2bf53b..060172a 100644
--- i/mrcnn/parallel_model.py
+++ w/mrcnn/parallel_model.py
@@ -32,6 +32,7 @@ class ParallelModel(KM.Model):
keras_model: The Keras model to parallelize
gpu_count: Number of GPUs. Must be > 1
"""
+ super().__init__()
self.inner_model = keras_model
self.gpu_count = gpu_count
merged_outputs = self.make_parallel()
diff --git i/samples/coco/coco.py w/samples/coco/coco.py
index 5d172b5..239ed75 100644
--- i/samples/coco/coco.py
+++ w/samples/coco/coco.py
@@ -81,7 +81,10 @@ class CocoConfig(Config):
IMAGES_PER_GPU = 2
# Uncomment to train on 8 GPUs (default is 1)
- # GPU_COUNT = 8
+ GPU_COUNT = 8
+ BACKBONE = "resnet50"
+ STEPS_PER_EPOCH = 50
+ TRAIN_ROIS_PER_IMAGE = 512
# Number of classes (including background)
NUM_CLASSES = 1 + 80 # COCO has 80 classes
@@ -496,29 +499,10 @@ if __name__ == ‘__main__‘:
# *** This training schedule is an example. Update to your needs ***
# Training - Stage 1
- print("Training network heads")
model.train(dataset_train, dataset_val,
learning_rate=config.LEARNING_RATE,
epochs=40,
- layers=‘heads‘,
- augmentation=augmentation)
-
- # Training - Stage 2
- # Finetune layers from ResNet stage 4 and up
- print("Fine tune Resnet stage 4 and up")
- model.train(dataset_train, dataset_val,
- learning_rate=config.LEARNING_RATE,
- epochs=120,
- layers=‘4+‘,
- augmentation=augmentation)
-
- # Training - Stage 3
- # Fine tune all layers
- print("Fine tune all layers")
- model.train(dataset_train, dataset_val,
- learning_rate=config.LEARNING_RATE / 10,
- epochs=160,
- layers=‘all‘,
+ layers=‘3+‘,
augmentation=augmentation)
elif args.command == "evaluate":
原文链接：https://detectron2.readthedocs.io/notes/benchmarks.html
欢迎关注磐创AI博客站：
http://panchuang.net/
sklearn机器学习中文官方文档：
http://sklearn123.com/
欢迎关注磐创博客资源汇总站：
http://docs.panchuang.net/
标签：line blob and 汇总 展开 dir benchmark number including
原文地址：https://www.cnblogs.com/panchuangai/p/13036569.html
