From 7745eaf21e095de1326767f469216993f4dd76f7 Mon Sep 17 00:00:00 2001 From: Double_V Date: Tue, 25 Feb 2020 16:05:18 +0800 Subject: [PATCH] update vot code (#4338) --- PaddleCV/tracking/README.md | 8 +++++--- PaddleCV/tracking/pytracking/eval_benchmark.py | 6 +++--- PaddleCV/tracking/pytracking/libs/optimization.py | 6 +++--- .../pytracking/parameter/atom/default_vot.py | 13 ++++++------- 4 files changed, 17 insertions(+), 16 deletions(-) diff --git a/PaddleCV/tracking/README.md b/PaddleCV/tracking/README.md index 552534ea..fe7fb44e 100644 --- a/PaddleCV/tracking/README.md +++ b/PaddleCV/tracking/README.md @@ -1,12 +1,12 @@ # tracking 单目标跟踪框架 -## 目标跟踪介绍 +## 介绍 tracking 是基于百度深度学习框架Paddle研发的视频单目标跟踪（Visual Object Tracking, VOT）库, 整体框架参考 [pytracking](https://github.com/visionml/pytracking)，其优秀的设计使得我们能够方便地将其他跟踪器如SiamFC，SiamRPN，SiamMask等融合到一个框架中，方便后续统一的实验和比较。 当前tracking涵盖当前目标跟踪的主流模型，包括SiamFC, SiamRPN, SiamMask, ATOM。tracking旨在给开发者提供一系列基于PaddlePaddle的便捷、高效的目标跟踪深度学习算法，后续会不断的扩展模型的丰富度。 -## 目标跟踪库的代码目录结构 +## 代码目录结构 ``` @@ -36,7 +36,7 @@ pytracking 包含跟踪代码 ### 数据准备 -目标跟踪的训练集和测试集是不同的，目前最好的模型往往是使用多个训练集进行训练。常用的数据集如下: +目标跟踪的训练集和测试集是不同的，目前最好的模型往往是使用多个训练集进行训练。 主流的训练数据集有： - [VID](http://bvisionweb1.cs.unc.edu/ilsvrc2015/ILSVRC2015_VID.tar.gz) @@ -60,6 +60,8 @@ tracking的工作环境： - python3 - PaddlePaddle1.7 +> 注意：如果遇到cmath无法import的问题，建议切换Python版本，建议使用python3.6.8, python3.7.0 + ### 安装依赖 1. 安装paddle，需要安装1.7版本的Paddle，如低于这个版本，请升级到Paddle 1.7. diff --git a/PaddleCV/tracking/pytracking/eval_benchmark.py b/PaddleCV/tracking/pytracking/eval_benchmark.py index 76cd3fac..cf9536eb 100644 --- a/PaddleCV/tracking/pytracking/eval_benchmark.py +++ b/PaddleCV/tracking/pytracking/eval_benchmark.py @@ -19,9 +19,9 @@ CURRENT_DIR = osp.dirname(__file__) sys.path.append(osp.join(CURRENT_DIR, '..')) from pytracking.admin.environment import env_settings -from pytracking.pysot_toolkit.datasets import DatasetFactory -from pytracking.pysot_toolkit.evaluation import EAOBenchmark, AccuracyRobustnessBenchmark, OPEBenchmark -from pytracking.pysot_toolkit.utils.region import vot_overlap +from pytracking.pysot_toolkit.pysot.datasets import DatasetFactory +from pytracking.pysot_toolkit.pysot.evaluation import EAOBenchmark, AccuracyRobustnessBenchmark, OPEBenchmark +from pytracking.pysot_toolkit.pysot.utils.region import vot_overlap parser = argparse.ArgumentParser(description='tracking evaluation') diff --git a/PaddleCV/tracking/pytracking/libs/optimization.py b/PaddleCV/tracking/pytracking/libs/optimization.py index 47dab592..41236ad8 100644 --- a/PaddleCV/tracking/pytracking/libs/optimization.py +++ b/PaddleCV/tracking/pytracking/libs/optimization.py @@ -394,7 +394,7 @@ class ConjugateGradient(ConjugateGradientBase): fetch_list=[v.name for v in self.f0]) res = TensorList(res) loss = self.problem.ip_output(res, res) - print('Paddle Loss: {}'.format(loss)) + #print('Paddle Loss: {}'.format(loss)) class GaussNewtonCG(ConjugateGradientBase): @@ -614,7 +614,7 @@ class GaussNewtonCG(ConjugateGradientBase): fetch_list=[v.name for v in self.f0]) res = TensorList(res) loss = self.problem.ip_output(res, res) - print('Paddle Loss: {}'.format(loss)) + #print('Paddle Loss: {}'.format(loss)) class GradientDescentL2: @@ -691,7 +691,7 @@ class GradientDescentL2: fetch_list=[self.loss.name] + grad_names) if self.debug: loss = res[0] - print('Paddle Loss: {}'.format(loss)) + #print('Paddle Loss: {}'.format(loss)) grad = TensorList(res[1:]) diff --git a/PaddleCV/tracking/pytracking/parameter/atom/default_vot.py b/PaddleCV/tracking/pytracking/parameter/atom/default_vot.py index ce8d0cce..e59e0187 100644 --- a/PaddleCV/tracking/pytracking/parameter/atom/default_vot.py +++ b/PaddleCV/tracking/pytracking/parameter/atom/default_vot.py @@ -1,6 +1,6 @@ import numpy as np -from pytracking.features.deep import ResNet50 +from pytracking.features.deep import ResNet18, ResNet50 from pytracking.features.extractor import MultiResolutionExtractor from pytracking.utils import TrackerParams, FeatureParams @@ -42,7 +42,9 @@ def parameters(): params.train_skipping = 10 # How often to run training (every n-th frame) # Online model parameters - deep_params.kernel_size = (4, 4) # Kernel size of filter + # deep_params.kernel_size = (4, 4) # when slice double grad is support, + # else, deep_params.kernel_size = (5, 5) + deep_params.kernel_size = (5, 5) # Kernel size of filter deep_params.compressed_dim = 64 # Dimension output of projection matrix deep_params.filter_reg = 1e-1 # Filter regularization factor deep_params.projection_reg = 1e-4 # Projection regularization factor @@ -104,11 +106,8 @@ def parameters(): # Setup the feature extractor (which includes the IoUNet) deep_fparams = FeatureParams(feature_params=[deep_params]) - deep_feat = ResNet50( - net_path='/home/vis/bily/code/baidu/personal-code/libi-13/paddle_ATOMnet-ep0040', - output_layers=['block2'], - fparams=deep_fparams, - normalize_power=2) + deep_feat = ResNet18( + output_layers=['block2'], fparams=deep_fparams, normalize_power=2) params.features = MultiResolutionExtractor([deep_feat]) params.vot_anno_conversion_type = 'preserve_area' -- GitLab