tf2-keras implement yolov5

Last update: Jan 08, 2023

Related tags

Deep Learning yolov5_in_tf2_keras

Overview

YOLOv5 in tesnorflow2.x-keras

模型测试

训练 COCO2017(val 5k)

检测效果

精度/召回率

Requirements

pip3 install -r requirements.txt

Get start

训练

python3 train.py

tensorboard

tensorboard --host 0.0.0.0 --logdir ./logs/ --port 8053 --samples_per_plugin=images=40

查看

http://127.0.0.1:8053

测试, 修改detect.py里面input_image和model_path

python3 detect.py

训练自己的数据

labelme打标自己的数据
打开data/labelme2coco.py脚本, 修改如下地方

input_dir = '这里写labelme打标时保存json标记文件的目录'
output_dir = '这里写要转CoCo格式的目录，建议建一个空目录'
labels = "这里是你打标时所有的类别名, txt文本即可, 每行一个类, 类名无需加引号"

执行data/labelme2coco.py脚本会在output_dir生成对应的json文件和图片
修改train.py文件中coco_annotation_file以及num_class, 注意classes通过CoCoDataGenrator(*).coco.cats[label_id]['name']可获得，由于coco中类别不连续，所以通过coco.cats拿到的数组下标拿到的类别可能不准.
开始训练, python3 train.py

Comments

关于类别损失计算的问题

您好，loss这段不是很理解， https://github.com/yyccR/yolov5_in_tf2_keras/blob/3e6645cbf94d2a1e11c33663e80113daa4590321/loss.py#L142-L152 请问targets最后两位应该是置信度1和最佳的anchor索引吗？ https://github.com/yyccR/yolov5_in_tf2_keras/blob/3e6645cbf94d2a1e11c33663e80113daa4590321/loss.py#L288-L293 那这边split出来的true_obj, true_cls应该就是对应的置信度1和最佳的anchor索引吧。那这个类别损失 https://github.com/yyccR/yolov5_in_tf2_keras/blob/3e6645cbf94d2a1e11c33663e80113daa4590321/loss.py#L356 计算的不是最佳anchor索引吗，是跟obj_mask 有关系吗

opened by whalefa1I 5
sparse_categorical_crossentropy训练时有nan结果

有的数据会在这行出现nan https://github.com/yyccR/yolov5_in_tf2_keras/blob/033a1156c1481f4258bf24a4a8215af39682da94/loss.py#L357 查看了input的is_nan，都正常。而且把sparse_categorical_crossentropy换成binary_crossentropy就好了。请问这两者在这里计算有差别吗，是否可以进行替换

opened by whalefa1I 3

lebelme2coco处理逻辑有误

我在实际使用您的代码训练自己的数据集时发现，labelme2coco.py 好像缺少对shape_type == "rectangle"时的处理，导致我最后生成的json文件annotations项为空。以下是labelme2coco.py文件100行到124行代码： ` if shape_type == "polygon": mask = labelme.utils.shape_to_mask( img.shape[:2], points, shape_type ) # cv2.imshow("",np.array(mask, dtype=np.uint8)*255) # cv2.waitKey(0)

            if group_id is None:
                group_id = uuid.uuid1()

            instance = (label, group_id)
            # print(instance)

            if instance in masks:
                masks[instance] = masks[instance] | mask
            else:
                masks[instance] = mask
            # print(masks[instance].shape)

            if shape_type == "rectangle":
                (x1, y1), (x2, y2) = points
                x1, x2 = sorted([x1, x2])
                y1, y2 = sorted([y1, y2])
                points = [x1, y1, x2, y1, x2, y2, x1, y2]
            if shape_type == "circle": 
            ....

` 代码永远不会执行到shape_type == "rectangle"或shape_type == "circle"。

opened by aijialin 2

layers.py
根據ultralytics/yolov5:

https://github.com/ultralytics/yolov5/blob/63ddb6f0d06f6309aa42bababd08c859197a27af/models/common.py#L70-L73

這一段程式:

https://github.com/yyccR/yolov5_in_tf2_keras/blob/46298d7c98073750176d64896ee9dc01b55c5aca/layers.py#L127-L132

是不是應該改寫成:

def call(self, inputs, *args, **kwargs): y = self.multiheadAttention(self.q(inputs), self.v(inputs), self.k(inputs)) + inputs x = self.fc1(x) x = self.fc2(x) x = x + y return x
opened by AugustusHsu 1
What is the mAP on COCO17 val ?

Hi @yyccR, thanks for your repo. I want to know if you can reach the same mAP as in original YOLOV5 (Train on COCO17 train and test on COCO17 val)? And do you have plan to release some pretrained checkpoint ?

opened by Tyler-D 1

Releases(v1.1)

v1.1(Jun 24, 2022)
v1.1 几个总结：

[1]. 调整tf.keras.layers.BatchNormalization的__call__方法中training=True

[2]. 新增TFLite/onnx格式导出与验证，详见/data/h5_to_tflite.py, /data/h5_to_onnx.py

[3]. 修改backbone网络里batch_size，在训练和测试时需指定，避免tflite导出时FlexOps问题

[4]. YoloHead里对类别不再做softmax，直接sigmoid，支持多类别输出

[5]. release里的yolov5s-best.h5为kaggle猫狗脸数据集的重新训练权重，训练:测试为8:2，val精度大概如下：

| class | [email protected] | [email protected]:0.95 | precision | recall | | :-: | :-: | :-: | :-: | :-: | | cat | 0.962680 | 0.672483 | 0.721003 | 0.958333 | | dog | 0.934285 | 0.546893 | 0.770701 | 0.923664 | | total | 0.948482 | 0.609688 | 0.745852 | 0.940999 |

[6]. release里的yolov5s-best.tflite为上述yolov5s-best.h5的tflite量化模型，建议用Netron软件打开查看输入输出

[7]. release里的yolov5s-best.onnx为上述yolov5s-best.h5的onnx模型，建议用Netron软件打开查看输入输出

[8]. android 模型测试效果如下：

就这样，继续加油！💪🏻💪🏻💪🏻
Source code(tar.gz)
Source code(zip)
yolov5s-best.h5(27.51 MB)
yolov5s-best.onnx(27.25 MB)
yolov5s-best.tflite(6.95 MB)
v1.0(Jun 21, 2022)
v1.0 几个总结：

[1]. 模型结构总的与 ultralytics/yolov5 v6.0 保持一致

[2]. 其中Conv层替换swish为Relu

[3]. 整体数据增强与 ultralytics/yolov5 保持一致

[4]. readme中训练所需的数据集为kaggle公开猫狗脸检测数据集，已放到release列表中

[5]. 为什么不训练coco数据集？因为没资源，跑一个coco要很久的，服务器一直都有任务在跑所以没空去跑 - . -

[6]. release里的yolov5s-best.h5为上述kaggle猫狗脸数据集的训练权重，训练:测试为8:2，val精度大概如下：

| class | [email protected] | [email protected]:0.95 | precision | recall | | :-: | :-: | :-: | :-: | :-: | | cat | 0.905156 | 0.584378 | 0.682848 | 0.886555 | | dog | 0.940633 | 0.513005 | 0.724036 | 0.934866 | | total | 0.922895 | 0.548692 | 0.703442 | 0.910710 |

就这样，继续加油！💪🏻💪🏻💪🏻
Source code(tar.gz)
Source code(zip)
JPEGImages.zip(260.17 MB)
yolov5s-best.h5(27.51 MB)

Owner

yangcheng

GitHub Repository

Tidy interface to polars

tidypolars tidypolars is a data frame library built on top of the blazingly fast polars library that gives access to methods and functions familiar to

144 Jan 08, 2023

Chatbot in 200 lines of code using TensorLayer

Seq2Seq Chatbot This is a 200 lines implementation of Twitter/Cornell-Movie Chatbot, please read the following references before you read the code: Pr

820 Dec 17, 2022

Tool for working with Y-chromosome data from YFull and FTDNA

ycomp ycomp is a tool for working with Y-chromosome data from YFull and FTDNA. Run ycomp -h for information on how to use the program. Installation Th

2 Jun 18, 2022

2D&3D human pose estimation

Human Pose Estimation Papers [CVPR 2016] - 201511 [IJCAI 2016] - 201602 Other Action Recognition with Joints-Pooled 3D Deep Convolutional Descriptors

133 Jan 02, 2023

Deep Markov Factor Analysis (NeurIPS2021)

Deep Markov Factor Analysis (DMFA) Codes and experiments for deep Markov factor analysis (DMFA) model accepted for publication at NeurIPS2021: A. Farn

2 Dec 16, 2022

Unrestricted Facial Geometry Reconstruction Using Image-to-Image Translation

Unrestricted Facial Geometry Reconstruction Using Image-to-Image Translation [Arxiv] [Video] Evaluation code for Unrestricted Facial Geometry Reconstr

242 Dec 30, 2022

Code release for BlockGAN: Learning 3D Object-aware Scene Representations from Unlabelled Images

BlockGAN Code release for BlockGAN: Learning 3D Object-aware Scene Representations from Unlabelled Images BlockGAN: Learning 3D Object-aware Scene Rep

41 May 18, 2022

MatryODShka: Real-time 6DoF Video View Synthesis using Multi-Sphere Images

Main repo for ECCV 2020 paper MatryODShka: Real-time 6DoF Video View Synthesis using Multi-Sphere Images. visual.cs.brown.edu/matryodshka

75 Dec 13, 2022

Geometric Vector Perceptron --- a rotation-equivariant GNN for learning from biomolecular structure

Geometric Vector Perceptron Code to accompany Learning from Protein Structure with Geometric Vector Perceptrons by B Jing, S Eismann, P Suriana, RJL T

85 Dec 29, 2022

An open source bike computer based on Raspberry Pi Zero (W, WH) with GPS and ANT+. Including offline map and navigation.

Pi Zero Bikecomputer An open-source bike computer based on Raspberry Pi Zero (W, WH) with GPS and ANT+ https://github.com/hishizuka/pizero_bikecompute

264 Jan 02, 2023

API for RL algorithm design & testing of BCA (Building Control Agent) HVAC on EnergyPlus building energy simulator by wrapping their EMS Python API

RL - EmsPy (work In Progress...) The EmsPy Python package was made to facilitate Reinforcement Learning (RL) algorithm research for developing and tes

20 Jan 05, 2023

DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting

DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting Created by Yongming Rao*, Wenliang Zhao*, Guangyi Chen, Yansong Tang, Zheng Z

322 Dec 31, 2022

Implementation of CSRL from the AAAI2022 paper: Constraint Sampling Reinforcement Learning: Incorporating Expertise For Faster Learning

CSRL Implementation of CSRL from the AAAI2022 paper: Constraint Sampling Reinforcement Learning: Incorporating Expertise For Faster Learning Python: 3

4 Apr 14, 2022

Fast and accurate optimisation for registration with little learningconvexadam

convexAdam Learn2Reg 2021 Submission Fast and accurate optimisation for registration with little learning Excellent results on Learn2Reg 2021 challeng

17 Dec 06, 2022

Re-implementation of the Noise Contrastive Estimation algorithm for pyTorch, following "Noise-contrastive estimation: A new estimation principle for unnormalized statistical models." (Gutmann and Hyvarinen, AISTATS 2010)

Noise Contrastive Estimation for pyTorch Overview This repository contains a re-implementation of the Noise Contrastive Estimation algorithm, implemen

42 Nov 24, 2022

tf2-keras implement yolov5

Related tags

Overview

YOLOv5 in tesnorflow2.x-keras

模型测试

Requirements

Get start

训练自己的数据

Comments

关于类别损失计算的问题

sparse_categorical_crossentropy训练时有nan结果

lebelme2coco处理逻辑有误

layers.py

What is the mAP on COCO17 val ?

Releases(v1.1)

v1.1(Jun 24, 2022)

v1.1 几个总结：

v1.0(Jun 21, 2022)

v1.0 几个总结：