Paddle训练COCO-stuff数据集学习记录

COCO-stuff数据集

COCO-Stuff数据集对COCO数据集中全部164K图片做了像素级的标注。

80 thing classes, 91 stuff classes and 1 class ‘unlabeled’

在这里插入图片描述

数据集下载
wget --directory-prefix=downloads http://images.cocodataset.org/zips/train2017.zip
wget --directory-prefix=downloads http://images.cocodataset.org/zips/val2017.zip
wget --directory-prefix=downloads http://calvin.inf.ed.ac.uk/wp-content/uploads/data/cocostuffdataset/stuffthingmaps_trainval2017.zip解压数据集
mkdir -p dataset/images
mkdir -p dataset/annotations
unzip downloads/train2017.zip -d dataset/images/
unzip downloads/val2017.zip -d dataset/images/
unzip downloads/stuffthingmaps_trainval2017.zip -d dataset/annotations/

下载完成数据集后需要生成数据集的读取文件，即train.txt，val.txt，根据先前cityspaces数据集的文件格式，博主发现COCO-stuff数据集的结构更为简单，因此便自己写了数据集目标生成代码，代码如下：

import os
import random
filePath1 = '/data/datasets/cocostuff/dataset/images/train2017/'     
filePath2 = '/data/datasets/cocostuff/dataset/annotations/train2017/'    
list_data1=os.listdir(filePath1) 
list_data2=os.listdir(filePath2)  
file = open("/data/datasets/cocostuff/dataset/train.txt", 'w+')
for i,j in zip(list_data1,list_data2):file.write('/data/datasets/cocostuff/dataset/images/train2017/'+i+' ')file.write('/data/datasets/cocostuff/dataset/annotations/train2017/'+j+'\n')
file.close()

生成的目录文件如下：其中第一组数据是数据集图片地址，第二组数据是标注文件地址

在这里插入图片描述

然而，却报错了，提升pre与lable不一致，即图片维度不一致，此时才发现，先前写的目录生成文件没有将图片与标注正确对应，重新改写：

import os
import random
path="train2017/"
filePath1 = '/data/datasets/cocostuff/dataset/images/'+path      
list_data1=os.listdir(filePath1)  
file = open("/data/datasets/cocostuff/dataset/train.txt", 'w+')
for i in list_data1:i=os.path.splitext(i)[0]file.write('/data/datasets/cocostuff/dataset/images/'+path+i+'.jpg ')file.write('/data/datasets/cocostuff/dataset/annotations/'+path+i+'.png'+'\n')
file.close()

生成数据集目录地址后，即可编辑数据集配置文件。

修改数据集配置文件，新建cfg文件，即在configs文件夹的rtformer中新建rtformer_cocostuff_512x512_120k.yml，具体内容如下：

_base_: '../_base_/coco_stuff.yml'batch_size: 3 # total batch size:  4 * 3
iters: 190000train_dataset:transforms:- type: ResizeStepScalingmin_scale_factor: 0.5max_scale_factor: 2.0scale_step_size: 0.25- type: RandomPaddingCropcrop_size: [520, 520]- type: RandomHorizontalFlip- type: RandomDistortbrightness_range: 0.4contrast_range: 0.4saturation_range: 0.4- type: Normalizemean: [0.485, 0.456, 0.406]std: [0.229, 0.224, 0.225]val_dataset:transforms:- type: Resizetarget_size: [2048, 1024]keep_ratio: True- type: Normalizemean: [0.485, 0.456, 0.406]std: [0.229, 0.224, 0.225]export:transforms:- type: Resizetarget_size: [2048, 512]keep_ratio: True- type: Normalizemean: [0.485, 0.456, 0.406]std: [0.229, 0.224, 0.225]optimizer:_inherited_: Falsetype: AdamWbeta1: 0.9beta2: 0.999weight_decay: 0.0125lr_scheduler:_inherited_: Falsetype: PolynomialDecaylearning_rate: 4.0e-4power: 1.end_lr: 1.0e-6warmup_iters: 1500warmup_start_lr: 1.0e-6loss:types:- type: CrossEntropyLosscoef: [1, 0.4]model:type: RTFormerbase_channels: 64head_channels: 128use_injection: [True, False]pretrained: https://paddleseg.bj.bcebos.com/dygraph/backbone/rtformer_base_backbone_imagenet_pretrained.zip

新建coco-stuff.yaml文件，配置数据集：

batch_size: 2
iters: 80000
train_dataset:type: Datasetdataset_root: /train_path: /data/datasets/cocostuff/dataset/train.txtnum_classes: 182transforms:- type: ResizeStepScalingmin_scale_factor: 0.5max_scale_factor: 2.0scale_step_size: 0.25- type: RandomPaddingCropcrop_size: [520, 520]- type: RandomHorizontalFlip- type: RandomDistortbrightness_range: 0.4contrast_range: 0.4saturation_range: 0.4- type: Normalizemode: train
val_dataset:type: Datasetdataset_root: /val_path: /data/datasets/cocostuff/dataset/val.txtnum_classes: 182transforms: - type: Normalizemode: val
optimizer:type: sgdmomentum: 0.9weight_decay: 4.0e-5
lr_scheduler:type: PolynomialDecaylearning_rate: 0.01end_lr: 0power: 0.9
loss:types:- type: CrossEntropyLosscoef: [1]

随后便可以运行了

报错问题

报错1：这个问题令我感到困惑，因为先前已经用该环境训练过cityspces数据集，但还是重新又部署了一下环境，但依旧出错，最后发现是由于博主的数据集类别设置错误导致的，这实在是令人匪夷所思。

OSError: (External) CUDNN error(8), CUDNN_STATUS_EXECUTION_FAILED.   [Hint: Please search for the error code(8) on website (https://docs.nvidia.com/deeplearning/cudnn/api/index.html#cudnnStatus_t) to get Nvidia's official solution and advice about CUDNN Error.] (at /paddle/paddle/phi/kernels/gpudnn/conv_grad_kernel.cu:502)

为以防万一，还是给出环境配置：

在这里插入图片描述

最终运行train.py文件即可

在这里插入图片描述

报错2

 The axis is expected to be in range of [0, 0), but got 0[Hint: Expected axis >= -rank && axis < rank == true, but received axis >= -rank && axis < rank:0 != true:1.] (at ../paddle/phi/infermeta/multiary.cc:961)

这个似乎是版本问题导致的，将paddle调整到2.4.0后该问题就解决了。

报错3

ValueError: (InvalidArgument) The shape of input[0] and input[1] is expected to be equal.But received input[0]'s shape = [1], input[1]'s shape = [1, 1].[Hint: Expected inputs_dims[i].size() == out_dims.size(), but received inputs_dims[i].size():2 != out_dims.size():1.] (at /paddle/paddle/phi/kernels/funcs/concat_funcs.h:55)

似乎是之前博主修改了metrics.py文件导致的，但好像并不是，保持metrics.py文件原样即可，修改下数据集目录即可。

警告

Warning:: 0D Tensor cannot be used as 'Tensor.numpy()[0]' . In order to avoid this problem, 0D Tensor will be changed to 1D numpy currently, but it's not correct and will be removed in release 2.6. For Tensor contain only one element, Please modify  'Tensor.numpy()[0]' to 'float(Tensor)' as soon as possible, otherwise 'Tensor.numpy()[0]' will raise error in release 2.6.