deep-learning-for-image-processing

deep-learning-for-image-processing copied to clipboard

您好，我运行train.py时，遇到如下报错： FileNotFoundError: Found no valid file for the classes roses, sunflowers, tulips. Supported extensions are: .jpg, .jpeg, .png, .ppm, .bmp, .pgm, .tif, .tiff, .webp 数据集我也是按照你的视频操作的，我debug后显示如下： image_path= 'D:\\deep-learning-for-image-processing-master\\deep-learning-for-image-processing-master\\data_set\\flower_data'

807xuan

yolov3_spp运行报错，运行到datasets.py中line259报错：

1

发生异常: ValueError setting an array element with a sequence. The requested array has an inhomogeneous shape after 1 dimensions. The detected shape was (5717,) + inhomogeneous part. File "D:\file\objectsegmentation\yolov3_spp\build_utils\datasets.py", line...

xin1347764176

**System information** * Have I written custom code: * OS Platform(e.g., window10 or Linux Ubuntu 16.04): * Python version: * Deep learning framework and version(e.g., Tensorflow2.1 or Pytorch1.3): * Use...

xin1347764176

数据读取中关键词错误

5

with open(args.keypoints_path, "r") as f: person_kps_info = json.load(f) kps_weights = np.array(person_kps_info["kps_weights"], dtype=np.float32).reshape((args.num_joints,)) person_kps_info中没有kps_weights这个关键词

Wslnjupt

Bumps [torch](https://github.com/pytorch/pytorch) from 1.10 to 1.13.1. Release notes Sourced from torch's releases. PyTorch 1.13.1 Release, small bug fix release This release is meant to fix the following issues (regressions /...

dependabot[bot]

I tried to train Mask RCNN using my own dataset, and I have already configured the environment and run through the official Voc code, but I am unable to run...

wang1528186571

对EfficientNetB0到EfficientNetB7参数的详细定义在[EfficientNet网络详解](https://blog.csdn.net/qq_37541097/article/details/114434046)中。根据[EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://arxiv.org/pdf/1905.11946.pdf)中的公式3，可以得知在EfficientNetB7中， _r=γ^Φ=1.15^Φ=600/224=2.6786_ _Φ=log(2.6786)/log(1.15)=7.04_ 进而可以推出 _depth_coefficient=d=α^Φ=1.2^7.04=3.6094≠3.1_ 我阅读了若干个关于EfficientNet的仓库的实现代码，发现几乎所有的实现代码都对EfficientNetB7中的depth_coefficient设置为3.1，所以我不确定上述推导过程是否正确。如果错误，正确的推导过程是什么呢？

T990820

Bumps [torch](https://github.com/pytorch/pytorch) from 1.10.0 to 1.13.1. Release notes Sourced from torch's releases. PyTorch 1.13.1 Release, small bug fix release This release is meant to fix the following issues (regressions /...

dependabot[bot]

Bumps [torch](https://github.com/pytorch/pytorch) from 1.10.0 to 1.13.1. Release notes Sourced from torch's releases. PyTorch 1.13.1 Release, small bug fix release This release is meant to fix the following issues (regressions /...

dependabot[bot]

训练时lr的显示问题

2

up你好，在模型的训练过程中，lr的显示仅在warm up的过程会变化，之后就固定了。但是tensorboard中记录的lr却是正常的。是create_lr_schedule函数中的返回值的问题吗

CJ666-njust