deep-learning-for-image-processing

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

老师您好，为什么设置为单gpu训练时loss改变，但是多GPU训练时损失保持不变

Wang-5ying

faster rcnn和其余几个目标检测相关代码的置信度的调整在哪呢

anzhi1211

**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...

MMYY-yy

Added MultiScaleRoIPooling Module and run this config **renset50+FPN+Faster_RCNN+RoIPooling**. Keeping other parameters fixed, using `batch_size`=8 in 4 `NVIDIA GeForce RTX 3080` machine, `num_workers`=8, `momentum`=0.9, `weight_decay`=1e-4, `epochs`=100, `lr-steps`=[25, 50], Finetuning on the...

cjliu01

pytorch版本问题

1

我电脑上的pytorch版本为 torch1.8.0；torchvision0.9.0；但是pycharm界面最上方一直出现Packages requirements 'torch==1.7.1；torchvision==0.8.2 aren't satisfied'.所以我想问用高版本的torch应该可以兼容低版本pytorch吗？ ![Uploading 360截图20240611103855123.png…]()

Zhangjq7585

在云上运行FCN网络的时候使用GPU进行训练会报这个错：FileNotFoundError: [Errno 2] No such file or directory srun: error: gpu03: task 0: Exited with exit code 1

6

这是完整的报错，网上搜了，很多讲的是进程之间通信的问题，这个问题要怎么解决呀？应该在代码中修改哪些位置？ Epoch: [0] [ 0/366] eta: 0:31:04 lr: 0.000000 loss: 2.1887 (2.1887) time: 5.0952 data: 0.7384 Epoch: [0] [ 10/366] eta: 0:15:24 lr: 0.000003 loss: 0.5890 (2.3867) time: 2.5974 data:...

nanwang-crea

请问老师，如何进行可视化呢

1334233852

HRNet

3

HRNet相关问题，老师您好，请问HRNet自适应任何分辨率的图片尺寸大小吗，我自制的数据集图片尺寸大小是1280x720的，但是训练的时候出现RuntimeError: The size of tensor a (180) must match the size of tensor b (184) at non-singleton dimension 3，是不是720这个维度在stage4里面做下采样的时候一直到45的时候再下采样就除不尽的，不知道是不是这个原因，老师可否有高见！谢谢！

1334233852

Bumps [tqdm](https://github.com/tqdm/tqdm) from 4.56.0 to 4.66.3. Release notes Sourced from tqdm's releases. tqdm v4.66.3 stable cli: eval safety (fixes CVE-2024-34062, GHSA-g7vv-2v7x-gj9p) tqdm v4.66.2 stable pandas: add DataFrame.progress_map (#1549) notebook: fix...

dependabot[bot]

Bumps [tqdm](https://github.com/tqdm/tqdm) from 4.42.1 to 4.66.3. Release notes Sourced from tqdm's releases. tqdm v4.66.3 stable cli: eval safety (fixes CVE-2024-34062, GHSA-g7vv-2v7x-gj9p) tqdm v4.66.2 stable pandas: add DataFrame.progress_map (#1549) notebook: fix...

dependabot[bot]