Lextal/pspnet-pytorch 排名第 16,448，有 590 个星标。
同类别比较
Lextal/pspnet-pytorch 排名第 16,448，此处有 8 个同类条目；Shimingyi/MotioNet 排名第 16,449。
同类别比较| 名称 | 排名 | 指标 |
|---|
| curiousily/Credit-Card-Fraud-Detection-using-Autoencoders-in-Keras | 16,437 | - 语言:
- Jupyter Notebook
- 星标数:
- 591
- 分叉数:
- 288
- 简介:
- iPython notebook and pre-trained model that shows how to build deep Autoencoder in Keras for Anomaly Detection in credit card transactions data
|
|---|
| hwwang55/RippleNet | 16,439 | - 语言:
- Python
- 星标数:
- 591
- 分叉数:
- 209
- 简介:
- A tensorflow implementation of RippleNet
|
|---|
| mahmoudnafifi/Exposure_Correction | 16,441 | - 语言:
- MATLAB
- 星标数:
- 591
- 分叉数:
- 70
- 简介:
- Project page of the paper "Learning Multi-Scale Photo Exposure Correction" (CVPR 2021).
|
|---|
| szagoruyko/diracnets | 16,445 | - 语言:
- Jupyter Notebook
- 星标数:
- 591
- 分叉数:
- 73
- 简介:
- Training Very Deep Neural Networks Without Skip-Connections
|
|---|
| Shimingyi/MotioNet | 16,449 | - 语言:
- Python
- 星标数:
- 590
- 分叉数:
- 83
- 简介:
- A deep neural network that directly reconstructs the motion of a 3D human skeleton from monocular video [ToG 2020]
|
|---|
| epfLLM/Megatron-LLM | 16,454 | - 语言:
- Python
- 星标数:
- 590
- 分叉数:
- 87
- 简介:
- distributed trainer for LLMs
|
|---|
| openai/mujoco-worldgen | 16,459 | - 语言:
- Python
- 星标数:
- 590
- 分叉数:
- 119
- 简介:
- Automatic object XML generation for Mujoco
|
|---|
| abduallahmohamed/Social-STGCNN | 16,467 | - 语言:
- Python
- 星标数:
- 589
- 分叉数:
- 146
- 简介:
- Code for "Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction" CVPR 2020
|
|---|
关键参数与规格
关键参数与规格| 参数 | 值 |
|---|
| 语言 | Python |
|---|
| 类别 | Model Development |
|---|
| 子类别 | Architecture |
|---|
| 关键词 | Computer vision |
|---|
| 星标数 | 590 |
|---|
| 分叉数 | 117 |
|---|
| 贡献者 | 1 |
|---|
| 创建日期 | 2017-09-15 |
|---|
| 更新日期 | 2026-10-06 |
|---|
| 1 天星标数 | 0 |
|---|
| 7 天星标数 | 0 |
|---|
| 排名 | 16,448 |
|---|
| 上次排名 | 16,238 |
|---|
| 排名变化 | -210 |
|---|
| 7 天星标排名 | 15,533 |
|---|
| 上次 7 天星标排名 | 15,543 |
|---|
| 7 天星标排名变化 | 10 |
|---|
| 总星标排名 | 16,984 |
|---|
| 上次总星标排名 | 16,963 |
|---|
| 总星标排名变化 | -21 |
|---|
| 国家 | USA |
|---|
README 摘录
pspnet-pytorch PyTorch implementation of PSPNet segmentation network Original paper Pyramid Scene Parsing Network Details This is a slightly different version - instead of direct 8x upsampling at the end I use three consequitive upsamplings for stability. Feature extraction Using pretrained weights for extractors - improved quality and convergence dramatically. Currently supported: SqueezeNet DenseNet-121 ResNet-18 ResNet-34 ResNet-50 ResNet-101 ResNet-152 Planned: DenseNet-169 DenseNet-201 Usage To follow the training routine in train. py you need a
DataLoader that yields the tuples of the following format: (Bx3xHxW FloatTensor x, BxHxW LongTensor y, BxN LongTensor y\_cls) where x - batch of input images, y - batch of groung truth seg maps, y\_cls - batch of 1D tensors of dimensionality N: N total number of classes, y\_cls[i, T] = 1 if class T is present in image i, 0 otherwise
常见问题
记录了多少星标和分叉？
Lextal/pspnet-pytorch 有 590 个星标和 117 个分叉。
仓库排名是多少？
Lextal/pspnet-pytorch 排名第 16,448。
记录的语言和类别是什么？
Lextal/pspnet-pytorch 有 590 个星标，语言为 Python，类别为 Model Development。
哪个仓库排名最接近？
Lextal/pspnet-pytorch 与 Shimingyi/MotioNet 比较，后者排名第 16,449，有 590 个星标。
pspnet-pytorch
PyTorch implementation of PSPNet segmentation network
Original paper
Pyramid Scene Parsing Network
Details
This is a slightly different version - instead of direct 8x upsampling at the end I use three consequitive upsamplings for stability.
Feature extraction
Using pretrained weights for extractors - improved quality and convergence dramatically.
Currently supported:
- SqueezeNet
- DenseNet-121
- ResNet-18
- ResNet-34
- ResNet-50
- ResNet-101
- ResNet-152
Planned:
- DenseNet-169
- DenseNet-201
Usage
To follow the training routine in train.py you need a DataLoader that yields the tuples of the following format:
(Bx3xHxW FloatTensor x, BxHxW LongTensor y, BxN LongTensor y_cls) where
x - batch of input images,
y - batch of groung truth seg maps,
y_cls - batch of 1D tensors of dimensionality N: N total number of classes,
y_cls[i, T] = 1 if class T is present in image i, 0 otherwise