spikezoo 0.2.1__py3-none-any.whl → 0.2.2__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -5,7 +5,7 @@ import os
5
5
  from .vidar_loader import load_vidar_dat_cpp
6
6
  from typing import Literal
7
7
 
8
- def load_vidar_dat(filename, height, width,remove_head=False, version:Literal['python','cpp'] = "cpp", out_format : Literal['array','tensor']="array",):
8
+ def load_vidar_dat(filename, height, width,remove_head=False, version:Literal['python','cpp'] = "python", out_format : Literal['array','tensor']="array",):
9
9
  """Load the spike stream from the .dat file."""
10
10
  # Spike decode
11
11
  if version == "python":
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.2
2
2
  Name: spikezoo
3
- Version: 0.2.1
3
+ Version: 0.2.2
4
4
  Summary: A deep learning toolbox for spike-to-image models.
5
5
  Home-page: https://github.com/chenkang455/Spike-Zoo
6
6
  Author: Kang Chen
@@ -36,12 +36,12 @@ Dynamic: requires-python
36
36
  Dynamic: summary
37
37
 
38
38
  <h2 align="center">
39
- <a href="">Spike-Zoo: A Toolbox for Spike-to-Image Reconstruction
39
+ <a href="">⚡Spike-Zoo: A Toolbox for Spike-to-Image Reconstruction
40
40
  </a>
41
41
  </h2>
42
42
 
43
43
  ## 📖 About
44
- Spike-Zoo is the go-to library for state-of-the-art pretrained **spike-to-image** models designed to reconstruct images from spike streams. Whether you're looking for a simple inference solution or aiming to train your own spike-to-image models, ⚡Spike-Zoo is a modular toolbox that supports both, with key features including:
44
+ ⚡Spike-Zoo is the go-to library for state-of-the-art pretrained **spike-to-image** models designed to reconstruct images from spike streams. Whether you're looking for a simple inference solution or aiming to train your own spike-to-image models, ⚡Spike-Zoo is a modular toolbox that supports both, with key features including:
45
45
 
46
46
  - Fast inference with pre-trained models.
47
47
  - Training support for custom-designed spike-to-image models.
@@ -138,22 +138,51 @@ We finish the training with one 4090 GPU in `2 minutes`, achieving `34.7dB` in P
138
138
  > 🌟 We encourage users to develop their models using our framework, with the tutorial being released soon.
139
139
 
140
140
  ### 4. Others
141
- We provide a faster `load_vidar_dat` function implemented with `cpp` (by @zeal-ye):
141
+ We provide a faster `load_vidar_dat` function implemented with `cpp` (by [@zeal-ye](https://github.com/zeal-ye)):
142
142
  ``` python
143
143
  import spikezoo as sz
144
144
  spike = sz.load_vidar_dat("data/scissor.dat",width = 400,height = 250,version='cpp')
145
145
  ```
146
146
  🚀 Results on [examples/test_load_dat.py](examples/test_load_dat.py) show that the `cpp` version is more than 10 times faster than the `python` version.
147
147
 
148
-
149
148
  ## 📅 TODO
150
149
  - [ ] Provide the tutorials.
151
150
  - [ ] Support more training settings.
152
151
  - [ ] Support more spike-based image reconstruction methods and datasets.
153
152
  - [ ] Support the overall pipeline for spike simulation.
154
153
 
154
+ ## 🤗 Supports
155
+ Run the following code to find our supported models, datasets and metrics:
156
+ ``` python
157
+ import spikezoo as sz
158
+ print(sz.get_models())
159
+ print(sz.get_datasets())
160
+ print(sz.get_metrics())
161
+ ```
162
+ **Supported Models:**
163
+ | Models | Source
164
+ | ---- | ---- |
165
+ | `tfp`,`tfi` | Spike camera and its coding methods |
166
+ | `spk2imgnet` | Spk2ImgNet: Learning to Reconstruct Dynamic Scene from Continuous Spike Stream |
167
+ | `wgse` | Learning Temporal-Ordered Representation for Spike Streams Based on Discrete Wavelet Transforms |
168
+ | `ssml` | Self-Supervised Mutual Learning for Dynamic Scene Reconstruction of Spiking Camera |
169
+ | `spikeformer` | SpikeFormer: Image Reconstruction from the Sequence of Spike Camera Based on Transformer |
170
+ | `ssir` | Spike Camera Image Reconstruction Using Deep Spiking Neural Networks |
171
+ | `bsf` | Boosting Spike Camera Image Reconstruction from a Perspective of Dealing with Spike Fluctuations |
172
+ | `stir` | Spatio-Temporal Interactive Learning for Efficient Image Reconstruction of Spiking Cameras |
173
+ | `spikeclip` | Rethinking High-speed Image Reconstruction Framework with Spike Camera |
174
+
175
+ **Supported Datasets:**
176
+ | Datasets | Source
177
+ | ---- | ---- |
178
+ | `reds_small` | Spk2ImgNet: Learning to Reconstruct Dynamic Scene from Continuous Spike Stream |
179
+ | `uhsr` | Recognizing Ultra-High-Speed Moving Objects with Bio-Inspired Spike Camera |
180
+ | `realworld` | `recVidarReal2019`,`momVidarReal2021` in [SpikeCV](https://github.com/Zyj061/SpikeCV) |
181
+ | `szdata` | SpikeReveal: Unlocking Temporal Sequences from Real Blurry Inputs with Spike Streams |
182
+
183
+
155
184
  ## ✨‍ Acknowledgment
156
- Our code is built on the open-source projects of [SpikeCV](https://spikecv.github.io/), [IQA-Pytorch](https://github.com/chaofengc/IQA-PyTorch), [BasicSR](https://github.com/XPixelGroup/BasicSR) and [NeRFStudio](https://github.com/nerfstudio-project/nerfstudio).We appreciate the effort of the contributors to these repositories. Thanks for @ruizhao26 and @Leozhangjiyuan for their help in building this project.
185
+ Our code is built on the open-source projects of [SpikeCV](https://spikecv.github.io/), [IQA-Pytorch](https://github.com/chaofengc/IQA-PyTorch), [BasicSR](https://github.com/XPixelGroup/BasicSR) and [NeRFStudio](https://github.com/nerfstudio-project/nerfstudio).We appreciate the effort of the contributors to these repositories. Thanks for [@ruizhao26](https://github.com/ruizhao26) and [@Leozhangjiyuan](https://github.com/Leozhangjiyuan) for their help in building this project.
157
186
 
158
187
  ## 📑 Citation
159
188
  If you find our codes helpful to your research, please consider to use the following citation:
@@ -202,10 +202,10 @@ spikezoo/utils/__init__.py,sha256=bYLlusAXwLCoY4s6nhVgviax9ioRA9aea8qgRmj2HpI,15
202
202
  spikezoo/utils/data_utils.py,sha256=mk1xeyIb7o_E1J7Z6-gtPq-rpKiMTxAWSTcvvPvVku8,2033
203
203
  spikezoo/utils/img_utils.py,sha256=0O9z58VzLxQEAuz-GGWCbpeHuHPOCpgBVjCBV9kf6sI,2257
204
204
  spikezoo/utils/other_utils.py,sha256=fKqs4zRxzQsIfmYZv02PZlVaGrmVEjq2KHTMrk_tBKY,2845
205
- spikezoo/utils/spike_utils.py,sha256=5pdmQUkr3Qup0kFpNGd5rPTwyut1XlJxgUnhrBx66mk,3120
205
+ spikezoo/utils/spike_utils.py,sha256=0GY1hQCOCj0HDDwjXxrHykdjTKmPdb9rC_CexpRzwdk,3123
206
206
  spikezoo/utils/vidar_loader.cpython-39-x86_64-linux-gnu.so,sha256=uXqu7ME---cZRRU5LUcLiNrjjtlOjxNwWHyTIQ10BGg,199088
207
- spikezoo-0.2.1.dist-info/LICENSE.txt,sha256=ukEi8E0PKq1dQGTXHUflg3rppLymwAhr7il9x-0nPgg,1062
208
- spikezoo-0.2.1.dist-info/METADATA,sha256=rL0LmpUASG8v-vnNa6QlpTG3-cCBhTeQFwd0fgM0DkE,6241
209
- spikezoo-0.2.1.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
210
- spikezoo-0.2.1.dist-info/top_level.txt,sha256=xF2iuOstrACJh43NW4dsTwIdgKfXPXAb_Xzl3M1ricM,9
211
- spikezoo-0.2.1.dist-info/RECORD,,
207
+ spikezoo-0.2.2.dist-info/LICENSE.txt,sha256=ukEi8E0PKq1dQGTXHUflg3rppLymwAhr7il9x-0nPgg,1062
208
+ spikezoo-0.2.2.dist-info/METADATA,sha256=j-XErZpa-tDx5wkFwwbOaHdcUjRuuGopldedu0hwEVk,7939
209
+ spikezoo-0.2.2.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
210
+ spikezoo-0.2.2.dist-info/top_level.txt,sha256=xF2iuOstrACJh43NW4dsTwIdgKfXPXAb_Xzl3M1ricM,9
211
+ spikezoo-0.2.2.dist-info/RECORD,,