mirrors
/
deep-person-reid
mirror of https://github.com/KaiyangZhou/deep-person-reid.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

update doc

gh-pages
kaiyangzhou 2021-08-11 17:00:39 +08:00
parent b4420d2d53
commit 45c4589e3d
7 changed files with 90 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
MODEL_ZOO.html
View File

@ -240,6 +240,18 @@
<td align="left">osnet_ain_x1_0</td>
<td align="center"><a href="https://drive.google.com/file/d/1-CaioD9NaqbHK_kzSMW8VE4_3KcsRjEo/view?usp=sharing">model</a></td>
</tr>
<tr>
<td align="left">osnet_ain_x0_75</td>
<td align="center"><a href="https://drive.google.com/file/d/1apy0hpsMypqstfencdH-jKIUEFOW4xoM/view?usp=sharing">model</a></td>
</tr>
<tr>
<td align="left">osnet_ain_x0_5</td>
<td align="center"><a href="https://drive.google.com/file/d/1KusKvEYyKGDTUBVRxRiz55G31wkihB6l/view?usp=sharing">model</a></td>
</tr>
<tr>
<td align="left">osnet_ain_x0_25</td>
<td align="center"><a href="https://drive.google.com/file/d/1SxQt2AvmEcgWNhaRb2xC4rP6ZwVDP0Wt/view?usp=sharing">model</a></td>
</tr>
</tbody>
</table></div>
<div class="section" id="same-domain-reid">

5
_modules/torchreid/models/__init__.html
View File

@ -241,7 +241,10 @@
<span class="s1">&#39;osnet_x0_5&#39;</span><span class="p">:</span> <span class="n">osnet_x0_5</span><span class="p">,</span>
<span class="s1">&#39;osnet_x0_25&#39;</span><span class="p">:</span> <span class="n">osnet_x0_25</span><span class="p">,</span>
<span class="s1">&#39;osnet_ibn_x1_0&#39;</span><span class="p">:</span> <span class="n">osnet_ibn_x1_0</span><span class="p">,</span>
<span class="s1">&#39;osnet_ain_x1_0&#39;</span><span class="p">:</span> <span class="n">osnet_ain_x1_0</span>
<span class="s1">&#39;osnet_ain_x1_0&#39;</span><span class="p">:</span> <span class="n">osnet_ain_x1_0</span><span class="p">,</span>
<span class="s1">&#39;osnet_ain_x0_75&#39;</span><span class="p">:</span> <span class="n">osnet_ain_x0_75</span><span class="p">,</span>
<span class="s1">&#39;osnet_ain_x0_5&#39;</span><span class="p">:</span> <span class="n">osnet_ain_x0_5</span><span class="p">,</span>
<span class="s1">&#39;osnet_ain_x0_25&#39;</span><span class="p">:</span> <span class="n">osnet_ain_x0_25</span>
<span class="p">}</span>

70
_modules/torchreid/models/osnet_ain.html
View File

@ -174,11 +174,17 @@
<span class="kn">from</span> <span class="nn">torch</span> <span class="kn">import</span> <span class="n">nn</span>
<span class="kn">from</span> <span class="nn">torch.nn</span> <span class="kn">import</span> <span class="n">functional</span> <span class="k">as</span> <span class="n">F</span>
<span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span><span class="s1">&#39;osnet_ain_x1_0&#39;</span><span class="p">]</span>
<span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span><span class="s1">&#39;osnet_ain_x1_0&#39;</span><span class="p">,</span> <span class="s1">&#39;osnet_ain_x0_75&#39;</span><span class="p">,</span> <span class="s1">&#39;osnet_ain_x0_5&#39;</span><span class="p">,</span> <span class="s1">&#39;osnet_ain_x0_25&#39;</span><span class="p">]</span>
<span class="n">pretrained_urls</span> <span class="o">=</span> <span class="p">{</span>
<span class="s1">&#39;osnet_ain_x1_0&#39;</span><span class="p">:</span>
<span class="s1">&#39;https://drive.google.com/uc?id=1-CaioD9NaqbHK_kzSMW8VE4_3KcsRjEo&#39;</span>
<span class="s1">&#39;https://drive.google.com/uc?id=1-CaioD9NaqbHK_kzSMW8VE4_3KcsRjEo&#39;</span><span class="p">,</span>
<span class="s1">&#39;osnet_ain_x0_75&#39;</span><span class="p">:</span>
<span class="s1">&#39;https://drive.google.com/uc?id=1apy0hpsMypqstfencdH-jKIUEFOW4xoM&#39;</span><span class="p">,</span>
<span class="s1">&#39;osnet_ain_x0_5&#39;</span><span class="p">:</span>
<span class="s1">&#39;https://drive.google.com/uc?id=1KusKvEYyKGDTUBVRxRiz55G31wkihB6l&#39;</span><span class="p">,</span>
<span class="s1">&#39;osnet_ain_x0_25&#39;</span><span class="p">:</span>
<span class="s1">&#39;https://drive.google.com/uc?id=1SxQt2AvmEcgWNhaRb2xC4rP6ZwVDP0Wt&#39;</span>
<span class="p">}</span>
@ -709,6 +715,66 @@
<span class="k">if</span> <span class="n">pretrained</span><span class="p">:</span>
<span class="n">init_pretrained_weights</span><span class="p">(</span><span class="n">model</span><span class="p">,</span> <span class="n">key</span><span class="o">=</span><span class="s1">&#39;osnet_ain_x1_0&#39;</span><span class="p">)</span>
<span class="k">return</span> <span class="n">model</span>
<span class="k">def</span> <span class="nf">osnet_ain_x0_75</span><span class="p">(</span>
<span class="n">num_classes</span><span class="o">=</span><span class="mi">1000</span><span class="p">,</span> <span class="n">pretrained</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">loss</span><span class="o">=</span><span class="s1">&#39;softmax&#39;</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span>
<span class="p">):</span>
<span class="n">model</span> <span class="o">=</span> <span class="n">OSNet</span><span class="p">(</span>
<span class="n">num_classes</span><span class="p">,</span>
<span class="n">blocks</span><span class="o">=</span><span class="p">[</span>
<span class="p">[</span><span class="n">OSBlockINin</span><span class="p">,</span> <span class="n">OSBlockINin</span><span class="p">],</span> <span class="p">[</span><span class="n">OSBlock</span><span class="p">,</span> <span class="n">OSBlockINin</span><span class="p">],</span>
<span class="p">[</span><span class="n">OSBlockINin</span><span class="p">,</span> <span class="n">OSBlock</span><span class="p">]</span>
<span class="p">],</span>
<span class="n">layers</span><span class="o">=</span><span class="p">[</span><span class="mi">2</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">2</span><span class="p">],</span>
<span class="n">channels</span><span class="o">=</span><span class="p">[</span><span class="mi">48</span><span class="p">,</span> <span class="mi">192</span><span class="p">,</span> <span class="mi">288</span><span class="p">,</span> <span class="mi">384</span><span class="p">],</span>
<span class="n">loss</span><span class="o">=</span><span class="n">loss</span><span class="p">,</span>
<span class="n">conv1_IN</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
<span class="o">**</span><span class="n">kwargs</span>
<span class="p">)</span>
<span class="k">if</span> <span class="n">pretrained</span><span class="p">:</span>
<span class="n">init_pretrained_weights</span><span class="p">(</span><span class="n">model</span><span class="p">,</span> <span class="n">key</span><span class="o">=</span><span class="s1">&#39;osnet_ain_x0_75&#39;</span><span class="p">)</span>
<span class="k">return</span> <span class="n">model</span>
<span class="k">def</span> <span class="nf">osnet_ain_x0_5</span><span class="p">(</span>
<span class="n">num_classes</span><span class="o">=</span><span class="mi">1000</span><span class="p">,</span> <span class="n">pretrained</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">loss</span><span class="o">=</span><span class="s1">&#39;softmax&#39;</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span>
<span class="p">):</span>
<span class="n">model</span> <span class="o">=</span> <span class="n">OSNet</span><span class="p">(</span>
<span class="n">num_classes</span><span class="p">,</span>
<span class="n">blocks</span><span class="o">=</span><span class="p">[</span>
<span class="p">[</span><span class="n">OSBlockINin</span><span class="p">,</span> <span class="n">OSBlockINin</span><span class="p">],</span> <span class="p">[</span><span class="n">OSBlock</span><span class="p">,</span> <span class="n">OSBlockINin</span><span class="p">],</span>
<span class="p">[</span><span class="n">OSBlockINin</span><span class="p">,</span> <span class="n">OSBlock</span><span class="p">]</span>
<span class="p">],</span>
<span class="n">layers</span><span class="o">=</span><span class="p">[</span><span class="mi">2</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">2</span><span class="p">],</span>
<span class="n">channels</span><span class="o">=</span><span class="p">[</span><span class="mi">32</span><span class="p">,</span> <span class="mi">128</span><span class="p">,</span> <span class="mi">192</span><span class="p">,</span> <span class="mi">256</span><span class="p">],</span>
<span class="n">loss</span><span class="o">=</span><span class="n">loss</span><span class="p">,</span>
<span class="n">conv1_IN</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
<span class="o">**</span><span class="n">kwargs</span>
<span class="p">)</span>
<span class="k">if</span> <span class="n">pretrained</span><span class="p">:</span>
<span class="n">init_pretrained_weights</span><span class="p">(</span><span class="n">model</span><span class="p">,</span> <span class="n">key</span><span class="o">=</span><span class="s1">&#39;osnet_ain_x0_5&#39;</span><span class="p">)</span>
<span class="k">return</span> <span class="n">model</span>
<span class="k">def</span> <span class="nf">osnet_ain_x0_25</span><span class="p">(</span>
<span class="n">num_classes</span><span class="o">=</span><span class="mi">1000</span><span class="p">,</span> <span class="n">pretrained</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">loss</span><span class="o">=</span><span class="s1">&#39;softmax&#39;</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span>
<span class="p">):</span>
<span class="n">model</span> <span class="o">=</span> <span class="n">OSNet</span><span class="p">(</span>
<span class="n">num_classes</span><span class="p">,</span>
<span class="n">blocks</span><span class="o">=</span><span class="p">[</span>
<span class="p">[</span><span class="n">OSBlockINin</span><span class="p">,</span> <span class="n">OSBlockINin</span><span class="p">],</span> <span class="p">[</span><span class="n">OSBlock</span><span class="p">,</span> <span class="n">OSBlockINin</span><span class="p">],</span>
<span class="p">[</span><span class="n">OSBlockINin</span><span class="p">,</span> <span class="n">OSBlock</span><span class="p">]</span>
<span class="p">],</span>
<span class="n">layers</span><span class="o">=</span><span class="p">[</span><span class="mi">2</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">2</span><span class="p">],</span>
<span class="n">channels</span><span class="o">=</span><span class="p">[</span><span class="mi">16</span><span class="p">,</span> <span class="mi">64</span><span class="p">,</span> <span class="mi">96</span><span class="p">,</span> <span class="mi">128</span><span class="p">],</span>
<span class="n">loss</span><span class="o">=</span><span class="n">loss</span><span class="p">,</span>
<span class="n">conv1_IN</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
<span class="o">**</span><span class="n">kwargs</span>
<span class="p">)</span>
<span class="k">if</span> <span class="n">pretrained</span><span class="p">:</span>
<span class="n">init_pretrained_weights</span><span class="p">(</span><span class="n">model</span><span class="p">,</span> <span class="n">key</span><span class="o">=</span><span class="s1">&#39;osnet_ain_x0_25&#39;</span><span class="p">)</span>
<span class="k">return</span> <span class="n">model</span>
</pre></div>
</div>

1
_modules/torchreid/utils/torchtools.html
View File

@ -247,6 +247,7 @@
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">if</span> <span class="n">fpath</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">&#39;File path is None&#39;</span><span class="p">)</span>
<span class="n">fpath</span> <span class="o">=</span> <span class="n">osp</span><span class="o">.</span><span class="n">abspath</span><span class="p">(</span><span class="n">osp</span><span class="o">.</span><span class="n">expanduser</span><span class="p">(</span><span class="n">fpath</span><span class="p">))</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">osp</span><span class="o">.</span><span class="n">exists</span><span class="p">(</span><span class="n">fpath</span><span class="p">):</span>
<span class="k">raise</span> <span class="ne">FileNotFoundError</span><span class="p">(</span><span class="s1">&#39;File is not found at &quot;</span><span class="si">{}</span><span class="s1">&quot;&#39;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">fpath</span><span class="p">))</span>
<span class="n">map_location</span> <span class="o">=</span> <span class="kc">None</span> <span class="k">if</span> <span class="n">torch</span><span class="o">.</span><span class="n">cuda</span><span class="o">.</span><span class="n">is_available</span><span class="p">()</span> <span class="k">else</span> <span class="s1">&#39;cpu&#39;</span>

3
_sources/MODEL_ZOO.md.txt
View File

@ -22,6 +22,9 @@
| osnet_x0_25 | [model](https://drive.google.com/file/d/1rb8UN5ZzPKRc_xvtHlyDh-cSz88YX9hs/view?usp=sharing) |
| osnet_ibn_x1_0 | [model](https://drive.google.com/file/d/1sr90V6irlYYDd4_4ISU2iruoRG8J__6l/view?usp=sharing) |
| osnet_ain_x1_0 | [model](https://drive.google.com/file/d/1-CaioD9NaqbHK_kzSMW8VE4_3KcsRjEo/view?usp=sharing) |
| osnet_ain_x0_75 | [model](https://drive.google.com/file/d/1apy0hpsMypqstfencdH-jKIUEFOW4xoM/view?usp=sharing) |
| osnet_ain_x0_5 | [model](https://drive.google.com/file/d/1KusKvEYyKGDTUBVRxRiz55G31wkihB6l/view?usp=sharing) |
| osnet_ain_x0_25 | [model](https://drive.google.com/file/d/1SxQt2AvmEcgWNhaRb2xC4rP6ZwVDP0Wt/view?usp=sharing) |
## Same-domain ReID

1
index.html
View File

@ -197,6 +197,7 @@
<div class="section" id="what-s-new">
<h2>What’s new<a class="headerlink" href="#what-s-new" title="Permalink to this headline"></a></h2>
<ul class="simple">
<li><p>[Aug 2021] We have released the ImageNet-pretrained models of <code class="docutils literal notranslate"><span class="pre">osnet_ain_x0_75</span></code>, <code class="docutils literal notranslate"><span class="pre">osnet_ain_x0_5</span></code> and <code class="docutils literal notranslate"><span class="pre">osnet_ain_x0_25</span></code>. The pretraining setup follows <a class="reference external" href="https://github.com/facebookresearch/pycls/blob/master/configs/archive/imagenet/resnet/R-50-1x64d_step_8gpu.yaml">pycls</a>.</p></li>
<li><p>[Apr 2021] We have updated the appendix in the <a class="reference external" href="https://arxiv.org/abs/1910.06827v5">TPAMI version of OSNet</a> to include results in the multi-source domain generalization setting. The trained models can be found in the <a class="reference external" href="https://kaiyangzhou.github.io/deep-person-reid/MODEL_ZOO.html">Model Zoo</a>.</p></li>
<li><p>[Apr 2021] We have added a script to automate the process of calculating average results over multiple splits. For more details please see <code class="docutils literal notranslate"><span class="pre">tools/parse_test_res.py</span></code>.</p></li>
<li><p>[Apr 2021] <code class="docutils literal notranslate"><span class="pre">v1.4.0</span></code>: We added the person search dataset, <a class="reference external" href="http://www.ee.cuhk.edu.hk/~xgwang/PS/dataset.html">CUHK-SYSU</a>. Please see the <a class="reference external" href="https://kaiyangzhou.github.io/deep-person-reid/">documentation</a> regarding how to download the dataset (it contains cropped person images).</p></li>

2
searchindex.js
View File

File diff suppressed because one or more lines are too long