Skip to content

Commit

Permalink
deploy: 65a0b4f
Browse files Browse the repository at this point in the history
  • Loading branch information
@fracape
fracape committed Dec 8, 2023
1 parent ef3e4fb commit 8bb31d8
Show file tree
Hide file tree
Showing 20 changed files with 934 additions and 934 deletions.
2 changes: 1 addition & 1 deletion tutorials/cli_tutorial_2.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -799,7 +799,7 @@ <h1>2. Registering Datasets<a class="headerlink" href="#registering-datasets" ti
</pre></div>
</div>
<p>Let’s remove the image data as well:</p>
<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span>rm -rf /tmp/my_data_set
<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="n">rm</span> <span class="o">-</span><span class="n">rf</span> <span class="o">/</span><span class="n">tmp</span><span class="o">/</span><span class="n">my_data_set</span>
</pre></div>
</div>
<p>A final note/observation before moving to the next tutorial.</p>
Expand Down
2 changes: 1 addition & 1 deletion tutorials/cli_tutorial_2_nb.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -805,7 +805,7 @@ <h2> Contents </h2>
</pre></div>
</div>
<p>Let’s remove the image data as well:</p>
<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span>rm -rf /tmp/my_data_set
<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="n">rm</span> <span class="o">-</span><span class="n">rf</span> <span class="o">/</span><span class="n">tmp</span><span class="o">/</span><span class="n">my_data_set</span>
</pre></div>
</div>
<p>A final note/observation before moving to the next tutorial.</p>
Expand Down
2 changes: 1 addition & 1 deletion tutorials/cli_tutorial_3.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -364,7 +364,7 @@ <h1>3. MPEG-VCM Evaluation<a class="headerlink" href="#mpeg-vcm-evaluation" titl
<li><p><code class="docutils literal notranslate"><span class="pre">oiv6-mpeg-detection-v1</span></code></p></li>
<li><p><code class="docutils literal notranslate"><span class="pre">oiv6-mpeg-segmentation-v1</span></code></p></li>
</ul>
<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span>compressai-vision list
<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="n">compressai</span><span class="o">-</span><span class="n">vision</span> <span class="nb">list</span>
</pre></div>
</div>
<div class="highlight-text notranslate"><div class="highlight"><pre><span></span>importing fiftyone
Expand Down
2 changes: 1 addition & 1 deletion tutorials/cli_tutorial_3_nb.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -370,7 +370,7 @@ <h2> Contents </h2>
<li><p><code class="docutils literal notranslate"><span class="pre">oiv6-mpeg-detection-v1</span></code></p></li>
<li><p><code class="docutils literal notranslate"><span class="pre">oiv6-mpeg-segmentation-v1</span></code></p></li>
</ul>
<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span>compressai-vision list
<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="n">compressai</span><span class="o">-</span><span class="n">vision</span> <span class="nb">list</span>
</pre></div>
</div>
<div class="highlight-text notranslate"><div class="highlight"><pre><span></span>importing fiftyone
Expand Down
78 changes: 39 additions & 39 deletions tutorials/cli_tutorial_6.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -362,15 +362,15 @@ <h1>6. VTM benchmark generation<a class="headerlink" href="#vtm-benchmark-genera
use the <code class="docutils literal notranslate"><span class="pre">vtm</span></code> subcommand to manage, encode and cache the VTM produced
bitstreams on disk.</p>
<p>Let’s generate some encoded bitstreams.</p>
<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span>compressai-vision vtm --y --dataset-name=oiv6-mpeg-detection-v1 \
--slice=0:2 \
--scale=100 \
--progress=1 \
--qpars=47 \
--vtm_cache=/tmp/bitstreams \
--vtm_dir={path_to_vtm_software}/bin \
--vtm_cfg={path_to_vtm_software}/cfg/encoder_intra_vtm.cfg \
--output=vtm_out.json
<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="n">compressai</span><span class="o">-</span><span class="n">vision</span> <span class="n">vtm</span> <span class="o">--</span><span class="n">y</span> <span class="o">--</span><span class="n">dataset</span><span class="o">-</span><span class="n">name</span><span class="o">=</span><span class="n">oiv6</span><span class="o">-</span><span class="n">mpeg</span><span class="o">-</span><span class="n">detection</span><span class="o">-</span><span class="n">v1</span> \
<span class="o">--</span><span class="nb">slice</span><span class="o">=</span><span class="mi">0</span><span class="p">:</span><span class="mi">2</span> \
<span class="o">--</span><span class="n">scale</span><span class="o">=</span><span class="mi">100</span> \
<span class="o">--</span><span class="n">progress</span><span class="o">=</span><span class="mi">1</span> \
<span class="o">--</span><span class="n">qpars</span><span class="o">=</span><span class="mi">47</span> \
<span class="o">--</span><span class="n">vtm_cache</span><span class="o">=/</span><span class="n">tmp</span><span class="o">/</span><span class="n">bitstreams</span> \
<span class="o">--</span><span class="n">vtm_dir</span><span class="o">=</span><span class="p">{</span><span class="n">path_to_vtm_software</span><span class="p">}</span><span class="o">/</span><span class="nb">bin</span> \
<span class="o">--</span><span class="n">vtm_cfg</span><span class="o">=</span><span class="p">{</span><span class="n">path_to_vtm_software</span><span class="p">}</span><span class="o">/</span><span class="n">cfg</span><span class="o">/</span><span class="n">encoder_intra_vtm</span><span class="o">.</span><span class="n">cfg</span> \
<span class="o">--</span><span class="n">output</span><span class="o">=</span><span class="n">vtm_out</span><span class="o">.</span><span class="n">json</span>
</pre></div>
</div>
<div class="highlight-text notranslate"><div class="highlight"><pre><span></span>importing fiftyone
Expand Down Expand Up @@ -403,15 +403,15 @@ <h1>6. VTM benchmark generation<a class="headerlink" href="#vtm-benchmark-genera
<p>As you can see, bitstreams we’re generated and cached into
<code class="docutils literal notranslate"><span class="pre">/tmp/bitstreams/SCALE/QP</span></code>. Let’s see what happens if we run the exact
same command again:</p>
<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span>compressai-vision vtm --y --dataset-name=oiv6-mpeg-detection-v1 \
--slice=0:2 \
--scale=100 \
--progress=1 \
--qpars=47 \
--vtm_cache=/tmp/bitstreams \
--vtm_dir={path_to_vtm_software}/bin \
--vtm_cfg={path_to_vtm_software}/cfg/encoder_intra_vtm.cfg \
--output=vtm_out.json
<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="n">compressai</span><span class="o">-</span><span class="n">vision</span> <span class="n">vtm</span> <span class="o">--</span><span class="n">y</span> <span class="o">--</span><span class="n">dataset</span><span class="o">-</span><span class="n">name</span><span class="o">=</span><span class="n">oiv6</span><span class="o">-</span><span class="n">mpeg</span><span class="o">-</span><span class="n">detection</span><span class="o">-</span><span class="n">v1</span> \
<span class="o">--</span><span class="nb">slice</span><span class="o">=</span><span class="mi">0</span><span class="p">:</span><span class="mi">2</span> \
<span class="o">--</span><span class="n">scale</span><span class="o">=</span><span class="mi">100</span> \
<span class="o">--</span><span class="n">progress</span><span class="o">=</span><span class="mi">1</span> \
<span class="o">--</span><span class="n">qpars</span><span class="o">=</span><span class="mi">47</span> \
<span class="o">--</span><span class="n">vtm_cache</span><span class="o">=/</span><span class="n">tmp</span><span class="o">/</span><span class="n">bitstreams</span> \
<span class="o">--</span><span class="n">vtm_dir</span><span class="o">=</span><span class="p">{</span><span class="n">path_to_vtm_software</span><span class="p">}</span><span class="o">/</span><span class="nb">bin</span> \
<span class="o">--</span><span class="n">vtm_cfg</span><span class="o">=</span><span class="p">{</span><span class="n">path_to_vtm_software</span><span class="p">}</span><span class="o">/</span><span class="n">cfg</span><span class="o">/</span><span class="n">encoder_intra_vtm</span><span class="o">.</span><span class="n">cfg</span> \
<span class="o">--</span><span class="n">output</span><span class="o">=</span><span class="n">vtm_out</span><span class="o">.</span><span class="n">json</span>
</pre></div>
</div>
<div class="highlight-text notranslate"><div class="highlight"><pre><span></span>importing fiftyone
Expand Down Expand Up @@ -442,19 +442,19 @@ <h1>6. VTM benchmark generation<a class="headerlink" href="#vtm-benchmark-genera
<p>Instead of generating the bitstreams, the program found them cached on
the disk and just verified them.</p>
<p>Let’s fool around and corrupt one of the bitstreams:</p>
<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span>echo &quot; &quot; &gt; /tmp/bitstreams/100/47/bin_000a1249af2bc5f0
<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="n">echo</span> <span class="s2">&quot; &quot;</span> <span class="o">&gt;</span> <span class="o">/</span><span class="n">tmp</span><span class="o">/</span><span class="n">bitstreams</span><span class="o">/</span><span class="mi">100</span><span class="o">/</span><span class="mi">47</span><span class="o">/</span><span class="n">bin_000a1249af2bc5f0</span>
</pre></div>
</div>
<p>And run the command again:</p>
<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span>compressai-vision vtm --y --dataset-name=oiv6-mpeg-detection-v1 \
--slice=0:2 \
--scale=100 \
--progress=1 \
--qpars=47 \
--vtm_cache=/tmp/bitstreams \
--vtm_dir={path_to_vtm_software}/bin \
--vtm_cfg={path_to_vtm_software}/cfg/encoder_intra_vtm.cfg \
--output=vtm_out.json
<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="n">compressai</span><span class="o">-</span><span class="n">vision</span> <span class="n">vtm</span> <span class="o">--</span><span class="n">y</span> <span class="o">--</span><span class="n">dataset</span><span class="o">-</span><span class="n">name</span><span class="o">=</span><span class="n">oiv6</span><span class="o">-</span><span class="n">mpeg</span><span class="o">-</span><span class="n">detection</span><span class="o">-</span><span class="n">v1</span> \
<span class="o">--</span><span class="nb">slice</span><span class="o">=</span><span class="mi">0</span><span class="p">:</span><span class="mi">2</span> \
<span class="o">--</span><span class="n">scale</span><span class="o">=</span><span class="mi">100</span> \
<span class="o">--</span><span class="n">progress</span><span class="o">=</span><span class="mi">1</span> \
<span class="o">--</span><span class="n">qpars</span><span class="o">=</span><span class="mi">47</span> \
<span class="o">--</span><span class="n">vtm_cache</span><span class="o">=/</span><span class="n">tmp</span><span class="o">/</span><span class="n">bitstreams</span> \
<span class="o">--</span><span class="n">vtm_dir</span><span class="o">=</span><span class="p">{</span><span class="n">path_to_vtm_software</span><span class="p">}</span><span class="o">/</span><span class="nb">bin</span> \
<span class="o">--</span><span class="n">vtm_cfg</span><span class="o">=</span><span class="p">{</span><span class="n">path_to_vtm_software</span><span class="p">}</span><span class="o">/</span><span class="n">cfg</span><span class="o">/</span><span class="n">encoder_intra_vtm</span><span class="o">.</span><span class="n">cfg</span> \
<span class="o">--</span><span class="n">output</span><span class="o">=</span><span class="n">vtm_out</span><span class="o">.</span><span class="n">json</span>
</pre></div>
</div>
<div class="highlight-text notranslate"><div class="highlight"><pre><span></span>importing fiftyone
Expand Down Expand Up @@ -493,17 +493,17 @@ <h1>6. VTM benchmark generation<a class="headerlink" href="#vtm-benchmark-genera
of crashes / data corruption, you can just send the same scripts into
your queue system over and over again if necessary.</p>
<p>Finally, you can run <code class="docutils literal notranslate"><span class="pre">detectron2-eval</span></code> for the VTM case like this:</p>
<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span>compressai-vision detectron2-eval --y --dataset-name=oiv6-mpeg-detection-v1 \
--slice=0:2 \
--scale=100 \
--progress=1 \
--qpars=47 \
--vtm \
--vtm_cache=/tmp/bitstreams \
--vtm_dir={path_to_vtm_software}/bin \
--vtm_cfg={path_to_vtm_software}/cfg/encoder_intra_vtm.cfg \
--output=detectron2_vtm.json \
--model=COCO-Detection/faster_rcnn_X_101_32x8d_FPN_3x.yaml
<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="n">compressai</span><span class="o">-</span><span class="n">vision</span> <span class="n">detectron2</span><span class="o">-</span><span class="nb">eval</span> <span class="o">--</span><span class="n">y</span> <span class="o">--</span><span class="n">dataset</span><span class="o">-</span><span class="n">name</span><span class="o">=</span><span class="n">oiv6</span><span class="o">-</span><span class="n">mpeg</span><span class="o">-</span><span class="n">detection</span><span class="o">-</span><span class="n">v1</span> \
<span class="o">--</span><span class="nb">slice</span><span class="o">=</span><span class="mi">0</span><span class="p">:</span><span class="mi">2</span> \
<span class="o">--</span><span class="n">scale</span><span class="o">=</span><span class="mi">100</span> \
<span class="o">--</span><span class="n">progress</span><span class="o">=</span><span class="mi">1</span> \
<span class="o">--</span><span class="n">qpars</span><span class="o">=</span><span class="mi">47</span> \
<span class="o">--</span><span class="n">vtm</span> \
<span class="o">--</span><span class="n">vtm_cache</span><span class="o">=/</span><span class="n">tmp</span><span class="o">/</span><span class="n">bitstreams</span> \
<span class="o">--</span><span class="n">vtm_dir</span><span class="o">=</span><span class="p">{</span><span class="n">path_to_vtm_software</span><span class="p">}</span><span class="o">/</span><span class="nb">bin</span> \
<span class="o">--</span><span class="n">vtm_cfg</span><span class="o">=</span><span class="p">{</span><span class="n">path_to_vtm_software</span><span class="p">}</span><span class="o">/</span><span class="n">cfg</span><span class="o">/</span><span class="n">encoder_intra_vtm</span><span class="o">.</span><span class="n">cfg</span> \
<span class="o">--</span><span class="n">output</span><span class="o">=</span><span class="n">detectron2_vtm</span><span class="o">.</span><span class="n">json</span> \
<span class="o">--</span><span class="n">model</span><span class="o">=</span><span class="n">COCO</span><span class="o">-</span><span class="n">Detection</span><span class="o">/</span><span class="n">faster_rcnn_X_101_32x8d_FPN_3x</span><span class="o">.</span><span class="n">yaml</span>
</pre></div>
</div>
<div class="highlight-text notranslate"><div class="highlight"><pre><span></span>importing fiftyone
Expand Down
Loading

0 comments on commit 8bb31d8

Please sign in to comment.