deploy: SimplexLab/TorchJD@6c71230

Author: ValerianRey

latest/docs/autojac/backward/index.html

@@ -303,9 +303,9 @@ <h1>backward<a class="headerlink" href="#backward" title="Link to this heading">
 <dt class="field-odd">Parameters<span class="colon">:</span></dt>
 <dd class="field-odd"><ul class="simple">
 <li><p><strong>tensors</strong> (<span class="sphinx_autodoc_typehints-type"><a class="reference external" href="https://docs.python.org/3/library/collections.abc.html#collections.abc.Sequence" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">Sequence</span></code></a>[<a class="reference external" href="https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor" title="(in PyTorch v2.10)"><code class="xref py py-class docutils literal notranslate"><span class="pre">Tensor</span></code></a>] | <a class="reference external" href="https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor" title="(in PyTorch v2.10)"><code class="xref py py-class docutils literal notranslate"><span class="pre">Tensor</span></code></a></span>) – The tensor or tensors to differentiate. Should be non-empty.</p></li>
-<li><p><strong>jac_tensors</strong> (<span class="sphinx_autodoc_typehints-type"><a class="reference external" href="https://docs.python.org/3/library/collections.abc.html#collections.abc.Sequence" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">Sequence</span></code></a>[<a class="reference external" href="https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor" title="(in PyTorch v2.10)"><code class="xref py py-class docutils literal notranslate"><span class="pre">Tensor</span></code></a>] | <a class="reference external" href="https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor" title="(in PyTorch v2.10)"><code class="xref py py-class docutils literal notranslate"><span class="pre">Tensor</span></code></a> | <a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.14)"><code class="xref py py-obj docutils literal notranslate"><span class="pre">None</span></code></a></span>) – The initial Jacobians to backpropagate, analog to the <cite>grad_tensors</cite>
-parameter of <cite>torch.autograd.backward</cite>. If provided, it must have the same structure as
-<code class="docutils literal notranslate"><span class="pre">tensors</span></code> and each tensor in <code class="docutils literal notranslate"><span class="pre">jac_tensors</span></code> must match the shape of the corresponding
+<li><p><strong>jac_tensors</strong> (<span class="sphinx_autodoc_typehints-type"><a class="reference external" href="https://docs.python.org/3/library/collections.abc.html#collections.abc.Sequence" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">Sequence</span></code></a>[<a class="reference external" href="https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor" title="(in PyTorch v2.10)"><code class="xref py py-class docutils literal notranslate"><span class="pre">Tensor</span></code></a>] | <a class="reference external" href="https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor" title="(in PyTorch v2.10)"><code class="xref py py-class docutils literal notranslate"><span class="pre">Tensor</span></code></a> | <a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.14)"><code class="xref py py-obj docutils literal notranslate"><span class="pre">None</span></code></a></span>) – The initial Jacobians to backpropagate, analog to the <code class="docutils literal notranslate"><span class="pre">grad_tensors</span></code>
+parameter of <a class="reference external" href="https://docs.pytorch.org/docs/stable/generated/torch.autograd.backward.html#torch.autograd.backward" title="(in PyTorch v2.10)"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.autograd.backward()</span></code></a>. If provided, it must have the same structure
+as <code class="docutils literal notranslate"><span class="pre">tensors</span></code> and each tensor in <code class="docutils literal notranslate"><span class="pre">jac_tensors</span></code> must match the shape of the corresponding
 tensor in <code class="docutils literal notranslate"><span class="pre">tensors</span></code>, with an extra leading dimension representing the number of rows of
 the resulting Jacobian (e.g. the number of losses). All tensors in <code class="docutils literal notranslate"><span class="pre">jac_tensors</span></code> must
 have the same first dimension. If <code class="docutils literal notranslate"><span class="pre">None</span></code>, defaults to the identity matrix. In this case,

latest/docs/autojac/jac/index.html

@@ -308,7 +308,7 @@ <h1>jac<a class="headerlink" href="#jac" title="Link to this heading">¶</a></h1
 their <code class="docutils literal notranslate"><span class="pre">requires_grad</span></code> flag set to <code class="docutils literal notranslate"><span class="pre">True</span></code>. If not provided, defaults to the leaf tensors
 that were used to compute the <code class="docutils literal notranslate"><span class="pre">outputs</span></code> parameter.</p></li>
 <li><p><strong>jac_outputs</strong> (<span class="sphinx_autodoc_typehints-type"><a class="reference external" href="https://docs.python.org/3/library/collections.abc.html#collections.abc.Sequence" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">Sequence</span></code></a>[<a class="reference external" href="https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor" title="(in PyTorch v2.10)"><code class="xref py py-class docutils literal notranslate"><span class="pre">Tensor</span></code></a>] | <a class="reference external" href="https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor" title="(in PyTorch v2.10)"><code class="xref py py-class docutils literal notranslate"><span class="pre">Tensor</span></code></a> | <a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.14)"><code class="xref py py-obj docutils literal notranslate"><span class="pre">None</span></code></a></span>) – The initial Jacobians to backpropagate, analog to the <code class="docutils literal notranslate"><span class="pre">grad_outputs</span></code>
-parameter of <code class="docutils literal notranslate"><span class="pre">torch.autograd.grad</span></code>. If provided, it must have the same structure as
+parameter of <a class="reference external" href="https://docs.pytorch.org/docs/stable/generated/torch.autograd.grad.html#torch.autograd.grad" title="(in PyTorch v2.10)"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.autograd.grad()</span></code></a>. If provided, it must have the same structure as
 <code class="docutils literal notranslate"><span class="pre">outputs</span></code> and each tensor in <code class="docutils literal notranslate"><span class="pre">jac_outputs</span></code> must match the shape of the corresponding
 tensor in <code class="docutils literal notranslate"><span class="pre">outputs</span></code>, with an extra leading dimension representing the number of rows of
 the resulting Jacobian (e.g. the number of losses). If <code class="docutils literal notranslate"><span class="pre">None</span></code>, defaults to the identity

latest/docs/autojac/mtl_backward/index.html

@@ -314,7 +314,7 @@ <h1>mtl_backward<a class="headerlink" href="#mtl-backward" title="Link to this h
 <li><p><strong>features</strong> (<span class="sphinx_autodoc_typehints-type"><a class="reference external" href="https://docs.python.org/3/library/collections.abc.html#collections.abc.Sequence" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">Sequence</span></code></a>[<a class="reference external" href="https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor" title="(in PyTorch v2.10)"><code class="xref py py-class docutils literal notranslate"><span class="pre">Tensor</span></code></a>] | <a class="reference external" href="https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor" title="(in PyTorch v2.10)"><code class="xref py py-class docutils literal notranslate"><span class="pre">Tensor</span></code></a></span>) – The last shared representation used for all tasks, as given by the feature
 extractor. Should be non-empty.</p></li>
 <li><p><strong>grad_tensors</strong> (<span class="sphinx_autodoc_typehints-type"><a class="reference external" href="https://docs.python.org/3/library/collections.abc.html#collections.abc.Sequence" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">Sequence</span></code></a>[<a class="reference external" href="https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor" title="(in PyTorch v2.10)"><code class="xref py py-class docutils literal notranslate"><span class="pre">Tensor</span></code></a>] | <a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.14)"><code class="xref py py-obj docutils literal notranslate"><span class="pre">None</span></code></a></span>) – The initial gradients to backpropagate, analog to the <code class="docutils literal notranslate"><span class="pre">grad_tensors</span></code>
-parameter of <code class="docutils literal notranslate"><span class="pre">torch.autograd.backward</span></code>. If any of the <code class="docutils literal notranslate"><span class="pre">tensors</span></code> is non-scalar,
+parameter of <a class="reference external" href="https://docs.pytorch.org/docs/stable/generated/torch.autograd.backward.html#torch.autograd.backward" title="(in PyTorch v2.10)"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.autograd.backward()</span></code></a>. If any of the <code class="docutils literal notranslate"><span class="pre">tensors</span></code> is non-scalar,
 <code class="docutils literal notranslate"><span class="pre">grad_tensors</span></code> must be provided, with the same length and shapes as <code class="docutils literal notranslate"><span class="pre">tensors</span></code>.
 Otherwise, this parameter is not needed and will default to scalars of 1.</p></li>
 <li><p><strong>tasks_params</strong> (<span class="sphinx_autodoc_typehints-type"><a class="reference external" href="https://docs.python.org/3/library/collections.abc.html#collections.abc.Sequence" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">Sequence</span></code></a>[<a class="reference external" href="https://docs.python.org/3/library/collections.abc.html#collections.abc.Iterable" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">Iterable</span></code></a>[<a class="reference external" href="https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor" title="(in PyTorch v2.10)"><code class="xref py py-class docutils literal notranslate"><span class="pre">Tensor</span></code></a>]] | <a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.14)"><code class="xref py py-obj docutils literal notranslate"><span class="pre">None</span></code></a></span>) – The parameters of each task-specific head. Their <code class="docutils literal notranslate"><span class="pre">requires_grad</span></code> flags