docs: [Automated] Regenerating documenation from

TRTorch Github Bot · TRTorch Github Bot · commit 9303ce2f091c · 2021-01-25T19:44:45.000Z
Signed-off-by: TRTorch Github Bot &lt;trtorch.github.bot@nvidia.com&gt;
diff --git a/docs/_notebooks/Resnet50-example.html b/docs/_notebooks/Resnet50-example.html
@@ -675,7 +675,7 @@
         </div>
        </div>
        <p>
-        <img alt="7ff72b2fb2f443dbaedf0e71b12aa769" src="http://developer.download.nvidia.com/compute/machine-learning/frameworks/nvidia_logo.png"/>
+        <img alt="89174e080c4b4d87aa6bb35bece7e6f2" src="http://developer.download.nvidia.com/compute/machine-learning/frameworks/nvidia_logo.png"/>
        </p>
        <h1 id="notebooks-resnet50-example--page-root">
         TRTorch Getting Started - ResNet 50
diff --git a/docs/_notebooks/lenet-getting-started.html b/docs/_notebooks/lenet-getting-started.html
@@ -769,7 +769,7 @@
         </div>
        </div>
        <p>
-        <img alt="61ea82a269d94750a349171805a268b6" src="http://developer.download.nvidia.com/compute/machine-learning/frameworks/nvidia_logo.png"/>
+        <img alt="bc357ab3290b4127af16e398763e49ed" src="http://developer.download.nvidia.com/compute/machine-learning/frameworks/nvidia_logo.png"/>
        </p>
        <h1 id="notebooks-lenet-getting-started--page-root">
         TRTorch Getting Started - LeNet
diff --git a/docs/_notebooks/ssd-object-detection-demo.html b/docs/_notebooks/ssd-object-detection-demo.html
@@ -789,7 +789,7 @@
         </div>
        </div>
        <p>
-        <img alt="61fc82d7549042dd92c38dcd3c8986ee" src="http://developer.download.nvidia.com/compute/machine-learning/frameworks/nvidia_logo.png"/>
+        <img alt="403c4e31d922412bbcb15356bf72367f" src="http://developer.download.nvidia.com/compute/machine-learning/frameworks/nvidia_logo.png"/>
        </p>
        <h1 id="notebooks-ssd-object-detection-demo--page-root">
         Object Detection with TRTorch (SSD)
diff --git a/docs/_sources/tutorials/use_from_pytorch.rst.txt b/docs/_sources/tutorials/use_from_pytorch.rst.txt
@@ -14,7 +14,7 @@ Start by loading ``trtorch`` into your application.
     import trtorch
 
 
-Then given a TorchScript module, you can lower it to TensorRT using the ``torch._C._jit_to_tensorrt`` API.
+Then given a TorchScript module, you can compile it with TensorRT using the ``torch._C._jit_to_backend("tensorrt", ...)`` API.
 
 .. code-block:: python
 
@@ -32,31 +32,36 @@ at the documentation for the TRTorch ``TensorRTCompileSpec`` API.
 .. code-block:: python
 
     spec = {
-        "forward": trtorch.TensorRTCompileSpec({
-            "input_shapes": [[1, 3, 300, 300]],
-            "op_precision": torch.half,
-            "refit": False,
-            "debug": False,
-            "strict_types": False,
-            "allow_gpu_fallback": True,
-            "device_type": "gpu",
-            "capability": trtorch.EngineCapability.default,
-            "num_min_timing_iters": 2,
-            "num_avg_timing_iters": 1,
-            "max_batch_size": 0,
-        })
-    }
-
-Now to compile with TRTorch, provide the target module objects and the spec dictionary to ``torch._C._jit_to_tensorrt``
+        "forward":
+            trtorch.TensorRTCompileSpec({
+                "input_shapes": [[1, 3, 300, 300]],
+                "op_precision": torch.half,
+                "refit": False,
+                "debug": False,
+                "strict_types": False,
+                "device": {
+                    "device_type": trtorch.DeviceType.GPU,
+                    "gpu_id": 0,
+                    "dla_core": 0,
+                    "allow_gpu_fallback": True
+                },
+                "capability": trtorch.EngineCapability.default,
+                "num_min_timing_iters": 2,
+                "num_avg_timing_iters": 1,
+                "max_batch_size": 0,
+            })
+        }
+
+Now to compile with TRTorch, provide the target module objects and the spec dictionary to ``torch._C._jit_to_backend("tensorrt", ...)``
 
 .. code-block:: python
 
-    trt_model = torch._C._jit_to_tensorrt(script_model._c, spec)
+    trt_model = torch._C._jit_to_backend("tensorrt", script_model, spec)
 
 To run explicitly call the function of the method you want to run (vs. how you can just call on the module itself in standard PyTorch)
 
 .. code-block:: python
 
-    input = torch.randn((1, 3, 300, 300).to("cuda").to(torch.half)
+    input = torch.randn((1, 3, 300, 300)).to("cuda").to(torch.half)
     print(trt_model.forward(input))
 
diff --git a/docs/py_api/trtorch.html b/docs/py_api/trtorch.html
@@ -969,6 +969,7 @@ <h2 id="functions">
          <span class="sig-paren">
           )
          </span>
+         → &lt;torch._C.ScriptClass object at 0x7fc804e6c928&gt;
          <a class="headerlink" href="#trtorch.TensorRTCompileSpec" title="Permalink to this definition">
           ¶
          </a>
@@ -1016,10 +1017,10 @@ <h2 id="functions">
             <span class="p">}</span> <span class="c1"># Dynamic input shape for input #2</span>
         <span class="p">],</span>
         <span class="s2">"device"</span><span class="p">:</span> <span class="p">{</span>
-        <span class="s2">"device_type"</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">device</span><span class="p">(</span><span class="s2">"cuda"</span><span class="p">),</span> <span class="c1"># Type of device to run engine on (for DLA use trtorch.DeviceType.DLA)</span>
-        <span class="s2">"gpu_id"</span><span class="p">:</span> <span class="mi">0</span><span class="p">,</span> <span class="c1"># Target gpu id to run engine (Use Xavier as gpu id for DLA)</span>
-        <span class="s2">"dla_core"</span><span class="p">:</span> <span class="mi">0</span><span class="p">,</span> <span class="c1"># (DLA only) Target dla core id to run engine</span>
-        <span class="s2">"allow_gpu_fallback"</span><span class="p">:</span> <span class="n">false</span><span class="p">,</span> <span class="c1"># (DLA only) Allow layers unsupported on DLA to run on GPU</span>
+            <span class="s2">"device_type"</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">device</span><span class="p">(</span><span class="s2">"cuda"</span><span class="p">),</span> <span class="c1"># Type of device to run engine on (for DLA use trtorch.DeviceType.DLA)</span>
+            <span class="s2">"gpu_id"</span><span class="p">:</span> <span class="mi">0</span><span class="p">,</span> <span class="c1"># Target gpu id to run engine (Use Xavier as gpu id for DLA)</span>
+            <span class="s2">"dla_core"</span><span class="p">:</span> <span class="mi">0</span><span class="p">,</span> <span class="c1"># (DLA only) Target dla core id to run engine</span>
+            <span class="s2">"allow_gpu_fallback"</span><span class="p">:</span> <span class="n">false</span><span class="p">,</span> <span class="c1"># (DLA only) Allow layers unsupported on DLA to run on GPU</span>
         <span class="p">},</span>
         <span class="s2">"op_precision"</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">half</span><span class="p">,</span> <span class="c1"># Operating precision set to FP16</span>
         <span class="s2">"refit"</span><span class="p">:</span> <span class="kc">False</span><span class="p">,</span> <span class="c1"># enable refit</span>
diff --git a/docs/searchindex.js b/docs/searchindex.js
diff --git a/docs/tutorials/use_from_pytorch.html b/docs/tutorials/use_from_pytorch.html
@@ -394,10 +394,13 @@ <h1 id="tutorials-use-from-pytorch--page-root">
         </div>
        </div>
        <p>
-        Then given a TorchScript module, you can lower it to TensorRT using the
+        Then given a TorchScript module, you can compile it with TensorRT using the
         <code class="docutils literal notranslate">
          <span class="pre">
-          torch._C._jit_to_tensorrt
+          torch._C._jit_to_backend("tensorrt",
+         </span>
+         <span class="pre">
+          ...)
          </span>
         </code>
         API.
@@ -451,34 +454,42 @@ <h1 id="tutorials-use-from-pytorch--page-root">
        <div class="highlight-python notranslate">
         <div class="highlight">
          <pre><span></span><span class="n">spec</span> <span class="o">=</span> <span class="p">{</span>
-    <span class="s2">"forward"</span><span class="p">:</span> <span class="n">trtorch</span><span class="o">.</span><span class="n">TensorRTCompileSpec</span><span class="p">({</span>
-        <span class="s2">"input_shapes"</span><span class="p">:</span> <span class="p">[[</span><span class="mi">1</span><span class="p">,</span> <span class="mi">3</span><span class="p">,</span> <span class="mi">300</span><span class="p">,</span> <span class="mi">300</span><span class="p">]],</span>
-        <span class="s2">"op_precision"</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">half</span><span class="p">,</span>
-        <span class="s2">"refit"</span><span class="p">:</span> <span class="kc">False</span><span class="p">,</span>
-        <span class="s2">"debug"</span><span class="p">:</span> <span class="kc">False</span><span class="p">,</span>
-        <span class="s2">"strict_types"</span><span class="p">:</span> <span class="kc">False</span><span class="p">,</span>
-        <span class="s2">"allow_gpu_fallback"</span><span class="p">:</span> <span class="kc">True</span><span class="p">,</span>
-        <span class="s2">"device_type"</span><span class="p">:</span> <span class="s2">"gpu"</span><span class="p">,</span>
-        <span class="s2">"capability"</span><span class="p">:</span> <span class="n">trtorch</span><span class="o">.</span><span class="n">EngineCapability</span><span class="o">.</span><span class="n">default</span><span class="p">,</span>
-        <span class="s2">"num_min_timing_iters"</span><span class="p">:</span> <span class="mi">2</span><span class="p">,</span>
-        <span class="s2">"num_avg_timing_iters"</span><span class="p">:</span> <span class="mi">1</span><span class="p">,</span>
-        <span class="s2">"max_batch_size"</span><span class="p">:</span> <span class="mi">0</span><span class="p">,</span>
-    <span class="p">})</span>
-<span class="p">}</span>
+    <span class="s2">"forward"</span><span class="p">:</span>
+        <span class="n">trtorch</span><span class="o">.</span><span class="n">TensorRTCompileSpec</span><span class="p">({</span>
+            <span class="s2">"input_shapes"</span><span class="p">:</span> <span class="p">[[</span><span class="mi">1</span><span class="p">,</span> <span class="mi">3</span><span class="p">,</span> <span class="mi">300</span><span class="p">,</span> <span class="mi">300</span><span class="p">]],</span>
+            <span class="s2">"op_precision"</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">half</span><span class="p">,</span>
+            <span class="s2">"refit"</span><span class="p">:</span> <span class="kc">False</span><span class="p">,</span>
+            <span class="s2">"debug"</span><span class="p">:</span> <span class="kc">False</span><span class="p">,</span>
+            <span class="s2">"strict_types"</span><span class="p">:</span> <span class="kc">False</span><span class="p">,</span>
+            <span class="s2">"device"</span><span class="p">:</span> <span class="p">{</span>
+                <span class="s2">"device_type"</span><span class="p">:</span> <span class="n">trtorch</span><span class="o">.</span><span class="n">DeviceType</span><span class="o">.</span><span class="n">GPU</span><span class="p">,</span>
+                <span class="s2">"gpu_id"</span><span class="p">:</span> <span class="mi">0</span><span class="p">,</span>
+                <span class="s2">"dla_core"</span><span class="p">:</span> <span class="mi">0</span><span class="p">,</span>
+                <span class="s2">"allow_gpu_fallback"</span><span class="p">:</span> <span class="kc">True</span>
+            <span class="p">},</span>
+            <span class="s2">"capability"</span><span class="p">:</span> <span class="n">trtorch</span><span class="o">.</span><span class="n">EngineCapability</span><span class="o">.</span><span class="n">default</span><span class="p">,</span>
+            <span class="s2">"num_min_timing_iters"</span><span class="p">:</span> <span class="mi">2</span><span class="p">,</span>
+            <span class="s2">"num_avg_timing_iters"</span><span class="p">:</span> <span class="mi">1</span><span class="p">,</span>
+            <span class="s2">"max_batch_size"</span><span class="p">:</span> <span class="mi">0</span><span class="p">,</span>
+        <span class="p">})</span>
+    <span class="p">}</span>
 </pre>
         </div>
        </div>
        <p>
         Now to compile with TRTorch, provide the target module objects and the spec dictionary to
         <code class="docutils literal notranslate">
          <span class="pre">
-          torch._C._jit_to_tensorrt
+          torch._C._jit_to_backend("tensorrt",
+         </span>
+         <span class="pre">
+          ...)
          </span>
         </code>
        </p>
        <div class="highlight-python notranslate">
         <div class="highlight">
-         <pre><span></span><span class="n">trt_model</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">_C</span><span class="o">.</span><span class="n">_jit_to_tensorrt</span><span class="p">(</span><span class="n">script_model</span><span class="o">.</span><span class="n">_c</span><span class="p">,</span> <span class="n">spec</span><span class="p">)</span>
+         <pre><span></span><span class="n">trt_model</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">_C</span><span class="o">.</span><span class="n">_jit_to_backend</span><span class="p">(</span><span class="s2">"tensorrt"</span><span class="p">,</span> <span class="n">script_model</span><span class="p">,</span> <span class="n">spec</span><span class="p">)</span>
 </pre>
         </div>
        </div>
@@ -487,7 +498,7 @@ <h1 id="tutorials-use-from-pytorch--page-root">
        </p>
        <div class="highlight-python notranslate">
         <div class="highlight">
-         <pre><span></span><span class="nb">input</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">randn</span><span class="p">((</span><span class="mi">1</span><span class="p">,</span> <span class="mi">3</span><span class="p">,</span> <span class="mi">300</span><span class="p">,</span> <span class="mi">300</span><span class="p">)</span><span class="o">.</span><span class="n">to</span><span class="p">(</span><span class="s2">"cuda"</span><span class="p">)</span><span class="o">.</span><span class="n">to</span><span class="p">(</span><span class="n">torch</span><span class="o">.</span><span class="n">half</span><span class="p">)</span>
+         <pre><span></span><span class="nb">input</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">randn</span><span class="p">((</span><span class="mi">1</span><span class="p">,</span> <span class="mi">3</span><span class="p">,</span> <span class="mi">300</span><span class="p">,</span> <span class="mi">300</span><span class="p">))</span><span class="o">.</span><span class="n">to</span><span class="p">(</span><span class="s2">"cuda"</span><span class="p">)</span><span class="o">.</span><span class="n">to</span><span class="p">(</span><span class="n">torch</span><span class="o">.</span><span class="n">half</span><span class="p">)</span>
 <span class="nb">print</span><span class="p">(</span><span class="n">trt_model</span><span class="o">.</span><span class="n">forward</span><span class="p">(</span><span class="nb">input</span><span class="p">))</span>
 </pre>
         </div>
