+
-
+
-
+
- 
+
-
+
-
+
- 
+
## 2. VGG16 Overview ### Very Deep Convolutional Networks for Large-Scale Image Recognition VGG is one of the earliest family of image classification networks that first used small (3x3) convolution filters and achieved significant improvements on ImageNet recognition challenge. The network architecture looks as follows
- 
+
## 3. Training a baseline VGG16 model We train VGG16 on CIFAR10 dataset. Define training and testing datasets and dataloaders. This will download the CIFAR 10 data in your
diff --git a/docs/_sources/contributors/conversion.rst.txt b/docs/_sources/contributors/conversion.rst.txt
index deb6d85a49..f19fc5eba8 100644
--- a/docs/_sources/contributors/conversion.rst.txt
+++ b/docs/_sources/contributors/conversion.rst.txt
@@ -19,7 +19,7 @@ inputs and assemble an array of resources to pass to the converter. Inputs can b
* The input is an output of a node that has already been converted
- * In this case the ITensor of the output has added to the to the ``value_tensor_map``,
+ * In this case the ITensor of the output has added to the ``value_tensor_map``,
The conversion stage will add the ITensor to the list of args for the converter
* The input is from a node that produces a static value
@@ -32,6 +32,7 @@ inputs and assemble an array of resources to pass to the converter. Inputs can b
static value has been evaluated
* The input is from a node that has not been converted
+
* Torch-TensorRT will error out here
Node Evaluation
diff --git a/docs/_sources/contributors/lowering.rst.txt b/docs/_sources/contributors/lowering.rst.txt
index 7208e9c4bf..38c4491295 100644
--- a/docs/_sources/contributors/lowering.rst.txt
+++ b/docs/_sources/contributors/lowering.rst.txt
@@ -134,7 +134,7 @@ Removes _all_ tuples and raises an error if some cannot be removed, this is used
Module Fallback
*****************
- `Torch-TensorRT/core/lowering/passes/module_fallback.cpp
- In this case the ITensor of the output has added to the to the
+ In this case the ITensor of the output has added to the
The input is from a node that has not been converted
-* Torch-TensorRT will error out here
+ Torch-TensorRT will error out here
+
-
- Torch-TensorRT/core/lowering/passes/module_fallback.cpp <https://github.com/nvidia/Torch-TensorRT/blob/master/core/lowering/passes/module_fallback.cpp>
-
+
+ Torch-TensorRT/core/lowering/passes/module_fallback.cpp
+
- The phase is optional and enabled by the user. It instructs the compiler to seperate nodes into ones that should run in PyTorch and ones that should run in TensorRT.
-Criteria for seperation include: Lack of a converter, operator is explicitly set to run in PyTorch by the user or the node has a flag which tells partitioning to
+ The phase is optional and enabled by the user. It instructs the compiler to separate nodes into ones that should run in PyTorch and ones that should run in TensorRT.
+Criteria for separation include: Lack of a converter, operator is explicitly set to run in PyTorch by the user or the node has a flag which tells partitioning to
run in PyTorch by the module fallback passes.
- :ref:
-
-
- `
+
+
+ Partitioning Phase
- partitioning
- The phase is optional and enabled by the user. It instructs the compiler to seperate nodes into ones that should run in PyTorch and ones that should run in TensorRT.
-Criteria for seperation include: Lack of a converter, operator is explicitly set to run in PyTorch by the user or the node has a flag which tells partitioning to
+ The phase is optional and enabled by the user. It instructs the compiler to separate nodes into ones that should run in PyTorch and ones that should run in TensorRT.
+Criteria for separation include: Lack of a converter, operator is explicitly set to run in PyTorch by the user or the node has a flag which tells partitioning to
run in PyTorch by the module fallback passes.
value_tensor_map
@@ -570,8 +570,14 @@
+
diff --git a/docs/contributors/partitioning.html b/docs/contributors/partitioning.html
index abf5e967b8..d278b8858c 100644
--- a/docs/contributors/partitioning.html
+++ b/docs/contributors/partitioning.html
@@ -468,8 +468,8 @@
The core has a couple major parts: The top level compiler interface which coordinates ingesting a module, lowering, -converting and generating a new module and returning it back to the user. The there are the three main phases of the +converting and generating a new module and returning it back to the user. There are the three main phases of the compiler, the lowering phase, the conversion phase, and the execution phase.
- :ref: - - - ` + + + Partitioning Phase - partitioning
- The phase is optional and enabled by the user. It instructs the compiler to seperate nodes into ones that should run in PyTorch and ones that should run in TensorRT. -Criteria for seperation include: Lack of a converter, operator is explicitly set to run in PyTorch by the user or the node has a flag which tells partitioning to + The phase is optional and enabled by the user. It instructs the compiler to separate nodes into ones that should run in PyTorch and ones that should run in TensorRT. +Criteria for separation include: Lack of a converter, operator is explicitly set to run in PyTorch by the user or the node has a flag which tells partitioning to run in PyTorch by the module fallback passes.