Replaced AlexNet2 with VGG16

hpvm/docs/getting-started.rst

@@ -3,14 +3,14 @@ Getting Started
 
 This tutorial covers the basic usage of all components in HPVM
 (components listed :doc:`here </components/index>`).
-We will generate a DNN model, AlexNet2 (for CIFAR10 dataset), into HPVM code, compile it with HPVM,
+We will generate a DNN model, VGG16 (for CIFAR10 dataset), into HPVM code, compile it with HPVM,
 perform autotuning on the compiled binary to find approximation choices (configurations),
 and profile the selected configurations to get real performance on device.
-The result will be a figure showing the accuracy-performance tradeoff of AlexNet2 over the
+The result will be a figure showing the accuracy-performance tradeoff of VGG16 over the
 (pre-defined) approximations and the configurations in a few formats.
 
 Please check ``test/dnn_benchmarks/model_params/`` exists and contains 
-``alexnet2_cifar10/`` and ``pytorch/alexnet2_cifar10.pth.tar``,
+``vgg16_cifar10/`` and ``pytorch/vgg16_cifar10.pth.tar``,
 which may not be the case if you opted out of model parameter download in the installer.
 In that case, you may run the installer again to download the parameter.
 It will not rebuild everything from scratch.
@@ -28,8 +28,8 @@ for easier access to ``test/dnn_benchmarks/model_params/``.
 You can also symlink it to other locations -- don't move it: it's used in test cases --
 and adjust the paths below accordingly.
 
-First, prepare 2 datasets for autotuning and testing for AlexNet2.
-These datasets are provided as ``model_params/alexnet2_cifar10/{tune|test}_{input|labels}.bin``,
+First, prepare 2 datasets for autotuning and testing for VGG16.
+These datasets are provided as ``model_params/vgg16_cifar10/{tune|test}_{input|labels}.bin``,
 where ``tune`` and ``test`` prefixes signify tuning and testing set.
 
 .. code-block:: python
@@ -37,13 +37,13 @@ where ``tune`` and ``test`` prefixes signify tuning and testing set.
    from torch2hpvm import BinDataset
    from pathlib import Path
 
-   data_dir = Path("model_params/alexnet2_cifar10")
+   data_dir = Path("model_params/vgg16_cifar10")
    dataset_shape = 5000, 3, 32, 32  # NCHW format.
    tuneset = BinDataset(data_dir / "tune_input.bin", data_dir / "tune_labels.bin", dataset_shape)
    testset = BinDataset(data_dir / "test_input.bin", data_dir / "test_labels.bin", dataset_shape)
 
 `BinDataset` is a utility `torch2hpvm` provides for creating dataset over binary files.
-Any instance `torch.utils.data.Dataset` can be used here.
+Any instance of `torch.utils.data.Dataset` can be used here.
 
 *Note* that each `module` is bound to 2 datasets: a "tune" and a "test" set.
 The generated binary accepts an argument to be either the string "tune" or "test",
@@ -57,8 +57,8 @@ Create a DNN `module` and load the checkpoint:
    from torch.nn import Module
    import dnn  # Defined at `hpvm/test/dnn_benchmarks/pytorch`
 
-   model: Module = dnn.AlexNet2()
-   checkpoint = "model_params/alexnet2_cifar10.pth.tar"
+   model: Module = dnn.VGG16()
+   checkpoint = "model_params/vgg16_cifar10.pth.tar"
    model.load_state_dict(torch.load(checkpoint))
 
 Any `torch.nn.Module` can be similarly used,
@@ -72,11 +72,11 @@ Now we are ready to export the model. The main functioning class of `torch2hpvm`
 
    from torch2hpvm import ModelExporter
 
-   output_dir = Path("./alexnet2_cifar10")
+   output_dir = Path("./vgg16_cifar10")
    build_dir = output_dir / "build"
-   target_binary = build_dir / "alexnet2_cifar10"
+   target_binary = build_dir / "vgg16_cifar10"
    batch_size = 500
-   conf_file = "hpvm-c/benchmarks/alexnet2_cifar10/data/tuner_confs.txt"
+   conf_file = "hpvm-c/benchmarks/vgg16_cifar10/data/tuner_confs.txt"
    exporter = ModelExporter(model, tuneset, testset, output_dir, config_file=conf_file)
    exporter.generate(batch_size=batch_size).compile(target_binary, build_dir)
 
@@ -89,13 +89,13 @@ and path to the compiled binary respectively.
   This file decides what approximation the binary will use during inference.
   This path is hardcoded into the binary and is only read when the binary starts,
   so it's fine to have `conf_file` point to a non-existing path.
-  An example can be found at ``hpvm-c/benchmarks/alexnet2_cifar10/data/tuner_confs.txt``.
+  An example can be found at ``hpvm-c/benchmarks/vgg16_cifar10/data/tuner_confs.txt``.
 
 * `exporter.generate` generates the HPVM-C code while `exporter.compile` is
   a helper that invokes the HPVM compiler for you.
 
-Now there should be a binary at ``./alexnet2_cifar10/build/alexnet2_cifar10``.
-Try running ``./alexnet2_cifar10/build/alexnet2_cifar10 test`` for inference over the test set.
+Now there should be a binary at ``./vgg16_cifar10/build/vgg16_cifar10``.
+Try running ``./vgg16_cifar10/build/vgg16_cifar10 test`` for inference over the test set.
 
 Compiling a Tuner Binary
 ------------------------
@@ -111,13 +111,13 @@ It also doesn't define a `conf_file`.
 
    from torch2hpvm import ModelExporter
 
-   tuner_output_dir = Path("./alexnet2_cifar10_tuner")
+   tuner_output_dir = Path("./vgg16_cifar10_tuner")
    tuner_build_dir = tuner_output_dir / "build"
-   tuner_binary = tuner_build_dir / "alexnet2_cifar10"
+   tuner_binary = tuner_build_dir / "vgg16_cifar10"
    exporter = ModelExporter(model, tuneset, testset, tuner_output_dir, target="hpvm_tensor_inspect")
    exporter.generate(batch_size=500).compile(tuner_binary, tuner_build_dir)
 
-This binary is generated at ``alexnet2_cifar10_tuner/build/alexnet2_cifar10``.
+This binary is generated at ``vgg16_cifar10_tuner/build/vgg16_cifar10``.
 It waits for autotuner signal and doesn't run on its own, so don't run it by yourself.
 Instead, import and use the tuner `predtuner`:
 
@@ -210,7 +210,7 @@ we obtained in the tuning step.
    from hpvm_profiler import profile_config_file, plot_hpvm_configs
 
    # Set `target_binary` to the path of the plain binary.
-   target_binary = "./alexnet2_cifar10/build/alexnet2_cifar10"
+   target_binary = "./vgg16_cifar10/build/vgg16_cifar10"
    # Set `config_file` to the config file produced in tuning, such as "hpvm_confs.txt".
    config_file = "hpvm_confs.txt"
    out_config_file = "hpvm_confs_profiled.txt"
@@ -222,7 +222,7 @@ while ``configs_profiled.png`` shows the final performance-accuracy tradeoff cur
 
 An example of ``configs_profiled.png`` looks like this (proportion of your image may be different):
 
-.. image:: _static/alexnet2_cifar10.png
+.. image:: _static/vgg16_cifar10.png
 
 -----------------------