pytorch · soumith · Jul 26, 2018 · Jul 26, 2018 · Jul 26, 2018 · Jul 26, 2018
diff --git a/docs/stable/.buildinfo → docs/0.4.0/.buildinfo b/docs/stable/.buildinfo → docs/0.4.0/.buildinfo
diff --git a/docs/0.4.0/_images/ELU.png b/docs/0.4.0/_images/ELU.png
diff --git a/docs/0.4.0/_images/Hardshrink.png b/docs/0.4.0/_images/Hardshrink.png
diff --git a/docs/0.4.0/_images/Hardtanh.png b/docs/0.4.0/_images/Hardtanh.png
diff --git a/docs/0.4.0/_images/LeakyReLU.png b/docs/0.4.0/_images/LeakyReLU.png
diff --git a/docs/0.4.0/_images/LogSigmoid.png b/docs/0.4.0/_images/LogSigmoid.png
diff --git a/docs/0.4.0/_images/PReLU.png b/docs/0.4.0/_images/PReLU.png
diff --git a/docs/0.4.0/_images/ReLU.png b/docs/0.4.0/_images/ReLU.png
diff --git a/docs/0.4.0/_images/ReLU6.png b/docs/0.4.0/_images/ReLU6.png
diff --git a/docs/0.4.0/_images/SELU.png b/docs/0.4.0/_images/SELU.png
diff --git a/docs/0.4.0/_images/Sigmoid.png b/docs/0.4.0/_images/Sigmoid.png
diff --git a/docs/0.4.0/_images/Softplus.png b/docs/0.4.0/_images/Softplus.png
diff --git a/docs/0.4.0/_images/Softshrink.png b/docs/0.4.0/_images/Softshrink.png
diff --git a/docs/0.4.0/_images/Softsign.png b/docs/0.4.0/_images/Softsign.png
diff --git a/docs/0.4.0/_images/Tanh.png b/docs/0.4.0/_images/Tanh.png
diff --git a/docs/0.4.0/_images/Tanhshrink.png b/docs/0.4.0/_images/Tanhshrink.png
diff --git a/docs/0.4.0/_modules/index.html b/docs/0.4.0/_modules/index.html
diff --git a/docs/0.4.0/_modules/torch.html b/docs/0.4.0/_modules/torch.html
diff --git a/docs/0.4.0/_modules/torch/_tensor_str.html b/docs/0.4.0/_modules/torch/_tensor_str.html
diff --git a/docs/0.4.0/_modules/torch/_utils.html b/docs/0.4.0/_modules/torch/_utils.html
diff --git a/docs/0.4.0/_modules/torch/autograd.html b/docs/0.4.0/_modules/torch/autograd.html
diff --git a/docs/0.4.0/_modules/torch/autograd/function.html b/docs/0.4.0/_modules/torch/autograd/function.html
diff --git a/docs/0.4.0/_modules/torch/autograd/grad_mode.html b/docs/0.4.0/_modules/torch/autograd/grad_mode.html
diff --git a/docs/0.4.0/_modules/torch/autograd/profiler.html b/docs/0.4.0/_modules/torch/autograd/profiler.html
diff --git a/docs/0.4.0/_modules/torch/cuda.html b/docs/0.4.0/_modules/torch/cuda.html
diff --git a/docs/0.4.0/_modules/torch/cuda/comm.html b/docs/0.4.0/_modules/torch/cuda/comm.html
diff --git a/docs/0.4.0/_modules/torch/cuda/nvtx.html b/docs/0.4.0/_modules/torch/cuda/nvtx.html
diff --git a/docs/0.4.0/_modules/torch/cuda/random.html b/docs/0.4.0/_modules/torch/cuda/random.html
diff --git a/docs/0.4.0/_modules/torch/cuda/streams.html b/docs/0.4.0/_modules/torch/cuda/streams.html
diff --git a/docs/0.4.0/_modules/torch/distributed.html b/docs/0.4.0/_modules/torch/distributed.html
diff --git a/docs/0.4.0/_modules/torch/distributions/bernoulli.html b/docs/0.4.0/_modules/torch/distributions/bernoulli.html
diff --git a/docs/0.4.0/_modules/torch/distributions/beta.html b/docs/0.4.0/_modules/torch/distributions/beta.html
diff --git a/docs/0.4.0/_modules/torch/distributions/binomial.html b/docs/0.4.0/_modules/torch/distributions/binomial.html
diff --git a/docs/0.4.0/_modules/torch/distributions/categorical.html b/docs/0.4.0/_modules/torch/distributions/categorical.html
diff --git a/docs/0.4.0/_modules/torch/distributions/cauchy.html b/docs/0.4.0/_modules/torch/distributions/cauchy.html
diff --git a/docs/0.4.0/_modules/torch/distributions/chi2.html b/docs/0.4.0/_modules/torch/distributions/chi2.html
diff --git a/docs/0.4.0/_modules/torch/distributions/constraint_registry.html b/docs/0.4.0/_modules/torch/distributions/constraint_registry.html
diff --git a/docs/0.4.0/_modules/torch/distributions/constraints.html b/docs/0.4.0/_modules/torch/distributions/constraints.html
diff --git a/docs/0.4.0/_modules/torch/distributions/dirichlet.html b/docs/0.4.0/_modules/torch/distributions/dirichlet.html
diff --git a/docs/0.4.0/_modules/torch/distributions/distribution.html b/docs/0.4.0/_modules/torch/distributions/distribution.html
diff --git a/docs/0.4.0/_modules/torch/distributions/exp_family.html b/docs/0.4.0/_modules/torch/distributions/exp_family.html
diff --git a/docs/0.4.0/_modules/torch/distributions/exponential.html b/docs/0.4.0/_modules/torch/distributions/exponential.html
diff --git a/docs/0.4.0/_modules/torch/distributions/fishersnedecor.html b/docs/0.4.0/_modules/torch/distributions/fishersnedecor.html
diff --git a/docs/0.4.0/_modules/torch/distributions/gamma.html b/docs/0.4.0/_modules/torch/distributions/gamma.html
diff --git a/docs/0.4.0/_modules/torch/distributions/geometric.html b/docs/0.4.0/_modules/torch/distributions/geometric.html
diff --git a/docs/0.4.0/_modules/torch/distributions/gumbel.html b/docs/0.4.0/_modules/torch/distributions/gumbel.html
diff --git a/docs/0.4.0/_modules/torch/distributions/independent.html b/docs/0.4.0/_modules/torch/distributions/independent.html
diff --git a/docs/0.4.0/_modules/torch/distributions/kl.html b/docs/0.4.0/_modules/torch/distributions/kl.html
diff --git a/docs/0.4.0/_modules/torch/distributions/laplace.html b/docs/0.4.0/_modules/torch/distributions/laplace.html
diff --git a/docs/0.4.0/_modules/torch/distributions/log_normal.html b/docs/0.4.0/_modules/torch/distributions/log_normal.html
diff --git a/docs/0.4.0/_modules/torch/distributions/multinomial.html b/docs/0.4.0/_modules/torch/distributions/multinomial.html
diff --git a/docs/0.4.0/_modules/torch/distributions/multivariate_normal.html b/docs/0.4.0/_modules/torch/distributions/multivariate_normal.html
diff --git a/docs/0.4.0/_modules/torch/distributions/normal.html b/docs/0.4.0/_modules/torch/distributions/normal.html
diff --git a/docs/0.4.0/_modules/torch/distributions/one_hot_categorical.html b/docs/0.4.0/_modules/torch/distributions/one_hot_categorical.html
diff --git a/docs/0.4.0/_modules/torch/distributions/pareto.html b/docs/0.4.0/_modules/torch/distributions/pareto.html
diff --git a/docs/0.4.0/_modules/torch/distributions/poisson.html b/docs/0.4.0/_modules/torch/distributions/poisson.html
diff --git a/docs/0.4.0/_modules/torch/distributions/relaxed_bernoulli.html b/docs/0.4.0/_modules/torch/distributions/relaxed_bernoulli.html
diff --git a/docs/0.4.0/_modules/torch/distributions/relaxed_categorical.html b/docs/0.4.0/_modules/torch/distributions/relaxed_categorical.html
diff --git a/docs/0.4.0/_modules/torch/distributions/studentT.html b/docs/0.4.0/_modules/torch/distributions/studentT.html
diff --git a/docs/0.4.0/_modules/torch/distributions/transformed_distribution.html b/docs/0.4.0/_modules/torch/distributions/transformed_distribution.html
diff --git a/docs/0.4.0/_modules/torch/distributions/transforms.html b/docs/0.4.0/_modules/torch/distributions/transforms.html
diff --git a/docs/0.4.0/_modules/torch/distributions/uniform.html b/docs/0.4.0/_modules/torch/distributions/uniform.html
diff --git a/docs/0.4.0/_modules/torch/functional.html b/docs/0.4.0/_modules/torch/functional.html
diff --git a/docs/0.4.0/_modules/torch/multiprocessing.html b/docs/0.4.0/_modules/torch/multiprocessing.html
diff --git a/docs/0.4.0/_modules/torch/nn/functional.html b/docs/0.4.0/_modules/torch/nn/functional.html
diff --git a/docs/0.4.0/_modules/torch/nn/init.html b/docs/0.4.0/_modules/torch/nn/init.html
diff --git a/docs/0.4.0/_modules/torch/nn/modules/activation.html b/docs/0.4.0/_modules/torch/nn/modules/activation.html
diff --git a/docs/0.4.0/_modules/torch/nn/modules/batchnorm.html b/docs/0.4.0/_modules/torch/nn/modules/batchnorm.html
diff --git a/docs/0.4.0/_modules/torch/nn/modules/container.html b/docs/0.4.0/_modules/torch/nn/modules/container.html
diff --git a/docs/0.4.0/_modules/torch/nn/modules/conv.html b/docs/0.4.0/_modules/torch/nn/modules/conv.html
diff --git a/docs/0.4.0/_modules/torch/nn/modules/distance.html b/docs/0.4.0/_modules/torch/nn/modules/distance.html
diff --git a/docs/0.4.0/_modules/torch/nn/modules/dropout.html b/docs/0.4.0/_modules/torch/nn/modules/dropout.html
diff --git a/docs/0.4.0/_modules/torch/nn/modules/instancenorm.html b/docs/0.4.0/_modules/torch/nn/modules/instancenorm.html
diff --git a/docs/0.4.0/_modules/torch/nn/modules/linear.html b/docs/0.4.0/_modules/torch/nn/modules/linear.html
diff --git a/docs/0.4.0/_modules/torch/nn/modules/loss.html b/docs/0.4.0/_modules/torch/nn/modules/loss.html
diff --git a/docs/0.4.0/_modules/torch/nn/modules/module.html b/docs/0.4.0/_modules/torch/nn/modules/module.html
diff --git a/docs/0.4.0/_modules/torch/nn/modules/normalization.html b/docs/0.4.0/_modules/torch/nn/modules/normalization.html
diff --git a/docs/0.4.0/_modules/torch/nn/modules/padding.html b/docs/0.4.0/_modules/torch/nn/modules/padding.html
diff --git a/docs/0.4.0/_modules/torch/nn/modules/pixelshuffle.html b/docs/0.4.0/_modules/torch/nn/modules/pixelshuffle.html
diff --git a/docs/0.4.0/_modules/torch/nn/modules/pooling.html b/docs/0.4.0/_modules/torch/nn/modules/pooling.html
diff --git a/docs/0.4.0/_modules/torch/nn/modules/rnn.html b/docs/0.4.0/_modules/torch/nn/modules/rnn.html
diff --git a/docs/0.4.0/_modules/torch/nn/modules/sparse.html b/docs/0.4.0/_modules/torch/nn/modules/sparse.html
diff --git a/docs/0.4.0/_modules/torch/nn/modules/upsampling.html b/docs/0.4.0/_modules/torch/nn/modules/upsampling.html
diff --git a/docs/0.4.0/_modules/torch/nn/parallel/data_parallel.html b/docs/0.4.0/_modules/torch/nn/parallel/data_parallel.html
diff --git a/docs/0.4.0/_modules/torch/nn/parallel/distributed.html b/docs/0.4.0/_modules/torch/nn/parallel/distributed.html
diff --git a/docs/0.4.0/_modules/torch/nn/parameter.html b/docs/0.4.0/_modules/torch/nn/parameter.html
diff --git a/docs/0.4.0/_modules/torch/nn/utils/clip_grad.html b/docs/0.4.0/_modules/torch/nn/utils/clip_grad.html
diff --git a/docs/0.4.0/_modules/torch/nn/utils/rnn.html b/docs/0.4.0/_modules/torch/nn/utils/rnn.html
diff --git a/docs/0.4.0/_modules/torch/nn/utils/weight_norm.html b/docs/0.4.0/_modules/torch/nn/utils/weight_norm.html
diff --git a/docs/0.4.0/_modules/torch/onnx.html b/docs/0.4.0/_modules/torch/onnx.html
diff --git a/docs/0.4.0/_modules/torch/optim/adadelta.html b/docs/0.4.0/_modules/torch/optim/adadelta.html
diff --git a/docs/0.4.0/_modules/torch/optim/adagrad.html b/docs/0.4.0/_modules/torch/optim/adagrad.html
diff --git a/docs/0.4.0/_modules/torch/optim/adam.html b/docs/0.4.0/_modules/torch/optim/adam.html
diff --git a/docs/0.4.0/_modules/torch/optim/adamax.html b/docs/0.4.0/_modules/torch/optim/adamax.html
diff --git a/docs/0.4.0/_modules/torch/optim/asgd.html b/docs/0.4.0/_modules/torch/optim/asgd.html
diff --git a/docs/0.4.0/_modules/torch/optim/lbfgs.html b/docs/0.4.0/_modules/torch/optim/lbfgs.html
diff --git a/docs/0.4.0/_modules/torch/optim/lr_scheduler.html b/docs/0.4.0/_modules/torch/optim/lr_scheduler.html
diff --git a/docs/0.4.0/_modules/torch/optim/optimizer.html b/docs/0.4.0/_modules/torch/optim/optimizer.html
diff --git a/docs/0.4.0/_modules/torch/optim/rmsprop.html b/docs/0.4.0/_modules/torch/optim/rmsprop.html
diff --git a/docs/0.4.0/_modules/torch/optim/rprop.html b/docs/0.4.0/_modules/torch/optim/rprop.html
diff --git a/docs/0.4.0/_modules/torch/optim/sgd.html b/docs/0.4.0/_modules/torch/optim/sgd.html
diff --git a/docs/0.4.0/_modules/torch/optim/sparse_adam.html b/docs/0.4.0/_modules/torch/optim/sparse_adam.html
diff --git a/docs/0.4.0/_modules/torch/random.html b/docs/0.4.0/_modules/torch/random.html
diff --git a/docs/0.4.0/_modules/torch/serialization.html b/docs/0.4.0/_modules/torch/serialization.html
diff --git a/docs/0.4.0/_modules/torch/sparse.html b/docs/0.4.0/_modules/torch/sparse.html
diff --git a/docs/0.4.0/_modules/torch/storage.html b/docs/0.4.0/_modules/torch/storage.html
diff --git a/docs/0.4.0/_modules/torch/tensor.html b/docs/0.4.0/_modules/torch/tensor.html
diff --git a/docs/0.4.0/_modules/torch/utils/checkpoint.html b/docs/0.4.0/_modules/torch/utils/checkpoint.html
diff --git a/docs/0.4.0/_modules/torch/utils/cpp_extension.html b/docs/0.4.0/_modules/torch/utils/cpp_extension.html
diff --git a/docs/0.4.0/_modules/torch/utils/data/dataloader.html b/docs/0.4.0/_modules/torch/utils/data/dataloader.html
diff --git a/docs/0.4.0/_modules/torch/utils/data/dataset.html b/docs/0.4.0/_modules/torch/utils/data/dataset.html
diff --git a/docs/0.4.0/_modules/torch/utils/data/distributed.html b/docs/0.4.0/_modules/torch/utils/data/distributed.html
diff --git a/docs/0.4.0/_modules/torch/utils/data/sampler.html b/docs/0.4.0/_modules/torch/utils/data/sampler.html
diff --git a/docs/0.4.0/_modules/torch/utils/ffi.html b/docs/0.4.0/_modules/torch/utils/ffi.html
diff --git a/docs/0.4.0/_modules/torch/utils/model_zoo.html b/docs/0.4.0/_modules/torch/utils/model_zoo.html
diff --git a/docs/stable/_modules/torchvision.html → docs/0.4.0/_modules/torchvision.html b/docs/stable/_modules/torchvision.html → docs/0.4.0/_modules/torchvision.html
diff --git a/.../_modules/torchvision/datasets/cifar.html → .../_modules/torchvision/datasets/cifar.html b/.../_modules/torchvision/datasets/cifar.html → .../_modules/torchvision/datasets/cifar.html
diff --git a/...e/_modules/torchvision/datasets/coco.html → ...0/_modules/torchvision/datasets/coco.html b/...e/_modules/torchvision/datasets/coco.html → ...0/_modules/torchvision/datasets/coco.html
diff --git a/..._modules/torchvision/datasets/folder.html → ..._modules/torchvision/datasets/folder.html b/..._modules/torchvision/datasets/folder.html → ..._modules/torchvision/datasets/folder.html
diff --git a/...e/_modules/torchvision/datasets/lsun.html → ...0/_modules/torchvision/datasets/lsun.html b/...e/_modules/torchvision/datasets/lsun.html → ...0/_modules/torchvision/datasets/lsun.html
diff --git a/.../_modules/torchvision/datasets/mnist.html → .../_modules/torchvision/datasets/mnist.html b/.../_modules/torchvision/datasets/mnist.html → .../_modules/torchvision/datasets/mnist.html
diff --git a/...dules/torchvision/datasets/phototour.html → ...dules/torchvision/datasets/phototour.html b/...dules/torchvision/datasets/phototour.html → ...dules/torchvision/datasets/phototour.html
diff --git a/.../_modules/torchvision/datasets/stl10.html → .../_modules/torchvision/datasets/stl10.html b/.../_modules/torchvision/datasets/stl10.html → .../_modules/torchvision/datasets/stl10.html
diff --git a/...e/_modules/torchvision/datasets/svhn.html → ...0/_modules/torchvision/datasets/svhn.html b/...e/_modules/torchvision/datasets/svhn.html → ...0/_modules/torchvision/datasets/svhn.html
diff --git a/.../_modules/torchvision/models/alexnet.html → .../_modules/torchvision/models/alexnet.html b/.../_modules/torchvision/models/alexnet.html → .../_modules/torchvision/models/alexnet.html
diff --git a/..._modules/torchvision/models/densenet.html → ..._modules/torchvision/models/densenet.html b/..._modules/torchvision/models/densenet.html → ..._modules/torchvision/models/densenet.html
diff --git a/...modules/torchvision/models/inception.html → ...modules/torchvision/models/inception.html b/...modules/torchvision/models/inception.html → ...modules/torchvision/models/inception.html
diff --git a/...e/_modules/torchvision/models/resnet.html → ...0/_modules/torchvision/models/resnet.html b/...e/_modules/torchvision/models/resnet.html → ...0/_modules/torchvision/models/resnet.html
diff --git a/...odules/torchvision/models/squeezenet.html → ...odules/torchvision/models/squeezenet.html b/...odules/torchvision/models/squeezenet.html → ...odules/torchvision/models/squeezenet.html
diff --git a/...able/_modules/torchvision/models/vgg.html → ....4.0/_modules/torchvision/models/vgg.html b/...able/_modules/torchvision/models/vgg.html → ....4.0/_modules/torchvision/models/vgg.html
diff --git a/...es/torchvision/transforms/transforms.html → ...es/torchvision/transforms/transforms.html b/...es/torchvision/transforms/transforms.html → ...es/torchvision/transforms/transforms.html
diff --git a/docs/stable/_modules/torchvision/utils.html → docs/0.4.0/_modules/torchvision/utils.html b/docs/stable/_modules/torchvision/utils.html → docs/0.4.0/_modules/torchvision/utils.html
diff --git a/docs/0.4.0/_sources/autograd.rst.txt b/docs/0.4.0/_sources/autograd.rst.txt
@@ -0,0 +1,91 @@
+.. role:: hidden
+    :class: hidden-section
+
+Automatic differentiation package - torch.autograd
+==================================================
+
+.. automodule:: torch.autograd
+.. currentmodule:: torch.autograd
+
+.. autofunction:: backward
+
+.. autofunction:: grad
+
+.. _locally-disable-grad:
+
+Locally disabling gradient computation
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+.. autoclass:: no_grad
+
+.. autoclass:: enable_grad
+
+.. autoclass:: set_grad_enabled
+
+In-place operations on Tensors
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Supporting in-place operations in autograd is a hard matter, and we discourage
+their use in most cases. Autograd's aggressive buffer freeing and reuse makes
+it very efficient and there are very few occasions when in-place operations
+actually lower memory usage by any significant amount. Unless you're operating
+under heavy memory pressure, you might never need to use them.
+
+In-place correctness checks
+---------------------------
+
+All :class:`Tensor` s keep track of in-place operations applied to them, and
+if the implementation detects that a tensor was saved for backward in one of
+the functions, but it was modified in-place afterwards, an error will be raised
+once backward pass is started. This ensures that if you're using in-place
+functions and not seeing any errors, you can be sure that the computed
+gradients are correct.
+
+Variable (deprecated)
+^^^^^^^^^^^^^^^^^^^^^
+
+.. warning::
+    The Variable API has been deprecated: Variables are no longer necessary to
+    use autograd with tensors. Autograd automatically supports Tensors with
+    ``requires_grad`` set to ``True``. Below please find a quick guide on what
+    has changed:
+
+    - ``Variable(tensor)`` and ``Variable(tensor, requires_grad)`` still work as expected,
+      but they return Tensors instead of Variables.
+    - ``var.data`` is the same thing as ``tensor.data``.
+    - Methods such as ``var.backward(), var.detach(), var.register_hook()`` now work on tensors
+      with the same method names.
+
+    In addition, one can now create tensors with ``requires_grad=True`` using factory
+    methods such as :func:`torch.randn`, :func:`torch.zeros`, :func:`torch.ones`, and others
+    like the following:
+
+    ``autograd_tensor = torch.randn((2, 3, 4), requires_grad=True)``
+
+Tensor autograd functions
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+.. autoclass:: torch.Tensor
+    :members: backward, detach, detach_, register_hook, retain_grad
+
+:hidden:`Function`
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+.. autoclass:: Function
+    :members:
+
+Profiler
+^^^^^^^^
+
+Autograd includes a profiler that lets you inspect the cost of different
+operators inside your model - both on the CPU and GPU. There are two modes
+implemented at the moment - CPU-only using :class:`~torch.autograd.profiler.profile`.
+and nvprof based (registers both CPU and GPU activity) using
+:class:`~torch.autograd.profiler.emit_nvtx`.
+
+.. autoclass:: torch.autograd.profiler.profile
+    :members:
+
+.. autoclass:: torch.autograd.profiler.emit_nvtx
+    :members:
+
+.. autofunction:: torch.autograd.profiler.load_nvprof
diff --git a/docs/0.4.0/_sources/bottleneck.rst.txt b/docs/0.4.0/_sources/bottleneck.rst.txt
@@ -0,0 +1,59 @@
+torch.utils.bottleneck
+======================
+
+.. currentmodule:: torch.utils.bottleneck
+
+`torch.utils.bottleneck` is a tool that can be used as an initial step for
+debugging bottlenecks in your program. It summarizes runs of your script with
+the Python profiler and PyTorch's autograd profiler.
+
+Run it on the command line with
+
+::
+
+    python -m torch.utils.bottleneck /path/to/source/script.py [args]
+
+where [args] are any number of arguments to `script.py`, or run
+``python -m torch.utils.bottleneck -h`` for more usage instructions.
+
+.. warning::
+    Because your script will be profiled, please ensure that it exits in a
+    finite amount of time.
+
+.. warning::
+    Due to the asynchronous nature of CUDA kernels, when running against
+    CUDA code, the cProfile output and CPU-mode autograd profilers may
+    not show correct timings: the reported CPU time reports the amount of time
+    used to launch the kernels but does not include the time the kernel
+    spent executing on a GPU unless the operation does a synchronize.
+    Ops that do synchronize appear to be extremely expensive under regular
+    CPU-mode profilers.
+    In these case where timings are incorrect, the CUDA-mode autograd profiler
+    may be helpful.
+
+.. note::
+    To decide which (CPU-only-mode or CUDA-mode) autograd profiler output to
+    look at, you should first check if your script is CPU-bound
+    ("CPU total time is much greater than CUDA total time").
+    If it is CPU-bound, looking at the results of the CPU-mode autograd
+    profiler will help. If on the other hand your script spends most of its
+    time executing on the GPU, then it makes sense to start
+    looking for responsible CUDA operators in the output of the CUDA-mode
+    autograd profiler.
+
+    Of course the reality is much more complicated and your script might not be
+    in one of those two extremes depending on the part of the model you're
+    evaluating. If the profiler outputs don't help, you could try looking at
+    the result of :func:`torch.autograd.profiler.emit_nvtx()` with ``nvprof``.
+    However, please take into account that the NVTX overhead is very high and
+    often gives a heavily skewed timeline.
+
+.. warning::
+    If you are profiling CUDA code, the first profiler that ``bottleneck`` runs
+    (cProfile) will include the CUDA startup time (CUDA buffer allocation cost)
+    in its time reporting. This should not matter if your bottlenecks result
+    in code much slower than the CUDA startup time.
+
+For more complicated uses of the profilers (like in a multi-GPU case),
+please see https://docs.python.org/3/library/profile.html
+or :func:`torch.autograd.profiler.profile()` for more information.
diff --git a/docs/0.4.0/_sources/checkpoint.rst.txt b/docs/0.4.0/_sources/checkpoint.rst.txt
@@ -0,0 +1,6 @@
+torch.utils.checkpoint
+======================
+
+.. currentmodule:: torch.utils.checkpoint
+.. autofunction:: checkpoint
+.. autofunction:: checkpoint_sequential
diff --git a/docs/0.4.0/_sources/cpp_extension.rst.txt b/docs/0.4.0/_sources/cpp_extension.rst.txt
@@ -0,0 +1,11 @@
+torch.utils.cpp_extension
+=========================
+
+.. currentmodule:: torch.utils.cpp_extension
+.. autofunction:: CppExtension
+.. autofunction:: CUDAExtension
+.. autofunction:: BuildExtension
+.. autofunction:: load
+.. autofunction:: include_paths
+.. autofunction:: check_compiler_abi_compatibility
+.. autofunction:: verify_ninja_availability
diff --git a/docs/0.4.0/_sources/cuda.rst.txt b/docs/0.4.0/_sources/cuda.rst.txt
@@ -0,0 +1,55 @@
+torch.cuda
+===================================
+
+.. currentmodule:: torch.cuda
+
+.. automodule:: torch.cuda
+   :members:
+
+Random Number Generator
+-------------------------
+.. autofunction:: get_rng_state
+.. autofunction:: set_rng_state
+.. autofunction:: manual_seed
+.. autofunction:: manual_seed_all
+.. autofunction:: seed
+.. autofunction:: seed_all
+.. autofunction:: initial_seed
+
+
+Communication collectives
+-------------------------
+
+.. autofunction:: torch.cuda.comm.broadcast
+
+.. autofunction:: torch.cuda.comm.broadcast_coalesced
+
+.. autofunction:: torch.cuda.comm.reduce_add
+
+.. autofunction:: torch.cuda.comm.scatter
+
+.. autofunction:: torch.cuda.comm.gather
+
+Streams and events
+------------------
+
+.. autoclass:: Stream
+   :members:
+
+.. autoclass:: Event
+   :members:
+
+Memory management
+-----------------
+.. autofunction:: empty_cache
+.. autofunction:: memory_allocated
+.. autofunction:: max_memory_allocated
+.. autofunction:: memory_cached
+.. autofunction:: max_memory_cached
+
+NVIDIA Tools Extension (NVTX)
+-----------------------------
+
+.. autofunction:: torch.cuda.nvtx.mark
+.. autofunction:: torch.cuda.nvtx.range_push
+.. autofunction:: torch.cuda.nvtx.range_pop
diff --git a/docs/0.4.0/_sources/data.rst.txt b/docs/0.4.0/_sources/data.rst.txt
@@ -0,0 +1,14 @@
+torch.utils.data
+===================================
+
+.. automodule:: torch.utils.data
+.. autoclass:: Dataset
+.. autoclass:: TensorDataset
+.. autoclass:: ConcatDataset
+.. autoclass:: DataLoader
+.. autoclass:: torch.utils.data.sampler.Sampler
+.. autoclass:: torch.utils.data.sampler.SequentialSampler
+.. autoclass:: torch.utils.data.sampler.RandomSampler
+.. autoclass:: torch.utils.data.sampler.SubsetRandomSampler
+.. autoclass:: torch.utils.data.sampler.WeightedRandomSampler
+.. autoclass:: torch.utils.data.distributed.DistributedSampler