Get Inception feature maps Parameters ---------- inp : torch.autograd.Variable Input tensor of shape Bx3xHxW. Val

Create an `ItemList` in `path` from the inputs in the `cols` of `path/csv_name`

Create from a csv file in `path/csv_labels`.

Get the filenames in `path/csv_name` opened with `header`.

Create a `TextDataBunch` from texts in csv files. `kwargs` are passed to the dataloader creation.

Create a `DataBunch` suitable for collaborative filtering from `ratings`.

Create from a `DataFrame` `df`.

Create a `DataBunch` from `df` and `valid_idx` with `dep_var`. `kwargs` are passed to `DataBunch.create`.

Create from imagenet style dataset in `path` with `train`,`valid`,`test` subfolders (or provide `valid_pct`).

Create a `TextDataBunch` from text files in folders.

Create a GAN from `learn_gen` and `learn_crit`.

Create from list of `fnames` in `path`.

Create from list of `fnames` in `path` with re expression `pat`.

Gets the indices for the most similar images.

Create a `TextDataBunch` from tokens and labels. `kwargs` are passed to the dataloader creation.

Gets indices with top losses.

Critic to train a `GAN`.

Generate classes from `items` by taking the sorted unique values.

Generate classes from unique `items` and add `background`.

Open a COCO style json in `fname` and returns the lists of filenames (with maybe `prefix`) and labelled bboxes.

Display table of contents for given `mod_name`.

Return the inner state minus the layer groups.

get free memory (in MBs) for the currently selected gpu id, w/o emptying the cache

get free memory (in MBs) for the currently selected gpu id, after emptying the cache

get used memory (in MBs) for the currently selected gpu id, w/o emptying the cache

Reclaim GPU RAM if CUDA out of memory happened, or execution was interrupted

A decorator that runs `GPUMemTrace` w/ report on func

get [gpu_id, its_free_ram] for the first gpu with highest available RAM

Check whether we have at least `version` of `package`. Returns True on success, False otherwise.

Take the mean and std of `o`.

Applies `hook_func` to `module`, `input`, `output`.

Create a dictionary value to index from `a`.

Insert the function doc `cells` at their correct position and updates `pos_dict`.

Return `True` if schedule completed.

Join `path` to every file name in `fnames`.