Hugging Face Datasets

Hugging Face Datasets 
!pip list | grep fastAIcourse
!pip list | grep datasets
fastAIcourse                  0.0.91      /home/ben/BENEDICT_Only/Benedict_Projects/Benedict_ML/fastAIcourse
datasets                      2.14.4
datasetsforecast              0.0.8
torch.set_printoptions(precision=2, linewidth=140, sci_mode=False)
torch.manual_seed(1)
mpl.rcParams['image.cmap'] = 'gray'
logging.disable(logging.WARNING)
name = "fashion_mnist"
ds_builder = load_dataset_builder(name)
print(ds_builder.info.description)
Fashion-MNIST is a dataset of Zalando's article images—consisting of a training set of
60,000 examples and a test set of 10,000 examples. Each example is a 28x28 grayscale image,
associated with a label from 10 classes. We intend Fashion-MNIST to serve as a direct drop-in
replacement for the original MNIST dataset for benchmarking machine learning algorithms.
It shares the same image size and structure of training and testing splits.

ds_builder.info.features
{'image': Image(decode=True, id=None),
 'label': ClassLabel(names=['T - shirt / top', 'Trouser', 'Pullover', 'Dress', 'Coat', 'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot'], id=None)}
ds_builder.info.splits
{'train': SplitInfo(name='train', num_bytes=31296607, num_examples=60000, shard_lengths=None, dataset_name='fashion_mnist'),
 'test': SplitInfo(name='test', num_bytes=5233810, num_examples=10000, shard_lengths=None, dataset_name='fashion_mnist')}
dsd = load_dataset(name)
dsd
DatasetDict({
    train: Dataset({
        features: ['image', 'label'],
        num_rows: 60000
    })
    test: Dataset({
        features: ['image', 'label'],
        num_rows: 10000
    })
})
train,test = dsd['train'],dsd['test']
train[0]
{'image': <PIL.PngImagePlugin.PngImageFile image mode=L size=28x28>,
 'label': 9}
x,y = ds_builder.info.features
x,y
('image', 'label')
x,y = 'image','label'
img = train[0][x]
img

xb = train[:5][x]
yb = train[:5][y]
xb, yb
([<PIL.PngImagePlugin.PngImageFile image mode=L size=28x28>,
  <PIL.PngImagePlugin.PngImageFile image mode=L size=28x28>,
  <PIL.PngImagePlugin.PngImageFile image mode=L size=28x28>,
  <PIL.PngImagePlugin.PngImageFile image mode=L size=28x28>,
  <PIL.PngImagePlugin.PngImageFile image mode=L size=28x28>],
 [9, 0, 0, 3, 0])
featy = train.features[y]
featy
ClassLabel(names=['T - shirt / top', 'Trouser', 'Pullover', 'Dress', 'Coat', 'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot'], id=None)
featy.int2str(yb)
['Ankle boot',
 'T - shirt / top',
 'T - shirt / top',
 'Dress',
 'T - shirt / top']
train['label'][:5]
[9, 0, 0, 3, 0]
Exported source 
def collate_fn(b):
    return {x:torch.stack([TF.to_tensor(o[x]) for o in b]),
            y:tensor([o[y] for o in b])}
dl = DataLoader(train, collate_fn=collate_fn, batch_size=16)
b = next(iter(dl))
b[x].shape,b[y]
(torch.Size([16, 1, 28, 28]),
 tensor([9, 0, 0, 3, 0, 2, 7, 2, 5, 5, 0, 9, 5, 5, 7, 9]))
Exported source 
def transforms(b):
    b[x] = [TF.to_tensor(o) for o in b[x]]
    return b
tds = train.with_transform(transforms)
dl = DataLoader(tds, batch_size=16)
b = next(iter(dl))
b[x].shape,b[y]
(torch.Size([16, 1, 28, 28]),
 tensor([9, 0, 0, 3, 0, 2, 7, 2, 5, 5, 0, 9, 5, 5, 7, 9]))
Exported source 
def _transformi(b): b[x] = [torch.flatten(TF.to_tensor(o)) for o in b[x]]
Exported source 
def inplace(f):
    def _f(b):
        f(b)
        return b
    return _f
transformi = inplace(_transformi)
r = train.with_transform(transformi)[0]
r[x].shape,r[y]
(torch.Size([784]), 9)
Exported source 
@inplace
def transformi(b): b[x] = [torch.flatten(TF.to_tensor(o)) for o in b[x]]
tdsf = train.with_transform(transformi)
r = tdsf[0]
r[x].shape,r[y]
(torch.Size([784]), 9)
d = dict(a=1,b=2,c=3)
ig = it emgetter('a','c')
ig(d)
(1, 3)
Exported source 
class D:
    def __getitem__(self, k): return 1 if k=='a' else 2 if k=='b' else 3
d = D()
ig(d)
(1, 3)
list(tdsf.features)
['image', 'label']
batch = dict(a=[1],b=[2]), dict(a=[3],b=[4])
default_collate(batch)
{'a': [tensor([1, 3])], 'b': [tensor([2, 4])]}
Exported source 
def collate_dict(ds):
    get = itemgetter(*ds.features)
    def _f(b): return get(default_collate(b))
    return _f
dlf = DataLoader(tdsf, batch_size=4, collate_fn=collate_dict(tdsf))
xb,yb = next(iter(dlf))
xb.shape,yb
(torch.Size([4, 784]), tensor([9, 0, 0, 3]))

Plotting images

b = next(iter(dl))
xb = b['image']
img = xb[0]
plt.imshow(img[0]);

Exported source 
@fc.delegates(plt.Axes.imshow)
def show_image(im, ax=None, figsize=None, title=None, noframe=True, **kwargs):
    "Show a PIL or PyTorch image on `ax`."
    if fc.hasattrs(im, ('cpu','permute','detach')):
        im = im.detach().cpu()
        if len(im.shape)==3 and im.shape[0]<5: im=im.permute(1,2,0)
    elif not isinstance(im,np.ndarray): im=np.array(im)
    if im.shape[-1]==1: im=im[...,0]
    if ax is None: _,ax = plt.subplots(figsize=figsize)
    ax.imshow(im, **kwargs)
    if title is not None: ax.set_title(title)
    ax.set_xticks([]) 
    ax.set_yticks([]) 
    if noframe: ax.axis('off')
    return ax
help(show_image)
Help on function show_image in module __main__:

show_image(im, ax=None, figsize=None, title=None, noframe=True, *, cmap=None, norm=None, aspect=None, interpolation=None, alpha=None, vmin=None, vmax=None, origin=None, extent=None, interpolation_stage=None, filternorm=True, filterrad=4.0, resample=None, url=None, data=None)
    Show a PIL or PyTorch image on `ax`.

show_image(img, figsize=(2,2));

fig,axs = plt.subplots(1,2)
show_image(img, axs[0])
show_image(xb[1], axs[1]);

Exported source 
@fc.delegates(plt.subplots, keep=True)
def subplots(
    nrows:int=1, # Number of rows in returned axes grid
    ncols:int=1, # Number of columns in returned axes grid
    figsize:tuple=None, # Width, height in inches of the returned figure
    imsize:int=3, # Size (in inches) of images that will be displayed in the returned figure
    suptitle:str=None, # Title to be set to returned figure
    **kwargs
): # fig and axs
    "A figure and set of subplots to display images of `imsize` inches"
    if figsize is None: figsize=(ncols*imsize, nrows*imsize)
    fig,ax = plt.subplots(nrows, ncols, figsize=figsize, **kwargs)
    if suptitle is not None: fig.suptitle(suptitle)
    if nrows*ncols==1: ax = np.array([ax])
    return fig,ax
Exported source 
from nbdev.showdoc import show_doc

source

subplots

 subplots (nrows:int=1, ncols:int=1, figsize:tuple=None, imsize:int=3,
           suptitle:str=None, sharex=False, sharey=False, squeeze=True,
           width_ratios=None, height_ratios=None, subplot_kw=None,
           gridspec_kw=None, **kwargs)

A figure and set of subplots to display images of imsize inches

Type Default Details
nrows int 1 Number of rows in returned axes grid
ncols int 1 Number of columns in returned axes grid
figsize tuple None Width, height in inches of the returned figure
imsize int 3 Size (in inches) of images that will be displayed in the returned figure
suptitle str None Title to be set to returned figure
sharex bool False
sharey bool False
squeeze bool True
width_ratios NoneType None
height_ratios NoneType None
subplot_kw NoneType None
gridspec_kw NoneType None
kwargs 
fig,axs = subplots(3,3, imsize=1)
imgs = xb[:8]
for ax,img in zip(axs.flat,imgs): show_image(img, ax)

–checking

Exported source 
def get_grid(
    n:int, # Number of axes
    nrows:int=None, # Number of rows, defaulting to `int(math.sqrt(n))`
    ncols:int=None, # Number of columns, defaulting to `ceil(n/rows)`
    title:str=None, # If passed, title set to the figure
    weight:str='bold', # Title font weight
    size:int=14, # Title font size
    **kwargs,
): # fig and axs
    "Return a grid of `n` axes, `rows` by `cols`"
    if nrows: ncols = ncols or int(np.floor(n/nrows))
    elif ncols: nrows = nrows or int(np.ceil(n/ncols))
    else:
        nrows = int(math.sqrt(n))
        ncols = int(np.floor(n/nrows))
    fig,axs = subplots(nrows, ncols, **kwargs)
    for i in range(n, nrows*ncols): axs.flat[i].set_axis_off()
    if title is not None: fig.suptitle(title, weight=weight, size=size)
    return fig,axs
fig,axs = get_grid(8, nrows=3, imsize=1)
for ax,img in zip(axs.flat,imgs): show_image(img, ax)

Exported source 
def show_images(ims:list, # Images to show
                nrows:int|None=None, # Number of rows in grid
                ncols:int|None=None, # Number of columns in grid (auto-calculated if None)
                titles:list|None=None, # Optional list of titles for each image
                **kwargs):
    "Show all images `ims` as subplots with `rows` using `titles`"
    axs = get_grid(len(ims), nrows, ncols, **kwargs)[1].flat
    for im,t,ax in zip_longest(ims, titles or [], axs): show_image(im, ax=ax, title=t)
yb = b['label']
lbls = yb[:8]
names = "Top Trouser Pullover Dress Coat Sandal Shirt Sneaker Bag Boot".split()
titles = itemgetter(*lbls)(names)
' '.join(titles)
'Boot Top Top Dress Top Pullover Sneaker Pullover'
show_images(imgs, imsize=1.7, titles=titles)

Exported source 
class DataLoaders:
    def __init__(self, *dls): self.train,self.valid = dls[:2]

    @classmethod
    def from_dd(cls, dd, batch_size, as_tuple=True, **kwargs):
        f = collate_dict(dd['train'])
        return cls(*get_dls(*dd.values(), bs=batch_size, collate_fn=f, **kwargs))
Back to top