from fastai.vision import *
from fastai.gen_doc.nbdoc import *

show_doc(AdaptiveConcatPool2d, title_level=3)

from fastai.gen_doc.nbdoc import *
from fastai.layers import * 

path = untar_data(URLs.MNIST_SAMPLE)
data = ImageDataBunch.from_folder(path)

def simple_cnn_max(actns:Collection[int], kernel_szs:Collection[int]=None,
               strides:Collection[int]=None) -> nn.Sequential:
    "CNN with `conv2d_relu` layers defined by `actns`, `kernel_szs` and `strides`"
    nl = len(actns)-1
    kernel_szs = ifnone(kernel_szs, [3]*nl)
    strides    = ifnone(strides   , [2]*nl)
    layers = [conv_layer(actns[i], actns[i+1], kernel_szs[i], stride=strides[i])
        for i in range(len(strides))]
    layers.append(nn.Sequential(nn.AdaptiveMaxPool2d(1), Flatten()))
    return nn.Sequential(*layers)

model = simple_cnn_max((3,16,16,2))
learner = Learner(data, model, metrics=[accuracy])
learner.fit(1)

def simple_cnn_avg(actns:Collection[int], kernel_szs:Collection[int]=None,
               strides:Collection[int]=None) -> nn.Sequential:
    "CNN with `conv2d_relu` layers defined by `actns`, `kernel_szs` and `strides`"
    nl = len(actns)-1
    kernel_szs = ifnone(kernel_szs, [3]*nl)
    strides    = ifnone(strides   , [2]*nl)
    layers = [conv_layer(actns[i], actns[i+1], kernel_szs[i], stride=strides[i])
        for i in range(len(strides))]
    layers.append(nn.Sequential(nn.AdaptiveAvgPool2d(1), Flatten()))
    return nn.Sequential(*layers)

model = simple_cnn_avg((3,16,16,2))
learner = Learner(data, model, metrics=[accuracy])
learner.fit(1)

def simple_cnn(actns:Collection[int], kernel_szs:Collection[int]=None,
               strides:Collection[int]=None) -> nn.Sequential:
    "CNN with `conv2d_relu` layers defined by `actns`, `kernel_szs` and `strides`"
    nl = len(actns)-1
    kernel_szs = ifnone(kernel_szs, [3]*nl)
    strides    = ifnone(strides   , [2]*nl)
    layers = [conv_layer(actns[i], actns[i+1], kernel_szs[i], stride=strides[i])
        for i in range(len(strides))]
    layers.append(nn.Sequential(AdaptiveConcatPool2d(1), Flatten()))
    return nn.Sequential(*layers)

model = simple_cnn((3,16,16,2))
learner = Learner(data, model, metrics=[accuracy])
learner.fit(1)

show_doc(Lambda, title_level=3)

model = nn.Sequential(
    nn.Conv2d(3,  16, kernel_size=3, stride=2, padding=1), nn.ReLU(),
    nn.Conv2d(16, 16, kernel_size=3, stride=2, padding=1), nn.ReLU(),
    nn.Conv2d(16, 10, kernel_size=3, stride=2, padding=1), nn.ReLU(),
    nn.AdaptiveAvgPool2d(1),
)

model.cuda()

for xb, yb in data.train_dl:
    out = (model(*[xb]))
    print(out.size())
    break

model = nn.Sequential(
    nn.Conv2d(3,  16, kernel_size=3, stride=2, padding=1), nn.ReLU(),
    nn.Conv2d(16, 16, kernel_size=3, stride=2, padding=1), nn.ReLU(),
    nn.Conv2d(16, 10, kernel_size=3, stride=2, padding=1), nn.ReLU(),
    nn.AdaptiveAvgPool2d(1),
    Lambda(lambda x: x.view(x.size(0),-1))
)

model.cuda()

for xb, yb in data.train_dl:
    out = (model(*[xb]))
    print(out.size())
    break

show_doc(Flatten)

model = nn.Sequential(
    nn.Conv2d(3,  16, kernel_size=3, stride=2, padding=1), nn.ReLU(),
    nn.Conv2d(16, 16, kernel_size=3, stride=2, padding=1), nn.ReLU(),
    nn.Conv2d(16, 10, kernel_size=3, stride=2, padding=1), nn.ReLU(),
    nn.AdaptiveAvgPool2d(1),
    Flatten(),
)

model.cuda()

for xb, yb in data.train_dl:
    out = (model(*[xb]))
    print(out.size())
    break

show_doc(PoolFlatten)

model = nn.Sequential(
    nn.Conv2d(3,  16, kernel_size=3, stride=2, padding=1), nn.ReLU(),
    nn.Conv2d(16, 16, kernel_size=3, stride=2, padding=1), nn.ReLU(),
    nn.Conv2d(16, 10, kernel_size=3, stride=2, padding=1), nn.ReLU(),
    PoolFlatten()
)

model.cuda()

for xb, yb in data.train_dl:
    out = (model(*[xb]))
    print(out.size())
    break

show_doc(ResizeBatch)

a = torch.tensor([[1., -1.], [1., -1.]])[None]
print(a)

out = ResizeBatch(4)
print(out(a))

show_doc(Debugger, title_level=3)

show_doc(PixelShuffle_ICNR, title_level=3)

show_doc(MergeLayer, title_level=3)

show_doc(PartialLayer, title_level=3)

show_doc(SigmoidRange, title_level=3)

show_doc(SequentialEx, title_level=3)

show_doc(SelfAttention, title_level=3)

show_doc(BatchNorm1dFlat, title_level=3)

show_doc(FlattenedLoss, title_level=3)

show_doc(BCEFlat)

show_doc(BCEWithLogitsFlat)

show_doc(CrossEntropyFlat)

show_doc(MSELossFlat)

show_doc(NoopLoss)

show_doc(WassersteinLoss)

show_doc(bn_drop_lin, doc_string=False)

show_doc(conv2d)

show_doc(conv2d_trans)

show_doc(conv_layer, doc_string=False)

show_doc(embedding, doc_string=False)

show_doc(relu)

show_doc(res_block)

show_doc(sigmoid_range)

show_doc(simple_cnn)

show_doc(batchnorm_2d)

show_doc(icnr)

show_doc(trunc_normal_)

show_doc(icnr)

show_doc(NormType)

show_doc(Debugger.forward)

show_doc(Lambda.forward)

show_doc(AdaptiveConcatPool2d.forward)

show_doc(NoopLoss.forward)

show_doc(PixelShuffle_ICNR.forward)

show_doc(WassersteinLoss.forward)

show_doc(MergeLayer.forward)

show_doc(SigmoidRange.forward)

show_doc(MergeLayer.forward)

show_doc(SelfAttention.forward)

show_doc(SequentialEx.forward)

show_doc(SequentialEx.append)

show_doc(SequentialEx.extend)

show_doc(SequentialEx.insert)

show_doc(PartialLayer.forward)

show_doc(BatchNorm1dFlat.forward)

show_doc(Flatten.forward)

show_doc(View)

show_doc(ResizeBatch.forward)

show_doc(View.forward)