Movatterモバイル変換

Dataset

Get dataset and buildcnn_learner.

URLs_MNIST_SAMPLE()tfms=aug_transforms(do_flip =FALSE)path='mnist_sample'bs=20data=ImageDataLoaders_from_folder(path,batch_tfms = tfms,size =26,bs = bs)learn=cnn_learner(data,xresnet50_deep(),metrics = accuracy)

Modify channels to 1:

init= learn$model[0][0][0][['in_channels']]print(init)# 3learn$model[0][0][0][['in_channels']]%f% 1Lprint(learn$model[0][0][0][['in_channels']])# 1

Here, one can observe a special assignment%f%. It helpsfor safe modification of layer parameters.

How to see and modify other parameters of the layer? First seenames:

names(learn$model[0][0][0])

Cnn layer parameters:

 [1] "add_module"                "apply"                     "bfloat16"                  [4] "bias"                      "buffers"                   "children"                  [7] "cpu"                       "cuda"                      "dilation"                 [10] "double"                    "dump_patches"              "eval"                     [13] "extra_repr"                "float"                     "forward"                  [16] "groups"                    "half"                      "has_children"             [19] "in_channels"               "kernel_size"               "load_state_dict"          [22] "modules"                   "named_buffers"             "named_children"           [25] "named_modules"             "named_parameters"          "out_channels"             [28] "output_padding"            "padding"                   "padding_mode"             [31] "parameters"                "register_backward_hook"    "register_buffer"          [34] "register_forward_hook"     "register_forward_pre_hook" "register_parameter"       [37] "requires_grad_"            "reset_parameters"          "share_memory"             [40] "state_dict"                "stride"                    "T_destination"            [43] "to"                        "train"                     "training"                 [46] "transposed"                "type"                      "weight"                   [49] "zero_grad"

Kernel size from(3, 3) to 9.

print(learn$model[0][0][0])# Conv2d(1, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False))learn$model[0][0][0][['kernel_size']]%f%  reticulate::tuple(list(9L,9L))print(learn$model[0][0][0])# Conv2d(1, 32, kernel_size=(9, 9), stride=(2, 2), padding=(1, 1), bias=False)

Inplace tensor ops

In addition, one could replace values inside tensors with the sameassignment.

For single in-place value modification:

x=tensor(c(1,2),c(3,4))# tensor([[1., 2.],#         [3., 4.]])print(x[0][0])# tensor(1.)# Now change it to 99.x[0][0]%f%99print(x[0][0])# tensor(99.)print(x)# tensor([[99.,  2.],#         [ 3.,  4.]])

Modify 2 or more values:

print(x[0])# tensor([99.,  2.])# change to 55, 55x[0]%f%c(55,55)# tensor([55., 55.])

Slicing

How to slice tensors? For less confusion, the slicing is the same asin python.narrow function requires a tensor and itsdimensions. Let’s see an example:

a=tensor(array(1:100,c(3,3,3,3)))a$shape# torch.Size([3, 3, 3, 3])

We can extract and play with tensor dimensions:

No change

First lets understand the tensor:

a %>% narrow('[:,:,:,:]')

tensor([[[[ 1, 28, 55],          [10, 37, 64],          [19, 46, 73]],         [[ 4, 31, 58],          [13, 40, 67],          [22, 49, 76]],         [[ 7, 34, 61],          [16, 43, 70],          [25, 52, 79]]],        [[[ 2, 29, 56],          [11, 38, 65],          [20, 47, 74]],         [[ 5, 32, 59],          [14, 41, 68],          [23, 50, 77]],         [[ 8, 35, 62],          [17, 44, 71],          [26, 53, 80]]],        [[[ 3, 30, 57],          [12, 39, 66],          [21, 48, 75]],         [[ 6, 33, 60],          [15, 42, 69],          [24, 51, 78]],         [[ 9, 36, 63],          [18, 45, 72],          [27, 54, 81]]]], dtype=torch.int32)

We could imagine that the tensor contains 3 R lists and each listcontain 3 matrices with 3 rows and 3 columns.

: without any indicated value before or after: will not modify the tensor.

1st list

How to extract 1st list from the tensor? Very simple:

a%>%narrow('[0,:,:,:]')

tensor([[[[ 1, 28, 55],          [10, 37, 64],          [19, 46, 73]],         [[ 4, 31, 58],          [13, 40, 67],          [22, 49, 76]],         [[ 7, 34, 61],          [16, 43, 70],          [25, 52, 79]]]], dtype=torch.int32)

Why from0? Because indexing starts from 0 not from1.

1st matrix

We could extract 1st matrix from all 3 lists.

a%>%narrow("[:,0,:,:]")

tensor([[[ 1, 28, 55],         [10, 37, 64],         [19, 46, 73]],        [[ 2, 29, 56],         [11, 38, 65],         [20, 47, 74]],        [[ 3, 30, 57],         [12, 39, 66],         [21, 48, 75]]], dtype=torch.int32)

1st matrix 1st row

a%>%narrow('[:,0,0,:]')

tensor([[ 1, 28, 55],        [ 2, 29, 56],        [ 3, 30, 57]], dtype=torch.int32)

2nd list 2nd matrix 2nd row

Extract 2nd list, 2nd matrix, and 2nd row:

a%>%narrow("[1,1,1,:]")

tensor([14, 41, 68], dtype=torch.int32)

NN module

How to build a model with fastaiModule class?Simple!

Prepare data:

library(magrittr)library(fastai)library(zeallot)if(!file.exists('mnist.pkl.gz')) {download.file('http://deeplearning.net/data/mnist/mnist.pkl.gz','mnist.pkl.gz')  R.utils::gunzip("mnist.pkl.gz",remove=FALSE)}c(c(x_train, y_train),c(x_valid, y_valid), res)%<-%  reticulate::py_load_object('mnist.pkl',encoding ='latin-1')x_train= x_train[1:500,1:784]x_valid= x_valid[1:500,1:784]y_train=as.integer(y_train)[1:500]y_valid=as.integer(y_valid)[1:500]

Plot example:

example=array_reshape(x_train[1,],c(28,28))example%>%show_image(cmap ='gray')%>%plot()

Dataloaders

Prepare data loaders and build a model:

TensorDataset=torch()$utils$data$TensorDatasetbs=32train_ds=TensorDataset(tensor(x_train),tensor(y_train))valid_ds=TensorDataset(tensor(x_valid),tensor(y_valid))train_dl=TfmdDL(train_ds,bs = bs,shuffle =TRUE)valid_dl=TfmdDL(valid_ds,bs =2* bs)dls=Data_Loaders(train_dl, valid_dl)one=one_batch(dls)x= one[[1]]y= one[[2]]x$shape; y$shapenn=nn()Functional=torch()$nn$functional

Model

Put your model intonn_module function:

model=nn_module(function(self) {  self$lin1= nn$Linear(784L, 50L,bias=TRUE)  self$lin2= nn$Linear(50L, 10L,bias=TRUE)  forward=function(y) {    x= self$lin1(y)    x= Functional$relu(x)    self$lin2(x)  }})

Conclusion

Fit the model:

learn=Learner(dls, model,loss_func=nn$CrossEntropyLoss(),metrics=accuracy)learn%>%summary()learn%>%fit_one_cycle(1,1e-2)

Note: if CUDA is available then the model will be automaticallytrained on GPU.