Low-level ops"

In fastai: Interface to 'fastai'

knitr::opts_chunk$set(echo = TRUE,eval = FALSE,echo = T)

Intro

The fastai library simplifies training fast and accurate neural nets using modern best practices. See the fastai website to get started. The library is based on research into deep learning best practices undertaken at fast.ai, and includes "out of the box" support for vision, text, tabular, and collab (collaborative filtering) models.

Dataset

Get dataset and build cnn_learner.

URLs_MNIST_SAMPLE()
tfms = aug_transforms(do_flip = FALSE)
path = 'mnist_sample'
bs = 20
data = 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$model[0][0][0][['in_channels']]
print(init)
# 3
learn$model[0][0][0][['in_channels']] %f% 1L
print(learn$model[0][0][0][['in_channels']])
# 1

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

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

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 same assignment.

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

Slicing

How to slice tensors? For less confusion, the slicing is the same as in python. narrow function requires a tensor and its dimensions. 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 list contain 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 from 0? Because indexing starts from 0 not from 1.

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 fastai Module 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$TensorDataset

bs = 32
train_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$shape; y$shape

nn = nn()
Functional = torch()$nn$functional

Model

Put your model into nn_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 automatically trained on GPU.

fastai documentation built on June 22, 2024, 11:15 a.m.