AI-TensorFlow-Libtensorflow
view release on metacpan or search on metacpan
lib/AI/TensorFlow/Libtensorflow/Manual/Notebook/InferenceUsingTFHubCenterNetObjDetect.pod view on Meta::CPAN
## DO NOT EDIT. Generated from notebook/InferenceUsingTFHubCenterNetObjDetect.ipynb using ./maint/process-notebook.pl.
use strict;
use warnings;
use utf8;
use constant IN_IPERL => !! $ENV{PERL_IPERL_RUNNING};
no if IN_IPERL, warnings => 'redefine'; # fewer messages when re-running cells
use feature qw(say state postderef);
use Syntax::Construct qw(each-array);
use lib::projectroot qw(lib);
BEGIN {
if( IN_IPERL ) {
$ENV{TF_CPP_MIN_LOG_LEVEL} = 3;
}
require AI::TensorFlow::Libtensorflow;
}
lib/AI/TensorFlow/Libtensorflow/Manual/Notebook/InferenceUsingTFHubCenterNetObjDetect.pod view on Meta::CPAN
# image_size => [width, height] (but usually square images)
my %model_name_to_params = (
centernet_hourglass_512x512 => {
handle => 'https://tfhub.dev/tensorflow/centernet/hourglass_512x512/1',
image_size => [ 512, 512 ],
},
);
my $model_name = 'centernet_hourglass_512x512';
say "Selected model: $model_name : $model_name_to_params{$model_name}{handle}";
my $model_uri = URI->new( $model_name_to_params{$model_name}{handle} );
$model_uri->query_form( 'tf-hub-format' => 'compressed' );
my $model_base = substr( $model_uri->path, 1 ) =~ s,/,_,gr;
my $model_archive_path = "${model_base}.tar.gz";
my $http = HTTP::Tiny->new;
for my $download ( [ $model_uri => $model_archive_path ],) {
my ($uri, $path) = @$download;
say "Downloading $uri to $path";
next if -e $path;
$http->mirror( $uri, $path );
}
use Archive::Extract;
my $ae = Archive::Extract->new( archive => $model_archive_path );
die "Could not extract archive" unless $ae->extract( to => $model_base );
my $saved_model = path($model_base)->child('saved_model.pb');
say "Saved model is in $saved_model" if -f $saved_model;
# Get the labels
my $response = $http->get('https://raw.githubusercontent.com/tensorflow/models/a4944a57ad2811e1f6a7a87589a9fc8a776e8d3c/object_detection/data/mscoco_label_map.pbtxt');
my %labels_map = $response->{content} =~ m<
(?:item \s+ \{ \s+
\Qname:\E \s+ "[^"]+" \s+
\Qid:\E \s+ (\d+) \s+
\Qdisplay_name:\E \s+ "([^"]+)" \s+
})+
>sgx;
my $label_count = List::Util::max keys %labels_map;
say "We have a label count of $label_count. These labels include: ",
join ", ", List::Util::head( 5, @labels_map{ sort keys %labels_map } );
my @tags = ( 'serve' );
if( File::Which::which('saved_model_cli')) {
local $ENV{TF_CPP_MIN_LOG_LEVEL} = 3; # quiet the TensorFlow logger for the following command
system(qw(saved_model_cli show),
qw(--dir) => $model_base,
qw(--tag_set) => join(',', @tags),
qw(--signature_def) => 'serving_default'
) == 0 or die "Could not run saved_model_cli";
} else {
say "Install the tensorflow Python package to get the `saved_model_cli` command.";
}
my $opt = AI::TensorFlow::Libtensorflow::SessionOptions->New;
my $graph = AI::TensorFlow::Libtensorflow::Graph->New;
my $session = AI::TensorFlow::Libtensorflow::Session->LoadFromSavedModel(
$opt, undef, $model_base, \@tags, $graph, undef, $s
);
AssertOK($s);
lib/AI/TensorFlow/Libtensorflow/Manual/Notebook/InferenceUsingTFHubCenterNetObjDetect.pod view on Meta::CPAN
),
);
}
sub load_image_to_pdl {
my ($uri, $image_size) = @_;
my $http = HTTP::Tiny->new;
my $response = $http->get( $uri );
die "Could not fetch image from $uri" unless $response->{success};
say "Downloaded $uri";
my $img = Imager->new;
$img->read( data => $response->{content} );
# Create PDL ndarray from Imager data in-memory.
my $data;
$img->write( data => \$data, type => 'raw' )
or die "could not write ". $img->errstr;
die "Image does not have 3 channels, it has @{[ $img->getchannels ]} channels"
lib/AI/TensorFlow/Libtensorflow/Manual/Notebook/InferenceUsingTFHubCenterNetObjDetect.pod view on Meta::CPAN
$gp->close;
IPerl->png( bytestream => path($plot_output_path)->slurp_raw ) if IN_IPERL;
use Filesys::DiskUsage qw/du/;
my $total = du( { 'human-readable' => 1, dereference => 1 },
$model_archive_path, $model_base );
say "Disk space usage: $total"; undef;
__END__
=pod
=encoding UTF-8
=head1 NAME
AI::TensorFlow::Libtensorflow::Manual::Notebook::InferenceUsingTFHubCenterNetObjDetect - Using TensorFlow to do object detection using a pre-trained model
lib/AI/TensorFlow/Libtensorflow/Manual/Notebook/InferenceUsingTFHubCenterNetObjDetect.pod view on Meta::CPAN
=head2 Load the library
First, we need to load the C<AI::TensorFlow::Libtensorflow> library and more helpers. We then create an C<AI::TensorFlow::Libtensorflow::Status> object and helper function to make sure that the calls to the C<libtensorflow> C library are working prop...
use strict;
use warnings;
use utf8;
use constant IN_IPERL => !! $ENV{PERL_IPERL_RUNNING};
no if IN_IPERL, warnings => 'redefine'; # fewer messages when re-running cells
use feature qw(say state postderef);
use Syntax::Construct qw(each-array);
use lib::projectroot qw(lib);
BEGIN {
if( IN_IPERL ) {
$ENV{TF_CPP_MIN_LOG_LEVEL} = 3;
}
require AI::TensorFlow::Libtensorflow;
}
lib/AI/TensorFlow/Libtensorflow/Manual/Notebook/InferenceUsingTFHubCenterNetObjDetect.pod view on Meta::CPAN
# image_size => [width, height] (but usually square images)
my %model_name_to_params = (
centernet_hourglass_512x512 => {
handle => 'https://tfhub.dev/tensorflow/centernet/hourglass_512x512/1',
image_size => [ 512, 512 ],
},
);
my $model_name = 'centernet_hourglass_512x512';
say "Selected model: $model_name : $model_name_to_params{$model_name}{handle}";
We download the model to the current directory and then extract the model to a folder with the name given in C<$model_base>.
my $model_uri = URI->new( $model_name_to_params{$model_name}{handle} );
$model_uri->query_form( 'tf-hub-format' => 'compressed' );
my $model_base = substr( $model_uri->path, 1 ) =~ s,/,_,gr;
my $model_archive_path = "${model_base}.tar.gz";
my $http = HTTP::Tiny->new;
for my $download ( [ $model_uri => $model_archive_path ],) {
my ($uri, $path) = @$download;
say "Downloading $uri to $path";
next if -e $path;
$http->mirror( $uri, $path );
}
use Archive::Extract;
my $ae = Archive::Extract->new( archive => $model_archive_path );
die "Could not extract archive" unless $ae->extract( to => $model_base );
my $saved_model = path($model_base)->child('saved_model.pb');
say "Saved model is in $saved_model" if -f $saved_model;
We need to download the COCO 2017 classification labels and parse out the mapping from the numeric index to the textual descriptions.
# Get the labels
my $response = $http->get('https://raw.githubusercontent.com/tensorflow/models/a4944a57ad2811e1f6a7a87589a9fc8a776e8d3c/object_detection/data/mscoco_label_map.pbtxt');
my %labels_map = $response->{content} =~ m<
(?:item \s+ \{ \s+
\Qname:\E \s+ "[^"]+" \s+
\Qid:\E \s+ (\d+) \s+
\Qdisplay_name:\E \s+ "([^"]+)" \s+
})+
>sgx;
my $label_count = List::Util::max keys %labels_map;
say "We have a label count of $label_count. These labels include: ",
join ", ", List::Util::head( 5, @labels_map{ sort keys %labels_map } );
=head2 Load the model and session
We define the tag set C<[ 'serve' ]> which we will use to load the model.
my @tags = ( 'serve' );
We can examine what computations are contained in the graph in terms of the names of the inputs and outputs of an operation found in the graph by running C<saved_model_cli>.
if( File::Which::which('saved_model_cli')) {
local $ENV{TF_CPP_MIN_LOG_LEVEL} = 3; # quiet the TensorFlow logger for the following command
system(qw(saved_model_cli show),
qw(--dir) => $model_base,
qw(--tag_set) => join(',', @tags),
qw(--signature_def) => 'serving_default'
) == 0 or die "Could not run saved_model_cli";
} else {
say "Install the tensorflow Python package to get the `saved_model_cli` command.";
}
The above C<saved_model_cli> output shows that the model input is at C<serving_default_input_tensor:0> which means the operation named C<serving_default_input_tensor> at index C<0> and there are multiple outputs with different shapes.
Per the L<model description|https://tfhub.dev/tensorflow/centernet/hourglass_512x512/1> on TensorFlow Hub:
=over 2
B<Inputs>
lib/AI/TensorFlow/Libtensorflow/Manual/Notebook/InferenceUsingTFHubCenterNetObjDetect.pod view on Meta::CPAN
Then we turn the C<Imager> data into a C<PDL> ndarray. Since we just need the 3 channels of the image as they are, they can be stored directly in a C<PDL> ndarray of type C<byte>.
The reason why we need to concatenate the C<PDL> ndarrays here despite the model only taking a single image at a time is to get an ndarray with four (4) dimensions with the last C<PDL> dimension of size one (1).
sub load_image_to_pdl {
my ($uri, $image_size) = @_;
my $http = HTTP::Tiny->new;
my $response = $http->get( $uri );
die "Could not fetch image from $uri" unless $response->{success};
say "Downloaded $uri";
my $img = Imager->new;
$img->read( data => $response->{content} );
# Create PDL ndarray from Imager data in-memory.
my $data;
$img->write( data => \$data, type => 'raw' )
or die "could not write ". $img->errstr;
die "Image does not have 3 channels, it has @{[ $img->getchannels ]} channels"
lib/AI/TensorFlow/Libtensorflow/Manual/Notebook/InferenceUsingTFHubCenterNetObjDetect.pod view on Meta::CPAN
IPerl->png( bytestream => path($plot_output_path)->slurp_raw ) if IN_IPERL;
=head1 RESOURCE USAGE
use Filesys::DiskUsage qw/du/;
my $total = du( { 'human-readable' => 1, dereference => 1 },
$model_archive_path, $model_base );
say "Disk space usage: $total"; undef;
=head1 CPANFILE
requires 'AI::TensorFlow::Libtensorflow';
requires 'AI::TensorFlow::Libtensorflow::DataType';
requires 'Archive::Extract';
requires 'Data::Printer';
requires 'Data::Printer::Filter::PDL';
requires 'FFI::Platypus::Buffer';
requires 'FFI::Platypus::Memory';
lib/AI/TensorFlow/Libtensorflow/Manual/Notebook/InferenceUsingTFHubEnformerGeneExprPredModel.pod view on Meta::CPAN
my $clinvar_uri = URI->new('https://ftp.ncbi.nlm.nih.gov/pub/clinvar/vcf_GRCh38/clinvar.vcf.gz');
my $clinvar_path = 'clinvar.vcf.gz';
my $http = HTTP::Tiny->new;
for my $download ( [ $model_uri => $model_archive_path ],
[ $targets_uri => $targets_path ],
[ $hg_uri => $hg_gz_path ],
[ $clinvar_uri => $clinvar_path ],) {
my ($uri, $path) = @$download;
say "Downloading $uri to $path";
next if -e $path;
$http->mirror( $uri, $path );
}
use Archive::Extract;
$Archive::Extract::DEBUG = 1;
$Archive::Extract::PREFER_BIN = 1; # for the larger model, prefer bin
if( ! -e $model_base ) {
my $ae = Archive::Extract->new( archive => $model_archive_path );
die "Could not extract archive" unless $ae->extract( to => $model_base );
}
use Digest::file qw(digest_file_hex);
if( digest_file_hex( $hg_gz_path, "MD5" ) eq $hg_md5_digest ) {
say "MD5 sum for $hg_gz_path OK";
} else {
die "Digest for $hg_gz_path failed";
}
(my $hg_uncompressed_path = $hg_gz_path) =~ s/\.gz$//;
my $hg_bgz_path = "${hg_uncompressed_path}.bgz";
use IPC::Run;
if( ! -e $hg_bgz_path ) {
lib/AI/TensorFlow/Libtensorflow/Manual/Notebook/InferenceUsingTFHubEnformerGeneExprPredModel.pod view on Meta::CPAN
my (@rest) = @_;
if( File::Which::which('saved_model_cli')) {
system(qw(saved_model_cli), @rest ) == 0
or die "Could not run saved_model_cli";
} else {
warn "saved_model_cli(): Install the tensorflow Python package to get the `saved_model_cli` command.\n";
return -1;
}
}
say "Checking with saved_model_cli scan:";
saved_model_cli( qw(scan),
qw(--dir) => $model_base,
);
saved_model_cli( qw(show),
qw(--dir) => $model_base,
qw(--all),
);
my $new_model_base = "${model_base}_new";
lib/AI/TensorFlow/Libtensorflow/Manual/Notebook/InferenceUsingTFHubEnformerGeneExprPredModel.pod view on Meta::CPAN
EOF
saved_model_cli( qw(show),
qw(--dir) => $new_model_base,
qw(--all),
);
my $model_central_base_pairs_length = 114_688; # bp
my $model_central_base_pair_window_size = 128; # bp / prediction
say "Number of predictions: ", $model_central_base_pairs_length / $model_central_base_pair_window_size;
use Data::Frame;
my $df = Data::Frame->from_csv( $targets_path, sep => "\t" )
->transform({
file => sub {
my ($col, $df) = @_;
# clean up the paths in 'file' column
[map { join "/", (split('/', $_))[7..8] } $col->list];
}
});
say "Number of targets: ", $df->nrow;
say "";
say "First 5:";
say $df->head(5);
my $opt = AI::TensorFlow::Libtensorflow::SessionOptions->New;
my @tags = ( 'serve' );
my $graph = AI::TensorFlow::Libtensorflow::Graph->New;
my $session = AI::TensorFlow::Libtensorflow::Session->LoadFromSavedModel(
$opt, undef, $new_model_base, \@tags, $graph, undef, $s
);
AssertOK($s);
lib/AI/TensorFlow/Libtensorflow/Manual/Notebook/InferenceUsingTFHubEnformerGeneExprPredModel.pod view on Meta::CPAN
my $from_alphabet_tr = $from_alphabet . lc $from_alphabet;
my $to_alphabet_tr = $to_alphabet x 2;
my $p = zeros(byte, bytes::length($seq));
my $p_dataref = $p->get_dataref;
${ $p_dataref } = $seq;
eval "tr/$from_alphabet_tr/$to_alphabet_tr/" for ${ $p_dataref };
$p->upd_data;
my $encoder = append(float(0), identity(float(length($from_alphabet)-1)) );
say "Encoder is\n", $encoder->info, $encoder if $SHOW_ENCODER;
my $encoded = $encoder->index( $p->dummy(0) );
return $encoded;
}
####
{
say "Testing one-hot encoding:\n";
my $onehot_test_seq = "ACGTNtgcan";
my $test_encoded = one_hot_dna( $onehot_test_seq );
$SHOW_ENCODER = 0;
say "One-hot encoding of sequence '$onehot_test_seq' is:";
say $test_encoded->info, $test_encoded;
}
package Interval {
use Bio::Location::Simple ();
use parent qw(Bio::Location::Simple);
sub center {
my $self = shift;
lib/AI/TensorFlow/Libtensorflow/Manual/Notebook/InferenceUsingTFHubEnformerGeneExprPredModel.pod view on Meta::CPAN
use overload '""' => \&_op_stringify;
sub _op_stringify { sprintf "%s:%s", $_[0]->seq_id // "(no sequence)", $_[0]->to_FTstring }
}
#####
{
say "Testing interval resizing:\n";
sub _debug_resize {
my ($interval, $to, $msg) = @_;
my $resized_interval = $interval->resize($to);
die "Wrong interval size for $interval --($to)--> $resized_interval"
unless $resized_interval->length == $to;
say sprintf "Interval: %s -> %s, length %2d : %s",
$interval,
$resized_interval, $resized_interval->length,
$msg;
}
for my $interval_spec ( [4, 8], [5, 8], [5, 9], [6, 9]) {
my ($start, $end) = @$interval_spec;
my $test_interval = Interval->new( -seq_id => 'chr11', -start => $start, -end => $end );
say sprintf "Testing interval %s with length %d", $test_interval, $test_interval->length;
say "-----";
for(0..5) {
my $base = $test_interval->length;
my $to = $base + $_;
_debug_resize $test_interval, $to, "$base -> $to (+ $_)";
}
say "";
}
}
undef;
use Bio::DB::HTS::Faidx;
my $hg_db = Bio::DB::HTS::Faidx->new( $hg_bgz_path );
lib/AI/TensorFlow/Libtensorflow/Manual/Notebook/InferenceUsingTFHubEnformerGeneExprPredModel.pod view on Meta::CPAN
sprintf "%s...%s (length %d)", uc substr($seq, 0, $n), uc substr($seq, -$n), length $seq;
} else {
sprintf "%s (length %d)", uc $seq, length $seq;
}
}
####
{
say "Testing sequence extraction:";
say "1 base: ", seq_info
extract_sequence( $hg_db,
Interval->new( -seq_id => 'chr11',
-start => 35_082_742 + 1,
-end => 35_082_742 + 1 ) );
say "3 bases: ", seq_info
extract_sequence( $hg_db,
Interval->new( -seq_id => 'chr11',
-start => 1,
-end => 1 )->resize(3) );
say "5 bases: ", seq_info
extract_sequence( $hg_db,
Interval->new( -seq_id => 'chr11',
-start => $hg_db->length('chr11'),
-end => $hg_db->length('chr11') )->resize(5) );
say "chr11 is of length ", $hg_db->length('chr11');
say "chr11 bases: ", seq_info
extract_sequence( $hg_db,
Interval->new( -seq_id => 'chr11',
-start => 1,
-end => $hg_db->length('chr11') )->resize( $hg_db->length('chr11') ) );
}
my $target_interval = Interval->new( -seq_id => 'chr11',
-start => 35_082_742 + 1, # BioPerl is 1-based
-end => 35_197_430 );
say "Target interval: $target_interval with length @{[ $target_interval->length ]}";
die "Target interval is not $model_central_base_pairs_length bp long"
unless $target_interval->length == $model_central_base_pairs_length;
say "Target sequence is ", seq_info extract_sequence( $hg_db, $target_interval );
say "";
my $resized_interval = $target_interval->resize( $model_sequence_length );
say "Resized interval: $resized_interval with length @{[ $resized_interval->length ]}";
die "resize() is not working properly!" unless $resized_interval->length == $model_sequence_length;
my $seq = extract_sequence( $hg_db, $resized_interval );
say "Resized sequence is ", seq_info($seq);
my $sequence_one_hot = one_hot_dna( $seq )->dummy(-1);
say $sequence_one_hot->info; undef;
use Devel::Timer;
my $t = Devel::Timer->new;
$t->mark('prediction of sequence');
my $predictions = $predict_on_batch->( $session, FloatPDLTOTFTensor( $sequence_one_hot ) );
$t->mark('End of prediction of sequence');
p $predictions;
$t->mark('END');
$t->report();
my $predictions_p = FloatTFTensorToPDL($predictions)->slice(',,(0)');
say $predictions_p->info; undef;
my @tracks = (
[ 'DNASE:CD14-positive monocyte female' => 41 => $predictions_p->slice('(41)') ],
[ 'DNASE:keratinocyte female' => 42 => $predictions_p->slice('(42)') ],
[ 'CHIP:H3K27ac:keratinocyte female' => 706 => $predictions_p->slice('(706)')],
[ 'CAGE:Keratinocyte - epidermal' => 4799 => log10(1 + $predictions_p->slice('(4799)')) ],
);
use PDL::Graphics::Gnuplot;
lib/AI/TensorFlow/Libtensorflow/Manual/Notebook/InferenceUsingTFHubEnformerGeneExprPredModel.pod view on Meta::CPAN
$targets_path,
$hg_gz_path,
$hg_bgz_path, $hg_bgz_fai_path,
$clinvar_path,
$plot_output_path,
);
say "Disk space usage: $total"; undef;
__END__
=pod
=encoding UTF-8
=head1 NAME
AI::TensorFlow::Libtensorflow::Manual::Notebook::InferenceUsingTFHubEnformerGeneExprPredModel - Using TensorFlow to do gene expression prediction using a pre-trained model
lib/AI/TensorFlow/Libtensorflow/Manual/Notebook/InferenceUsingTFHubEnformerGeneExprPredModel.pod view on Meta::CPAN
my $clinvar_uri = URI->new('https://ftp.ncbi.nlm.nih.gov/pub/clinvar/vcf_GRCh38/clinvar.vcf.gz');
my $clinvar_path = 'clinvar.vcf.gz';
my $http = HTTP::Tiny->new;
for my $download ( [ $model_uri => $model_archive_path ],
[ $targets_uri => $targets_path ],
[ $hg_uri => $hg_gz_path ],
[ $clinvar_uri => $clinvar_path ],) {
my ($uri, $path) = @$download;
say "Downloading $uri to $path";
next if -e $path;
$http->mirror( $uri, $path );
}
B<STREAM (STDOUT)>:
Downloading https://tfhub.dev/deepmind/enformer/1?tf-hub-format=compressed to deepmind_enformer_1.tar.gz
Downloading https://raw.githubusercontent.com/calico/basenji/master/manuscripts/cross2020/targets_human.txt to targets_human.txt
Downloading http://hgdownload.cse.ucsc.edu/goldenPath/hg38/bigZips/hg38.fa.gz to hg38.fa.gz
Downloading https://ftp.ncbi.nlm.nih.gov/pub/clinvar/vcf_GRCh38/clinvar.vcf.gz to clinvar.vcf.gz
lib/AI/TensorFlow/Libtensorflow/Manual/Notebook/InferenceUsingTFHubEnformerGeneExprPredModel.pod view on Meta::CPAN
use Archive::Extract;
$Archive::Extract::DEBUG = 1;
$Archive::Extract::PREFER_BIN = 1; # for the larger model, prefer bin
if( ! -e $model_base ) {
my $ae = Archive::Extract->new( archive => $model_archive_path );
die "Could not extract archive" unless $ae->extract( to => $model_base );
}
use Digest::file qw(digest_file_hex);
if( digest_file_hex( $hg_gz_path, "MD5" ) eq $hg_md5_digest ) {
say "MD5 sum for $hg_gz_path OK";
} else {
die "Digest for $hg_gz_path failed";
}
B<STREAM (STDOUT)>:
MD5 sum for hg38.fa.gz OK
B<RESULT>:
lib/AI/TensorFlow/Libtensorflow/Manual/Notebook/InferenceUsingTFHubEnformerGeneExprPredModel.pod view on Meta::CPAN
my (@rest) = @_;
if( File::Which::which('saved_model_cli')) {
system(qw(saved_model_cli), @rest ) == 0
or die "Could not run saved_model_cli";
} else {
warn "saved_model_cli(): Install the tensorflow Python package to get the `saved_model_cli` command.\n";
return -1;
}
}
say "Checking with saved_model_cli scan:";
saved_model_cli( qw(scan),
qw(--dir) => $model_base,
);
B<STREAM (STDOUT)>:
Checking with saved_model_cli scan:
MetaGraph with tag set ['serve'] does not contain the default denylisted ops: {'ReadFile', 'PrintV2', 'WriteFile'}
B<RESULT>:
lib/AI/TensorFlow/Libtensorflow/Manual/Notebook/InferenceUsingTFHubEnformerGeneExprPredModel.pod view on Meta::CPAN
=back
The input shape C<(-1, 393216, 4)> thus represents dimensions C<[batch size] x [sequence length] x [one-hot encoding of ACGT]>.
The output shape C<(-1, 896, 5313)> represents dimensions C<[batch size] x [ predictions along 114,688 base pairs / 128 base pair windows ] x [ human target by index ]>. We can confirm this by doing some calculations:
my $model_central_base_pairs_length = 114_688; # bp
my $model_central_base_pair_window_size = 128; # bp / prediction
say "Number of predictions: ", $model_central_base_pairs_length / $model_central_base_pair_window_size;
B<STREAM (STDOUT)>:
Number of predictions: 896
B<RESULT>:
1
and by looking at the targets file:
lib/AI/TensorFlow/Libtensorflow/Manual/Notebook/InferenceUsingTFHubEnformerGeneExprPredModel.pod view on Meta::CPAN
my $df = Data::Frame->from_csv( $targets_path, sep => "\t" )
->transform({
file => sub {
my ($col, $df) = @_;
# clean up the paths in 'file' column
[map { join "/", (split('/', $_))[7..8] } $col->list];
}
});
say "Number of targets: ", $df->nrow;
say "";
say "First 5:";
say $df->head(5);
B<STREAM (STDOUT)>:
Number of targets: 5313
First 5:
------------------------------------------------------------------------------------------------------------------------------------------------
index genome identifier file clip scale sum_stat description
------------------------------------------------------------------------------------------------------------------------------------------------
0 0 0 ENCFF833POA encode/ENCSR000EIJ 32 2 mean DNASE:cerebellum male adult (27 years) and male adult (35 years)
lib/AI/TensorFlow/Libtensorflow/Manual/Notebook/InferenceUsingTFHubEnformerGeneExprPredModel.pod view on Meta::CPAN
my $from_alphabet_tr = $from_alphabet . lc $from_alphabet;
my $to_alphabet_tr = $to_alphabet x 2;
my $p = zeros(byte, bytes::length($seq));
my $p_dataref = $p->get_dataref;
${ $p_dataref } = $seq;
eval "tr/$from_alphabet_tr/$to_alphabet_tr/" for ${ $p_dataref };
$p->upd_data;
my $encoder = append(float(0), identity(float(length($from_alphabet)-1)) );
say "Encoder is\n", $encoder->info, $encoder if $SHOW_ENCODER;
my $encoded = $encoder->index( $p->dummy(0) );
return $encoded;
}
####
{
say "Testing one-hot encoding:\n";
my $onehot_test_seq = "ACGTNtgcan";
my $test_encoded = one_hot_dna( $onehot_test_seq );
$SHOW_ENCODER = 0;
say "One-hot encoding of sequence '$onehot_test_seq' is:";
say $test_encoded->info, $test_encoded;
}
B<STREAM (STDOUT)>:
Testing one-hot encoding:
Encoder is
PDL: Float D [5,4]
[
lib/AI/TensorFlow/Libtensorflow/Manual/Notebook/InferenceUsingTFHubEnformerGeneExprPredModel.pod view on Meta::CPAN
use overload '""' => \&_op_stringify;
sub _op_stringify { sprintf "%s:%s", $_[0]->seq_id // "(no sequence)", $_[0]->to_FTstring }
}
#####
{
say "Testing interval resizing:\n";
sub _debug_resize {
my ($interval, $to, $msg) = @_;
my $resized_interval = $interval->resize($to);
die "Wrong interval size for $interval --($to)--> $resized_interval"
unless $resized_interval->length == $to;
say sprintf "Interval: %s -> %s, length %2d : %s",
$interval,
$resized_interval, $resized_interval->length,
$msg;
}
for my $interval_spec ( [4, 8], [5, 8], [5, 9], [6, 9]) {
my ($start, $end) = @$interval_spec;
my $test_interval = Interval->new( -seq_id => 'chr11', -start => $start, -end => $end );
say sprintf "Testing interval %s with length %d", $test_interval, $test_interval->length;
say "-----";
for(0..5) {
my $base = $test_interval->length;
my $to = $base + $_;
_debug_resize $test_interval, $to, "$base -> $to (+ $_)";
}
say "";
}
}
undef;
B<STREAM (STDOUT)>:
Testing interval resizing:
lib/AI/TensorFlow/Libtensorflow/Manual/Notebook/InferenceUsingTFHubEnformerGeneExprPredModel.pod view on Meta::CPAN
sprintf "%s...%s (length %d)", uc substr($seq, 0, $n), uc substr($seq, -$n), length $seq;
} else {
sprintf "%s (length %d)", uc $seq, length $seq;
}
}
####
{
say "Testing sequence extraction:";
say "1 base: ", seq_info
extract_sequence( $hg_db,
Interval->new( -seq_id => 'chr11',
-start => 35_082_742 + 1,
-end => 35_082_742 + 1 ) );
say "3 bases: ", seq_info
extract_sequence( $hg_db,
Interval->new( -seq_id => 'chr11',
-start => 1,
-end => 1 )->resize(3) );
say "5 bases: ", seq_info
extract_sequence( $hg_db,
Interval->new( -seq_id => 'chr11',
-start => $hg_db->length('chr11'),
-end => $hg_db->length('chr11') )->resize(5) );
say "chr11 is of length ", $hg_db->length('chr11');
say "chr11 bases: ", seq_info
extract_sequence( $hg_db,
Interval->new( -seq_id => 'chr11',
-start => 1,
-end => $hg_db->length('chr11') )->resize( $hg_db->length('chr11') ) );
}
B<STREAM (STDOUT)>:
Testing sequence extraction:
1 base: G (length 1)
lib/AI/TensorFlow/Libtensorflow/Manual/Notebook/InferenceUsingTFHubEnformerGeneExprPredModel.pod view on Meta::CPAN
B<RESULT>:
1
Now we can use the same target interval that is used in the example notebook which recreates part of L<figure 1|https://www.nature.com/articles/s41592-021-01252-x/figures/1> from the Enformer paper.
my $target_interval = Interval->new( -seq_id => 'chr11',
-start => 35_082_742 + 1, # BioPerl is 1-based
-end => 35_197_430 );
say "Target interval: $target_interval with length @{[ $target_interval->length ]}";
die "Target interval is not $model_central_base_pairs_length bp long"
unless $target_interval->length == $model_central_base_pairs_length;
say "Target sequence is ", seq_info extract_sequence( $hg_db, $target_interval );
say "";
my $resized_interval = $target_interval->resize( $model_sequence_length );
say "Resized interval: $resized_interval with length @{[ $resized_interval->length ]}";
die "resize() is not working properly!" unless $resized_interval->length == $model_sequence_length;
my $seq = extract_sequence( $hg_db, $resized_interval );
say "Resized sequence is ", seq_info($seq);
B<STREAM (STDOUT)>:
Target interval: chr11:35082743..35197430 with length 114688
Target sequence is GGTGGCAGCC...ATCTCCTTTT (length 114688)
Resized interval: chr11:34943479..35336694 with length 393216
Resized sequence is ACTAGTTCTA...GGCCCAAATC (length 393216)
B<RESULT>:
1
To prepare the input we have to one-hot encode this resized sequence and give it a dummy dimension at the end to indicate that it is is a batch with a single sequence. Then we can turn the PDL ndarray into a C<TFTensor> and pass it to our prediction ...
my $sequence_one_hot = one_hot_dna( $seq )->dummy(-1);
say $sequence_one_hot->info; undef;
B<STREAM (STDOUT)>:
PDL: Float D [4,393216,1]
use Devel::Timer;
my $t = Devel::Timer->new;
$t->mark('prediction of sequence');
lib/AI/TensorFlow/Libtensorflow/Manual/Notebook/InferenceUsingTFHubEnformerGeneExprPredModel.pod view on Meta::CPAN
01 -> 02 14.5634 100.00% prediction of sequence -> End of prediction of sequence
02 -> 03 0.0007 0.00% End of prediction of sequence -> END
00 -> 01 0.0000 0.00% INIT -> prediction of sequence
</span></code></pre></span>
=end html
Now we turn the C<TFTensor> output into a PDL ndarray.
my $predictions_p = FloatTFTensorToPDL($predictions)->slice(',,(0)');
say $predictions_p->info; undef;
B<STREAM (STDOUT)>:
PDL: Float D [5313,896]
=head2 Plot predicted tracks
These predictions can be plotted
my @tracks = (
lib/AI/TensorFlow/Libtensorflow/Manual/Notebook/InferenceUsingTFHubEnformerGeneExprPredModel.pod view on Meta::CPAN
$targets_path,
$hg_gz_path,
$hg_bgz_path, $hg_bgz_fai_path,
$clinvar_path,
$plot_output_path,
);
say "Disk space usage: $total"; undef;
B<STREAM (STDOUT)>:
Disk space usage: 4.66G
=head1 CPANFILE
requires 'AI::TensorFlow::Libtensorflow';
requires 'AI::TensorFlow::Libtensorflow::DataType';
requires 'Archive::Extract';
lib/AI/TensorFlow/Libtensorflow/Manual/Notebook/InferenceUsingTFHubMobileNetV2Model.pod view on Meta::CPAN
## DO NOT EDIT. Generated from notebook/InferenceUsingTFHubMobileNetV2Model.ipynb using ./maint/process-notebook.pl.
use strict;
use warnings;
use utf8;
use constant IN_IPERL => !! $ENV{PERL_IPERL_RUNNING};
no if IN_IPERL, warnings => 'redefine'; # fewer messages when re-running cells
use feature qw(say state);
use Syntax::Construct qw(each-array);
use lib::projectroot qw(lib);
BEGIN {
if( IN_IPERL ) {
$ENV{TF_CPP_MIN_LOG_LEVEL} = 3;
}
require AI::TensorFlow::Libtensorflow;
}
lib/AI/TensorFlow/Libtensorflow/Manual/Notebook/InferenceUsingTFHubMobileNetV2Model.pod view on Meta::CPAN
image_size => [ 224, 224 ],
},
mobilenet_v2_140_224 => {
handle => "https://tfhub.dev/google/imagenet/mobilenet_v2_140_224/classification/5",
image_size => [ 224, 224 ],
},
);
my $model_name = 'mobilenet_v2_100_224';
say "Selected model: $model_name : $model_name_to_params{$model_name}{handle}";
my $model_uri = URI->new( $model_name_to_params{$model_name}{handle} );
$model_uri->query_form( 'tf-hub-format' => 'compressed' );
my $model_base = substr( $model_uri->path, 1 ) =~ s,/,_,gr;
my $model_archive_path = "${model_base}.tar.gz";
use constant IMAGENET_LABEL_COUNT_WITH_BG => 1001;
my $labels_uri = URI->new('https://storage.googleapis.com/download.tensorflow.org/data/ImageNetLabels.txt');
my $labels_path = ($labels_uri->path_segments)[-1];
my $http = HTTP::Tiny->new;
for my $download ( [ $model_uri => $model_archive_path ],
[ $labels_uri => $labels_path ]) {
my ($uri, $path) = @$download;
say "Downloading $uri to $path";
next if -e $path;
$http->mirror( $uri, $path );
}
use Archive::Extract;
my $ae = Archive::Extract->new( archive => $model_archive_path );
die "Could not extract archive" unless $ae->extract( to => $model_base );
my $saved_model = path($model_base)->child('saved_model.pb');
say "Saved model is in $saved_model" if -f $saved_model;
my @labels = path($labels_path)->lines( { chomp => 1 });
die "Labels should have @{[ IMAGENET_LABEL_COUNT_WITH_BG ]} items"
unless @labels == IMAGENET_LABEL_COUNT_WITH_BG;
say "Got labels: ", join( ", ", List::Util::head(5, @labels) ), ", etc.";
my @tags = ( 'serve' );
if( File::Which::which('saved_model_cli')) {
local $ENV{TF_CPP_MIN_LOG_LEVEL} = 3; # quiet the TensorFlow logger for the following command
system(qw(saved_model_cli show),
qw(--dir) => $model_base,
qw(--tag_set) => join(',', @tags),
qw(--signature_def) => 'serving_default'
) == 0 or die "Could not run saved_model_cli";
} else {
say "Install the tensorflow Python package to get the `saved_model_cli` command.";
}
my $opt = AI::TensorFlow::Libtensorflow::SessionOptions->New;
my $graph = AI::TensorFlow::Libtensorflow::Graph->New;
my $session = AI::TensorFlow::Libtensorflow::Session->LoadFromSavedModel(
$opt, undef, $model_base, \@tags, $graph, undef, $s
);
AssertOK($s);
lib/AI/TensorFlow/Libtensorflow/Manual/Notebook/InferenceUsingTFHubMobileNetV2Model.pod view on Meta::CPAN
out => $graph->OperationByName('StatefulPartitionedCall'),
);
die "Could not get all operations" unless List::Util::all(sub { defined }, values %ops);
my %outputs = map { $_ => [ AI::TensorFlow::Libtensorflow::Output->New( { oper => $ops{$_}, index => 0 } ) ] }
keys %ops;
p %outputs;
say "Input: " , $outputs{in}[0];
say "Output: ", $outputs{out}[0];
my %images_for_test_to_uri = (
"tiger" => "https://upload.wikimedia.org/wikipedia/commons/b/b0/Bengal_tiger_%28Panthera_tigris_tigris%29_female_3_crop.jpg",
#by Charles James Sharp, CC BY-SA 4.0 <https://creativecommons.org/licenses/by-sa/4.0>, via Wikimedia Commons
"bus" => "https://upload.wikimedia.org/wikipedia/commons/6/63/LT_471_%28LTZ_1471%29_Arriva_London_New_Routemaster_%2819522859218%29.jpg",
#by Martin49 from London, England, CC BY 2.0 <https://creativecommons.org/licenses/by/2.0>, via Wikimedia Commons
"car" => "https://upload.wikimedia.org/wikipedia/commons/4/49/2013-2016_Toyota_Corolla_%28ZRE172R%29_SX_sedan_%282018-09-17%29_01.jpg",
#by EurovisionNim, CC BY-SA 4.0 <https://creativecommons.org/licenses/by-sa/4.0>, via Wikimedia Commons
"cat" => "https://upload.wikimedia.org/wikipedia/commons/4/4d/Cat_November_2010-1a.jpg",
#by Alvesgaspar, CC BY-SA 3.0 <https://creativecommons.org/licenses/by-sa/3.0>, via Wikimedia Commons
lib/AI/TensorFlow/Libtensorflow/Manual/Notebook/InferenceUsingTFHubMobileNetV2Model.pod view on Meta::CPAN
qtype => 'mixing', # 'mixing' seems to work better than 'normal'
);
}
sub load_image_to_pdl {
my ($uri, $image_size) = @_;
my $http = HTTP::Tiny->new;
my $response = $http->get( $uri );
die "Could not fetch image from $uri" unless $response->{success};
say "Downloaded $uri";
my $img = Imager->new;
$img->read( data => $response->{content} );
my $rescaled = imager_scale_to($img, $image_size);
say sprintf "Rescaled image from [ %d x %d ] to [ %d x %d ]",
$img->getwidth, $img->getheight,
$rescaled->getwidth, $rescaled->getheight;
my $padded = imager_paste_center_pad($rescaled, $image_size,
# ARGB fits in 32-bits (uint32_t)
channels => 4
);
say sprintf "Padded to [ %d x %d ]", $padded->getwidth, $padded->getheight;
# Create PDL ndarray from Imager data in-memory.
my $data;
$padded->write( data => \$data, type => 'raw' )
or die "could not write ". $padded->errstr;
# $data is packed as PDL->dims == [w,h] with ARGB pixels
# $ PDL::howbig(ulong) # 4
my $pdl_raw = zeros(ulong, $padded->getwidth, $padded->getheight);
${ $pdl_raw->get_dataref } = $data;
lib/AI/TensorFlow/Libtensorflow/Manual/Notebook/InferenceUsingTFHubMobileNetV2Model.pod view on Meta::CPAN
$outputs{out}, \@outputs_t,
undef,
undef,
$s
);
AssertOK($s);
return $outputs_t[0];
};
say "Warming up the model";
use PDL::GSL::RNG;
my $rng = PDL::GSL::RNG->new('default');
my $image_size = $model_name_to_params{$model_name}{image_size};
my $warmup_input = zeros(float, 3, @$image_size, 1 );
$rng->get_uniform($warmup_input);
p $RunSession->($session, FloatPDLTOTFTensor($warmup_input));
my $output_pdl_batched = FloatTFTensorToPDL($RunSession->($session, $t));
my $softmax = sub { ( map $_/sumover($_)->dummy(0), exp($_[0]) )[0] };
lib/AI/TensorFlow/Libtensorflow/Manual/Notebook/InferenceUsingTFHubMobileNetV2Model.pod view on Meta::CPAN
},
)
})
);
IPerl->display($html);
} else {
for my $batch_idx (0..$#image_names) {
my $image_name = $image_names[$batch_idx];
my @top_for_image = $top_lists[$batch_idx]->list;
my @td;
say "Image name: `$image_name`";
my $header = [ ('Rank', 'Label No', 'Label', 'Prob') ];
my @rows;
while( my ($i, $label_index) = each @top_for_image ) {
my $class_index = $includes_background_class ? $label_index : $label_index + 1;
push @rows, [ (
$i + 1,
$class_index,
$labels[$class_index],
$probabilities_batched->at($label_index,$batch_idx),
) ];
}
say generate_table( rows => [ $header, @rows ], header_row => 1 );
print "\n";
}
}
my $p_approx_batched = $probabilities_batched->sumover->approx(1, 1e-5);
p $p_approx_batched;
say "All probabilities sum up to approximately 1" if $p_approx_batched->all->sclr;
use Filesys::DiskUsage qw/du/;
my $total = du( { 'human-readable' => 1, dereference => 1 },
$model_archive_path, $model_base, $labels_path );
say "Disk space usage: $total"; undef;
my @solid_channel_uris = (
'https://upload.wikimedia.org/wikipedia/commons/thumb/6/62/Solid_red.svg/480px-Solid_red.svg.png',
'https://upload.wikimedia.org/wikipedia/commons/thumb/1/1d/Green_00FF00_9x9.svg/480px-Green_00FF00_9x9.svg.png',
'https://upload.wikimedia.org/wikipedia/commons/thumb/f/ff/Solid_blue.svg/480px-Solid_blue.svg.png',
);
undef;
__END__
lib/AI/TensorFlow/Libtensorflow/Manual/Notebook/InferenceUsingTFHubMobileNetV2Model.pod view on Meta::CPAN
=head2 Load the library
First, we need to load the C<AI::TensorFlow::Libtensorflow> library and more helpers. We then create an C<AI::TensorFlow::Libtensorflow::Status> object and helper function to make sure that the calls to the C<libtensorflow> C library are working prop...
use strict;
use warnings;
use utf8;
use constant IN_IPERL => !! $ENV{PERL_IPERL_RUNNING};
no if IN_IPERL, warnings => 'redefine'; # fewer messages when re-running cells
use feature qw(say state);
use Syntax::Construct qw(each-array);
use lib::projectroot qw(lib);
BEGIN {
if( IN_IPERL ) {
$ENV{TF_CPP_MIN_LOG_LEVEL} = 3;
}
require AI::TensorFlow::Libtensorflow;
}
lib/AI/TensorFlow/Libtensorflow/Manual/Notebook/InferenceUsingTFHubMobileNetV2Model.pod view on Meta::CPAN
image_size => [ 224, 224 ],
},
mobilenet_v2_140_224 => {
handle => "https://tfhub.dev/google/imagenet/mobilenet_v2_140_224/classification/5",
image_size => [ 224, 224 ],
},
);
my $model_name = 'mobilenet_v2_100_224';
say "Selected model: $model_name : $model_name_to_params{$model_name}{handle}";
B<STREAM (STDOUT)>:
Selected model: mobilenet_v2_100_224 : https://tfhub.dev/google/imagenet/mobilenet_v2_100_224/classification/5
B<RESULT>:
1
We download the model and labels to the current directory then extract the model to a folder with the name given in C<$model_base>.
lib/AI/TensorFlow/Libtensorflow/Manual/Notebook/InferenceUsingTFHubMobileNetV2Model.pod view on Meta::CPAN
use constant IMAGENET_LABEL_COUNT_WITH_BG => 1001;
my $labels_uri = URI->new('https://storage.googleapis.com/download.tensorflow.org/data/ImageNetLabels.txt');
my $labels_path = ($labels_uri->path_segments)[-1];
my $http = HTTP::Tiny->new;
for my $download ( [ $model_uri => $model_archive_path ],
[ $labels_uri => $labels_path ]) {
my ($uri, $path) = @$download;
say "Downloading $uri to $path";
next if -e $path;
$http->mirror( $uri, $path );
}
use Archive::Extract;
my $ae = Archive::Extract->new( archive => $model_archive_path );
die "Could not extract archive" unless $ae->extract( to => $model_base );
my $saved_model = path($model_base)->child('saved_model.pb');
say "Saved model is in $saved_model" if -f $saved_model;
my @labels = path($labels_path)->lines( { chomp => 1 });
die "Labels should have @{[ IMAGENET_LABEL_COUNT_WITH_BG ]} items"
unless @labels == IMAGENET_LABEL_COUNT_WITH_BG;
say "Got labels: ", join( ", ", List::Util::head(5, @labels) ), ", etc.";
B<STREAM (STDOUT)>:
Downloading https://tfhub.dev/google/imagenet/mobilenet_v2_100_224/classification/5?tf-hub-format=compressed to google_imagenet_mobilenet_v2_100_224_classification_5.tar.gz
Downloading https://storage.googleapis.com/download.tensorflow.org/data/ImageNetLabels.txt to ImageNetLabels.txt
Saved model is in google_imagenet_mobilenet_v2_100_224_classification_5/saved_model.pb
Got labels: background, tench, goldfish, great white shark, tiger shark, etc.
B<RESULT>:
lib/AI/TensorFlow/Libtensorflow/Manual/Notebook/InferenceUsingTFHubMobileNetV2Model.pod view on Meta::CPAN
We can examine what computations are contained in the graph in terms of the names of the inputs and outputs of an operation found in the graph by running C<saved_model_cli>.
if( File::Which::which('saved_model_cli')) {
local $ENV{TF_CPP_MIN_LOG_LEVEL} = 3; # quiet the TensorFlow logger for the following command
system(qw(saved_model_cli show),
qw(--dir) => $model_base,
qw(--tag_set) => join(',', @tags),
qw(--signature_def) => 'serving_default'
) == 0 or die "Could not run saved_model_cli";
} else {
say "Install the tensorflow Python package to get the `saved_model_cli` command.";
}
B<STREAM (STDOUT)>:
The given SavedModel SignatureDef contains the following input(s):
inputs['inputs'] tensor_info:
dtype: DT_FLOAT
shape: (-1, 224, 224, 3)
name: serving_default_inputs:0
The given SavedModel SignatureDef contains the following output(s):
lib/AI/TensorFlow/Libtensorflow/Manual/Notebook/InferenceUsingTFHubMobileNetV2Model.pod view on Meta::CPAN
out => $graph->OperationByName('StatefulPartitionedCall'),
);
die "Could not get all operations" unless List::Util::all(sub { defined }, values %ops);
my %outputs = map { $_ => [ AI::TensorFlow::Libtensorflow::Output->New( { oper => $ops{$_}, index => 0 } ) ] }
keys %ops;
p %outputs;
say "Input: " , $outputs{in}[0];
say "Output: ", $outputs{out}[0];
B<STREAM (STDOUT)>:
Input: serving_default_inputs:0
Output: StatefulPartitionedCall:0
B<STREAM (STDERR)>:
=for html <span style="display:inline-block;margin-left:1em;"><pre style="display: block"><code><span style="color: #33ccff;">{</span><span style="">
</span><span style="color: #6666cc;">in</span><span style=""> </span><span style="color: #33ccff;"> </span><span style="color: #33ccff;">[</span><span style="">
lib/AI/TensorFlow/Libtensorflow/Manual/Notebook/InferenceUsingTFHubMobileNetV2Model.pod view on Meta::CPAN
qtype => 'mixing', # 'mixing' seems to work better than 'normal'
);
}
sub load_image_to_pdl {
my ($uri, $image_size) = @_;
my $http = HTTP::Tiny->new;
my $response = $http->get( $uri );
die "Could not fetch image from $uri" unless $response->{success};
say "Downloaded $uri";
my $img = Imager->new;
$img->read( data => $response->{content} );
my $rescaled = imager_scale_to($img, $image_size);
say sprintf "Rescaled image from [ %d x %d ] to [ %d x %d ]",
$img->getwidth, $img->getheight,
$rescaled->getwidth, $rescaled->getheight;
my $padded = imager_paste_center_pad($rescaled, $image_size,
# ARGB fits in 32-bits (uint32_t)
channels => 4
);
say sprintf "Padded to [ %d x %d ]", $padded->getwidth, $padded->getheight;
# Create PDL ndarray from Imager data in-memory.
my $data;
$padded->write( data => \$data, type => 'raw' )
or die "could not write ". $padded->errstr;
# $data is packed as PDL->dims == [w,h] with ARGB pixels
# $ PDL::howbig(ulong) # 4
my $pdl_raw = zeros(ulong, $padded->getwidth, $padded->getheight);
${ $pdl_raw->get_dataref } = $data;
lib/AI/TensorFlow/Libtensorflow/Manual/Notebook/InferenceUsingTFHubMobileNetV2Model.pod view on Meta::CPAN
$outputs{out}, \@outputs_t,
undef,
undef,
$s
);
AssertOK($s);
return $outputs_t[0];
};
say "Warming up the model";
use PDL::GSL::RNG;
my $rng = PDL::GSL::RNG->new('default');
my $image_size = $model_name_to_params{$model_name}{image_size};
my $warmup_input = zeros(float, 3, @$image_size, 1 );
$rng->get_uniform($warmup_input);
p $RunSession->($session, FloatPDLTOTFTensor($warmup_input));
B<STREAM (STDOUT)>:
lib/AI/TensorFlow/Libtensorflow/Manual/Notebook/InferenceUsingTFHubMobileNetV2Model.pod view on Meta::CPAN
},
)
})
);
IPerl->display($html);
} else {
for my $batch_idx (0..$#image_names) {
my $image_name = $image_names[$batch_idx];
my @top_for_image = $top_lists[$batch_idx]->list;
my @td;
say "Image name: `$image_name`";
my $header = [ ('Rank', 'Label No', 'Label', 'Prob') ];
my @rows;
while( my ($i, $label_index) = each @top_for_image ) {
my $class_index = $includes_background_class ? $label_index : $label_index + 1;
push @rows, [ (
$i + 1,
$class_index,
$labels[$class_index],
$probabilities_batched->at($label_index,$batch_idx),
) ];
}
say generate_table( rows => [ $header, @rows ], header_row => 1 );
print "\n";
}
}
B<DISPLAY>:
=for html <span style="display:inline-block;margin-left:1em;"><p><table style="width: 100%"><tr><td><tt>apple</tt></td><td><a href="https://upload.wikimedia.org/wikipedia/commons/1/15/Red_Apple.jpg"><img alt="apple" src="https://upload.wikimedia.org/...
my $p_approx_batched = $probabilities_batched->sumover->approx(1, 1e-5);
p $p_approx_batched;
say "All probabilities sum up to approximately 1" if $p_approx_batched->all->sclr;
B<STREAM (STDOUT)>:
All probabilities sum up to approximately 1
B<STREAM (STDERR)>:
=for html <span style="display:inline-block;margin-left:1em;"><pre style="display: block"><code><span style="color: #cc66cc;">PDL</span><span style="color: #33ccff;"> {</span><span style="">
</span><span style="color: #6666cc;">Data </span><span style=""> : </span><span style="color: #33ccff;">[</span><span style="color: #ff6633;">1 1 1 1 1 1 1 1 1 1 1 1</span><span style="color: #33ccff;">]</span><span style="">
</span><span style="color: #6666cc;">Type </span><span style=""> : </span><span style="color: #cc66cc;">double</span><span style="">
lib/AI/TensorFlow/Libtensorflow/Manual/Notebook/InferenceUsingTFHubMobileNetV2Model.pod view on Meta::CPAN
1
=head1 RESOURCE USAGE
use Filesys::DiskUsage qw/du/;
my $total = du( { 'human-readable' => 1, dereference => 1 },
$model_archive_path, $model_base, $labels_path );
say "Disk space usage: $total"; undef;
B<STREAM (STDOUT)>:
Disk space usage: 27.45M
=head1 DEBUGGING
The following images can be used to test the C<load_image_to_pdl> function.
my @solid_channel_uris = (
maint/process-capi.pl view on Meta::CPAN
use FindBin;
use lib "$FindBin::Bin/../lib";
use Sub::Uplevel; # place early to override caller()
package TF::CAPI::Extract {
use Mu;
use CLI::Osprey;
use AI::TensorFlow::Libtensorflow::Lib;
use feature qw(say postderef);
use Syntax::Construct qw(heredoc-indent);
use Function::Parameters;
use Path::Tiny;
use Types::Path::Tiny qw/Path/;
use File::Find::Rule;
use Sort::Key::Multi qw(iikeysort);
use List::Util qw(uniq first);
use List::SomeUtils qw(firstidx part);
maint/process-capi.pl view on Meta::CPAN
}
method check_functions($first_arg = undef) {
my $functions = AI::TensorFlow::Libtensorflow::Lib->ffi->_attached_functions;
my @dupes = map { $_->[0]{c} }
grep { @$_ != 1 } values $functions->%*;
die "Duplicated functions @dupes" if @dupes;
my @data = $self->fdecl_data->@*;
say <<~STATS;
Statistics:
==========
Attached functions: @{[ scalar keys %$functions ]}
Total CAPI functions: @{[ scalar @data ]}
STATS
my $first_missing_function = first {
! exists $functions->{$_->{func_name}}
&&
(
! defined $first_arg ||
$_->{fdecl} =~ /\(\s*\Q$first_arg\E\s*\*/
)
} @data;
say "Missing function:";
use DDP; p $first_missing_function;
}
method run() {
$self->generate_capi_funcs;
#$self->check_types;
$self->check_functions;
}
subcommand 'generate-capi-docs' => method(@) {
maint/process-notebook.pl view on Meta::CPAN
echo -e "## DO NOT EDIT. Generated from $SRC using $GENERATOR.\n" | sponge -a $DST
## Add code to $DST
jupyter nbconvert $SRC --to script --stdout | sponge -a $DST;
## Add
## __END__
##
## =pod
##
perl -E 'say qq|__END__\n\n=pod\n\n|' | sponge -a $DST;
## Add POD
iperl nbconvert.iperl $SRC | sponge -a $DST;
## Edit to NAME
perl -0777 -pi -e 's/(=head1 NAME\n+)$ENV{SRC_BASENAME}/\1$ENV{PODNAME}/' $DST
## Edit to local section link (Markdown::Pod does not yet recognise this).
perl -pi -E 's,\QL<CPANFILE|#CPANFILE>\E,L<CPANFILE|/CPANFILE>,g' $DST
( run in 0.655 second using v1.01-cache-2.11-cpan-5623c5533a1 )