Skip to content

Commit

Permalink
[WIP] Final dev branch merge (#29)
Browse files Browse the repository at this point in the history 
* SameDiff: convertDataType and gradient check util improvements (#12)

* GradCheck util improvements

* StopGradient constructor + test

* SameDiff: Add datatype conversion

* Javadoc and add DataType.isNumerical()

* Small fix

* Fix SameDiff TF import test cases intermediate naming (workaround for bad default)

* TFGraphTestAllHelper: check intermediates in execution order

* Add missing debug listener

* [WIP] lstmBlock fix + other changes (#13)

- fixes lstmBlock issue
- changes NDArray method reshape(), permute(), transpose() by making them return instance instead of pointer
- CheckNumerics op
- fixes for ReduceBool IsInfOrNan & IsFinite

* Small test fix

* CheckNumerics op wrapper

* Compatibility of deserialization (#18)

Signed-off-by: Alexander Stoyakin <alexander.stoyakin@gmail.com>

* SameDiff: add activation gradient checking support for debugging (#19)

* SameDiff gradient checker: first pass on activation gradient checks

* Fixes + tests for activation gradient checking

* Javadoc

* [WIP] Some nd4j data type corrections (#20)

* Adjust data type

* Set correct Data type.

* Size of proper data type.

* fix averaged cpu load (#22)

* [WIP] Multiple dataset iterators (#27)

* Splitting dataset into arbitrary number

* Fixes

* Multiple split of iterator

* Test

* Test

* Some fixes

* signature change

* one more tweak

Signed-off-by: raver119 <raver119@gmail.com>

* one more test for sequential use of DataSetIteratorSplitter

Signed-off-by: raver119 <raver119@gmail.com>

* Fixes

* Fixes

* one more test for Alexander

Signed-off-by: raver119 <raver119@gmail.com>

* Some fixes

* Some fixes

* one more test for Alexander

Signed-off-by: raver119 <raver119@gmail.com>

* minor test fix

Signed-off-by: raver119 <raver119@gmail.com>

* Some fixes

* Some fixes

* couple of assertions tweaked

Signed-off-by: raver119 <raver119@gmail.com>

* MDS splitter test :/

Signed-off-by: raver119 <raver119@gmail.com>

* Minor refactoring

* Multi dataset

* Some fixes

* More tests
  • Loading branch information
@raver119
raver119 committed Jun 26, 2019
1 parent 26ab58b commit 6124dd7
Show file tree
Hide file tree
Showing 7 changed files with 1,022 additions and 22 deletions.
255 changes: 251 additions & 4 deletions ...rning4j-core/src/test/java/org/deeplearning4j/datasets/iterator/DataSetSplitterTests.java
View file
Expand Up @@ -20,9 +20,15 @@
import org.deeplearning4j.BaseDL4JTest;
import org.deeplearning4j.datasets.iterator.tools.DataSetGenerator;
import org.junit.Test;
import org.nd4j.linalg.dataset.api.iterator.DataSetIterator;
import org.nd4j.linalg.exception.ND4JIllegalStateException;
import org.nd4j.linalg.factory.Nd4j;

import static org.junit.Assert.assertEquals;
import java.util.Collections;
import java.util.List;
import java.util.Random;

import static org.junit.Assert.*;

public class DataSetSplitterTests extends BaseDL4JTest {
@Test
Expand All @@ -39,7 +45,7 @@ public void testSplitter_1() throws Exception {
int gcntTest = 0;
int global = 0;
// emulating epochs here
for (int e = 0; e < numEpochs; e++){
for (int e = 0; e < numEpochs; e++) {
int cnt = 0;
while (train.hasNext()) {
val data = train.next().getFeatures();
Expand Down Expand Up @@ -79,7 +85,7 @@ public void testSplitter_2() throws Exception {
int gcntTest = 0;
int global = 0;
// emulating epochs here
for (int e = 0; e < numEpochs; e++){
for (int e = 0; e < numEpochs; e++) {
int cnt = 0;
while (train.hasNext()) {
val data = train.next().getFeatures();
Expand Down Expand Up @@ -117,7 +123,7 @@ public void testSplitter_3() throws Exception {
int gcntTest = 0;
int global = 0;
// emulating epochs here
for (int e = 0; e < numEpochs; e++){
for (int e = 0; e < numEpochs; e++) {
int cnt = 0;
while (train.hasNext()) {
val data = train.next().getFeatures();
Expand All @@ -144,4 +150,245 @@ public void testSplitter_3() throws Exception {

assertEquals(1000 * numEpochs, global);
}

@Test
public void testSplitter_4() {
val back = new DataSetGenerator(1000, new int[]{32, 100}, new int[]{32, 5});

val splitter = new DataSetIteratorSplitter(back, 1000, new double[]{0.5, 0.3, 0.2});
List<DataSetIterator> iteratorList = splitter.getIterators();
val numEpochs = 10;
int global = 0;
// emulating epochs here
for (int e = 0; e < numEpochs; e++) {
int iterNo = 0;
int perEpoch = 0;
for (val partIterator : iteratorList) {
int cnt = 0;
partIterator.reset();
while (partIterator.hasNext()) {
val data = partIterator.next().getFeatures();
assertEquals("Train failed on iteration " + cnt + "; epoch: " + e,
(float) perEpoch, data.getFloat(0), 1e-5);
//gcntTrain++;
global++;
cnt++;
++perEpoch;
}
++iterNo;
}
}

assertEquals(1000* numEpochs, global);
}

@Test
public void testSplitter_5() {
val back = new DataSetGenerator(1000, new int[]{32, 100}, new int[]{32, 5});

val splitter = new DataSetIteratorSplitter(back, new int[]{900, 100});

List<DataSetIterator> iteratorList = splitter.getIterators();
val numEpochs = 10;

int global = 0;
// emulating epochs here
for (int e = 0; e < numEpochs; e++) {
int iterNo = 0;
int perEpoch = 0;
for (val partIterator : iteratorList) {
partIterator.reset();
while (partIterator.hasNext()) {
int cnt = 0;
val data = partIterator.next().getFeatures();

assertEquals("Train failed on iteration " + cnt + "; epoch: " + e,
(float) perEpoch, data.getFloat(0), 1e-5);
//gcntTrain++;
global++;
cnt++;
++perEpoch;
}
++iterNo;
}
}

assertEquals(1000 * numEpochs, global);
}

@Test
public void testSplitter_6() {
val back = new DataSetGenerator(1000, new int[]{32, 100}, new int[]{32, 5});

// we're going to mimic train+test+validation split
val splitter = new DataSetIteratorSplitter(back, new int[]{800, 100, 100});

assertEquals(3, splitter.getIterators().size());

val trainIter = splitter.getIterators().get(0);
val testIter = splitter.getIterators().get(1);
val validationIter = splitter.getIterators().get(2);

// we're going to have multiple epochs
int numEpochs = 10;
for (int e = 0; e < numEpochs; e++) {
int globalIter = 0;
trainIter.reset();
testIter.reset();
validationIter.reset();

boolean trained = false;
while (trainIter.hasNext()) {
trained = true;
val ds = trainIter.next();
assertNotNull(ds);

assertEquals("Failed at iteration [" + globalIter + "]", (double) globalIter, ds.getFeatures().getDouble(0), 1e-5f);
globalIter++;
}
assertTrue("Failed at epoch [" + e + "]", trained);
assertEquals(800, globalIter);


// test set is used every epoch
boolean tested = false;
//testIter.reset();
while (testIter.hasNext()) {
tested = true;
val ds = testIter.next();
assertNotNull(ds);

assertEquals("Failed at iteration [" + globalIter + "]", (double) globalIter, ds.getFeatures().getDouble(0), 1e-5f);
globalIter++;
}
assertTrue("Failed at epoch [" + e + "]", tested);
assertEquals(900, globalIter);

// validation set is used every 5 epochs
if (e % 5 == 0) {
boolean validated = false;
//validationIter.reset();
while (validationIter.hasNext()) {
validated = true;
val ds = validationIter.next();
assertNotNull(ds);

assertEquals("Failed at iteration [" + globalIter + "]", (double) globalIter, ds.getFeatures().getDouble(0), 1e-5f);
globalIter++;
}
assertTrue("Failed at epoch [" + e + "]", validated);
}

// all 3 iterators have exactly 1000 elements combined
if (e % 5 == 0)
assertEquals(1000, globalIter);
else
assertEquals(900, globalIter);
trainIter.reset();
}
}

@Test
public void testUnorderedSplitter_1() {
val back = new DataSetGenerator(1000, new int[]{32, 100}, new int[]{32, 5});

val splitter = new DataSetIteratorSplitter(back, new int[]{500, 500});

List<DataSetIterator> iteratorList = splitter.getIterators();
val numEpochs = 10;

int global = 0;
// emulating epochs here
for (int e = 0; e < numEpochs; e++) {

// Get data from second part, then rewind for the first one.
int cnt = 0;
int partNumber = 1;
while (iteratorList.get(partNumber).hasNext()) {
int farCnt = (1000 / 2) * (partNumber) + cnt;
val data = iteratorList.get(partNumber).next().getFeatures();

assertEquals("Train failed on iteration " + cnt + "; epoch: " + e, (float) farCnt, data.getFloat(0), 1e-5);
cnt++;
global++;
}
iteratorList.get(partNumber).reset();
partNumber = 0;
cnt = 0;
while (iteratorList.get(0).hasNext()) {
val data = iteratorList.get(0).next().getFeatures();

assertEquals("Train failed on iteration " + cnt + "; epoch: " + e, (float) cnt++, data.getFloat(0), 1e-5);
global++;
}
}
}

@Test
public void testUnorderedSplitter_2() {
val back = new DataSetGenerator(1000, new int[]{32, 100}, new int[]{32, 5});

val splitter = new DataSetIteratorSplitter(back, new int[]{2});

List<DataSetIterator> iteratorList = splitter.getIterators();

for (int partNumber = 0 ; partNumber < iteratorList.size(); ++partNumber) {
int cnt = 0;
while (iteratorList.get(partNumber).hasNext()) {
val data = iteratorList.get(partNumber).next().getFeatures();

assertEquals("Train failed on iteration " + cnt, (float) (500*partNumber + cnt), data.getFloat(0), 1e-5);
cnt++;
}
}
}

@Test
public void testUnorderedSplitter_3() {
val back = new DataSetGenerator(1000, new int[]{32, 100}, new int[]{32, 5});

val splitter = new DataSetIteratorSplitter(back, new int[]{10});

List<DataSetIterator> iteratorList = splitter.getIterators();
Random random = new Random();
int[] indexes = new int[iteratorList.size()];
for (int i = 0; i < indexes.length; ++i) {
indexes[i] = random.nextInt(iteratorList.size());
}

for (int partNumber : indexes) {
int cnt = 0;
while (iteratorList.get(partNumber).hasNext()) {
val data = iteratorList.get(partNumber).next().getFeatures();

assertEquals("Train failed on iteration " + cnt, (float) (500*partNumber + cnt), data.getFloat(0), 1e-5);
cnt++;
}
}
}

@Test
public void testUnorderedSplitter_4() {
val back = new DataSetGenerator(1000, new int[]{32, 100}, new int[]{32, 5});

// we're going to mimic train+test+validation split
val splitter = new DataSetIteratorSplitter(back, new int[]{80, 10, 5});

assertEquals(3, splitter.getIterators().size());

val trainIter = splitter.getIterators().get(0); // 0..79
val testIter = splitter.getIterators().get(1); // 80 ..89
val validationIter = splitter.getIterators().get(2); // 90..94

// we're skipping train/test and go for validation first. we're that crazy, right.
int valCnt = 0;
while (validationIter.hasNext()) {
val ds = validationIter.next();
assertNotNull(ds);

assertEquals("Validation failed on iteration " + valCnt, (float) valCnt + 90, ds.getFeatures().getFloat(0), 1e-5);
valCnt++;
}
assertEquals(5, valCnt);
}
}

0 comments on commit 6124dd7

Please sign in to comment.