Fix several typos; add LICENSE and a few other minor adjustments

.gitignore

@@ -16,7 +16,7 @@ project/plugins/project/
 .scala_dependencies
 .worksheet
 *.iml
-.idea/*
+.idea/
 
 # other
 *.txt

LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

dl/src/main/scala/com/intel/analytics/bigdl/example/imageclassification/README.md

@@ -13,7 +13,7 @@ To start with this example, you need prepare your model and dataset.
 
 2. Prepare predict dataset
 
-    Put your image data for prediction in the ./predict foler. Alternatively, you may also use imagenet-2012 validation dataset to run the example, which can be found from <http://image-net.org/download-images>. After you download the file (ILSVRC2012_img_val.tar), run the follow commands to prepare the data.
+    Put your image data for prediction in the ./predict folder. Alternatively, you may also use imagenet-2012 validation dataset to run the example, which can be found from <http://image-net.org/download-images>. After you download the file (ILSVRC2012_img_val.tar), run the follow commands to prepare the data.
 
      ```bash
     mkdir predict

dl/src/main/scala/com/intel/analytics/bigdl/example/textclassification/TextClassifier.scala

@@ -41,7 +41,7 @@ import scala.language.existentials
  * This example use a (pre-trained GloVe embedding) to convert word to vector,
  * and uses it to train a text classification model on the 20 Newsgroup dataset
  * with 20 different categories. This model can achieve around 90% accuracy after
- * 2 epoches training.
+ * 2 epochs training.
  */
 class TextClassifier(param: TextClassificationParams) {
   val log: Logger = LoggerFactory.getLogger(this.getClass)

dl/src/main/scala/com/intel/analytics/bigdl/models/resnet/README.md

@@ -39,9 +39,9 @@ Model is implemented in <code>ResNet</code>
         --learningRate 0.1 -n 4
         ```
 
-<code>Optimizer</code> class is used to train the model. Users can define validation method to evaluate the model. We use Top1Accurary as the validation method.
+<code>Optimizer</code> class is used to train the model. Users can define validation method to evaluate the model. We use Top1Accuracy as the validation method.
 
-We support Local and Spark versions of training. Users can define <code>env</code> as "Local" or "Spark" to set the training envrionment.
+We support Local and Spark versions of training. Users can define <code>env</code> as "Local" or "Spark" to set the training environment.
 
 ##Parameters
 ```

dl/src/main/scala/com/intel/analytics/bigdl/models/rnn/Train.scala

@@ -52,7 +52,7 @@ object Train {
       val trainData = dataArray._1
       val valData = dataArray._2
       val trainMaxLength = dataArray._3
-      val valMaxLegnth = dataArray._4
+      val valMaxLength = dataArray._4
 
       val batchSize = 1
 
@@ -62,7 +62,7 @@ object Train {
            .transform(SampleToBatch(batchSize = batchSize))
       val validationSet = DataSet.array(valData)
            .transform(LabeledSentenceToSample(dictionaryLength,
-             Some(valMaxLegnth), Some(valMaxLegnth)))
+             Some(valMaxLength), Some(valMaxLength)))
            .transform(SampleToBatch(batchSize = batchSize))
 
       val model = if (param.modelSnapshot.isDefined) {

dl/src/main/scala/com/intel/analytics/bigdl/nn/Bilinear.scala

@@ -121,7 +121,7 @@ class Bilinear[T: ClassTag](inputSize1: Int,
     gradInput2.cmul(gradOutput.narrow(2, 1, 1).expand(
       Array(gradInput2.size(1), gradInput2.size(2))))
 
-    // do remaing slices of weight tensor
+    // do remaining slices of weight tensor
     if(weight.size(1) > 1) {
       buff1.resizeAs(res1)
 

dl/src/main/scala/com/intel/analytics/bigdl/nn/InitializationMethod.scala

@@ -18,7 +18,7 @@
 package com.intel.analytics.bigdl.nn
 
 /**
- * Initialization method to initializee bias and weight
+ * Initialization method to initialize bias and weight
  */
 sealed trait InitializationMethod
 

dl/src/main/scala/com/intel/analytics/bigdl/nn/SoftShrink.scala

@@ -31,22 +31,22 @@ import scala.reflect.ClassTag
  * f(x) = ⎨ x + lambda, if x < -lambda
  *        ⎩ 0, otherwise
  *
- * @param lamda Default is 0.5.
+ * @param lambda Default is 0.5.
  */
 
 @SerialVersionUID(- 2868096135424517459L)
 class SoftShrink[T: ClassTag](
-    val lamda: Double = 0.5
+    val lambda: Double = 0.5
   )( implicit ev: TensorNumeric[T]) extends TensorModule[T] {
 
   override def updateOutput(input: Tensor[T]): Tensor[T] = {
     output.resizeAs(input)
     val func = new TensorFunc4[T] {
       override def apply (data1: Array[T], offset1: Int, data2: Array[T], offset2: Int): Unit = {
-        data1(offset1) = if (ev.toType[Double](data2(offset2)) > lamda) {
-          ev.minus(data2(offset2), ev.fromType[Double](lamda))
-        } else if (ev.toType[Double](data2(offset2)) < - lamda) {
-          ev.plus(data2(offset2), ev.fromType[Double](lamda))
+        data1(offset1) = if (ev.toType[Double](data2(offset2)) > lambda) {
+          ev.minus(data2(offset2), ev.fromType[Double](lambda))
+        } else if (ev.toType[Double](data2(offset2)) < - lambda) {
+          ev.plus(data2(offset2), ev.fromType[Double](lambda))
         } else {
           ev.fromType[Int](0)
         }
@@ -62,8 +62,8 @@ class SoftShrink[T: ClassTag](
     val func = new TensorFunc6[T] {
       override def apply(data1: Array[T], offset1: Int, data2: Array[T], offset2: Int,
                          data3: Array[T], offset3: Int): Unit = {
-        data1(offset1) = if (ev.toType[Double](data3(offset3)) > lamda ||
-        ev.toType[Double](data3(offset3)) < - lamda) {
+        data1(offset1) = if (ev.toType[Double](data3(offset3)) > lambda ||
+        ev.toType[Double](data3(offset3)) < - lambda) {
           data2(offset2)
         } else {
           ev.fromType[Int](0)
@@ -82,7 +82,7 @@ class SoftShrink[T: ClassTag](
 
 object SoftShrink {
   def apply[@specialized(Float, Double) T: ClassTag](
-      lamda: Double = 0.5)(implicit ev: TensorNumeric[T]) : SoftShrink[T] = {
-    new SoftShrink[T](lamda)
+      lambda: Double = 0.5)(implicit ev: TensorNumeric[T]) : SoftShrink[T] = {
+    new SoftShrink[T](lambda)
   }
 }

dl/src/main/scala/com/intel/analytics/bigdl/nn/SpatialDilatedConvolution.scala

@@ -199,7 +199,7 @@ class SpatialDilatedConvolution[T: ClassTag](
     // For each element in batch, do:
     var elt = 1
     while (elt <= batchSize) {
-      // Matrix mulitply per output:
+      // Matrix multiply per output:
       val input_n = input.select(1, elt)
       val output_n = output.select(1, elt)
 
@@ -304,7 +304,7 @@ class SpatialDilatedConvolution[T: ClassTag](
     // For each element in batch, do:
     var elt = 1
     while (elt <= batchSize) {
-      // Matrix mulitply per sample:
+      // Matrix multiply per sample:
       val gradInput_n = gradInput.select(1, elt)
       val gradOutput_n = gradOutput.select(1, elt)
 
@@ -395,7 +395,7 @@ class SpatialDilatedConvolution[T: ClassTag](
     // For each element in batch, do:
     var elt = 1
     while (elt <= batchSize) {
-      // Matrix mulitply per output:
+      // Matrix multiply per output:
       val input_n = input.select(1, elt)
       val gradOutput_n = gradOutput.select(1, elt)
 

dl/src/main/scala/com/intel/analytics/bigdl/nn/SpatialFullConvolution.scala

@@ -470,7 +470,7 @@ class SpatialFullConvolution[A <: Activity : ClassTag, T: ClassTag](
     var elt = 1
     // For each element in batch, do:
     while (elt <= batchSize) {
-      // Matrix mulitply per output:
+      // Matrix multiply per output:
       val input_n = inputTensor.select(1, elt)
       val gradOutput_n = gradOutput.select(1, elt)
 

dl/src/main/scala/com/intel/analytics/bigdl/nn/SpatialSubtractiveNormalization.scala

@@ -31,7 +31,7 @@ import scala.reflect.ClassTag
  * an input image, since there is only one feature, the region is only spatial. For
  * an RGB image, the weighted average is taken over RGB channels and a spatial region.
  *
- * If the kernel is 1D, then it will be used for constructing and seperable 2D kernel.
+ * If the kernel is 1D, then it will be used for constructing and separable 2D kernel.
  * The operations will be much more efficient in this case.
  *
  * The kernel is generally chosen as a gaussian when it is believed that the correlation

dl/src/main/scala/com/intel/analytics/bigdl/nn/Unsqueeze.scala

@@ -42,7 +42,7 @@ class Unsqueeze[T: ClassTag](
   }
 
   private def getActualPosition(input: Tensor[T]) : Int = {
-    // get valid dimesion offset for batchMode (if any)
+    // get valid dimension offset for batchMode (if any)
     val inputDim = input.dim() // data batch dim
     numInputDims = if (numInputDims != Int.MinValue) numInputDims else inputDim // feature map dim
     val offsetDim = inputDim - numInputDims

dl/src/main/scala/com/intel/analytics/bigdl/optim/Adagrad.scala

@@ -37,7 +37,7 @@ class Adagrad[@specialized(Float, Double) T: ClassTag](implicit ev: TensorNumeri
    *                  config("learningRateDecay") : learning rate decay
    * @param state     a table describing the state of the optimizer; after each call the state
    *                  is modified
-   *                  state("paramVariance") : vector of temporal variances of paramters
+   *                  state("paramVariance") : vector of temporal variances of parameters
    * @return the new x vector and the function list, evaluated before the update
    */
   override def optimize(feval: (Tensor[T]) => (T, Tensor[T]),