# Does anyone know how to load and classify a single image with TransferLearningHelper?

**URL:** <https://community.konduit.ai/t/does-anyone-know-how-to-load-and-classify-a-single-image-with-transferlearninghelper/1560>\
**Category:** DL4J\
**Created:** [August 15, 2021, 9:41pm UTC](https://community.konduit.ai/t/does-anyone-know-how-to-load-and-classify-a-single-image-with-transferlearninghelper/1560 "2021-08-15T21:41:34Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![javaberlin](https://yyz1.discourse-cdn.com/flex035/user_avatar/community.konduit.ai/javaberlin/32/606_2.png) [@javaberlin](https://community.konduit.ai/u/javaberlin)\
**Post date:** [August 15, 2021, 9:41pm UTC](https://community.konduit.ai/t/does-anyone-know-how-to-load-and-classify-a-single-image-with-transferlearninghelper/1560/1 "2021-08-15T21:41:34Z")

</div>

Hi guys, I am trying to classify a single image using the TransferLearningHelper class. Unfortunately the DL4J examples only show how to evaluate the model using iterators , splitting files in a directory in training and test sets. I am trying to classify an image using this code:

```auto
NativeImageLoader nativeImageLoader = new NativeImageLoader(height, width,3);
 DataNormalization scaler = new VGG16ImagePreProcessor();
INDArray img = nativeImageLoader.asMatrix(new File("C:\\sample.jpg"));
 scaler..transform(img);
 transferLearningHelper.outputFromFeaturized(img);

```

This code is not working , the method "outputFromFeaturized (img) "  
throws exception …

thanks

---

<div class="post-metadata">

**Author:** ![agibsonccc](https://yyz1.discourse-cdn.com/flex035/user_avatar/community.konduit.ai/agibsonccc/32/697_2.png) [@agibsonccc](https://community.konduit.ai/u/agibsonccc)\
**Post date:** [August 16, 2021, 12:22pm UTC](https://community.konduit.ai/t/does-anyone-know-how-to-load-and-classify-a-single-image-with-transferlearninghelper/1560/2 "2021-08-16T12:22:53Z")

</div>

> [@javaberlin](#):
>
> m

@javaberlin could you adapt the example we have publicly to something I can take a look at so I can understand all the assumptions made when running this? Thanks!

---

<div class="post-metadata">

**Author:** ![javaberlin](https://yyz1.discourse-cdn.com/flex035/user_avatar/community.konduit.ai/javaberlin/32/606_2.png) [@javaberlin](https://community.konduit.ai/u/javaberlin)\
**Post date:** [August 16, 2021, 6:31pm UTC](https://community.konduit.ai/t/does-anyone-know-how-to-load-and-classify-a-single-image-with-transferlearninghelper/1560/3 "2021-08-16T18:31:51Z")

</div>

@agibsonccc I am using the FitFromFeatutized.java example  
at [deeplearning4j-examples/FitFromFeaturized.java at master · eclipse/deeplearning4j-examples · GitHub](https://github.com/eclipse/deeplearning4j-examples/blob/master/dl4j-examples/src/main/java/org/deeplearning4j/examples/advanced/features/transferlearning/editlastlayer/presave/FitFromFeaturized.java)

The piece of code below is what I added to that example ( after line 110 ) , basically I am saving the model , and trying to open it. That part works. After that I read a single image from the flowers directory and try to classify it. This is where I get an Exception:

```auto
Caused by: org.deeplearning4j.exception.DL4JInvalidInputException: Input that is not a matrix; expected matrix (rank 2), got rank 4 array with shape [1, 3, 224, 224]. Missing preprocessor or wrong input type? (layer name: predictions, layer index: 1, layer type: OutputLayer)

```

This is the code I added to the “FitFearturized.java” class :

```auto

        for (int epoch = 0; epoch < nEpochs; epoch++) {
            if (epoch == 0) {
                Evaluation eval = transferLearningHelper.unfrozenGraph().evaluate(testIter);
                log.info("Eval stats BEFORE fit.....");
                log.info(eval.stats()+"\n");
                testIter.reset();
            }
            int iter = 0;
            while (trainIter.hasNext()) {
                transferLearningHelper.fitFeaturized(trainIter.next());
                if (iter % 10 == 0) {
                    log.info("Evaluate model at iter " + iter + " ....");
                    Evaluation eval = transferLearningHelper.unfrozenGraph().evaluate(testIter);
                    log.info(eval.stats());
                    testIter.reset();
                }
                iter++;
            }
            trainIter.reset();
            log.info("Epoch #"+epoch+" complete");
        }
        log.info("Model build complete");
// ########## BEGINN ADDED CODE #########
        ModelSerializer.writeModel(vgg16Transfer, new File("M:\\models\\flowersmodel.zip"), true);
        ComputationGraph model = null;
        log.info("Trying to open the model");
        try {
            model = ModelSerializer.restoreComputationGraph("M:\\models\\flowersmodel.zip");
            log.info("Success: Model opened");
        } catch (Exception e) {
           log.error("Unable to open model: " +e.getMessage());
        }

        NativeImageLoader nativeImageLoader = new NativeImageLoader(224, 224,3);
        INDArray img = nativeImageLoader.asMatrix(new File("C:\\Users\\kh\\dl4j-examples-data\\dl4j-examples\\flower_photos\\daisy\\5547758_eea9edfd54_n.jpg"));
        DataNormalization scaler = new VGG16ImagePreProcessor();
        scaler.transform(img);
        INDArray[] output = transferLearningHelper.unfrozenGraph().output(false, img);
        log.info("Classification: "+output);
    }

```

My questions would be:

1. Is this the right way to save the trained model , using the vgg16Transfer object, or do I have to save the “transferLearningHelper.unfrozenGraph()” instead ?
2. There is something wrong the way I am loading the image, how to do it correctly ?
3. How to do the classification ? There are other methods like “outputSingle(…)”, “outputFeaturized(…)” etc. …

Thanks