Merge pull request #25420 from Abdurrahheem:ash/01D-batchnorm

0/1D test for BatchNorm layer #25420

This PR introduces support for 0/1D inputs in `BatchNorm` layer.

### Pull Request Readiness Checklist

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [x] There is a reference to the original bug report and related work
- [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
      Patch to opencv_extra has the same branch name.
- [x] The feature is well documented and sample code can be built with the project CMake

modules/dnn/src/layers/batch_norm_layer.cpp

@@ -163,6 +163,11 @@ public:
                          std::vector<MatShape> &outputs,
                          std::vector<MatShape> &internals) const CV_OVERRIDE
     {
+        if (inputs[0].empty()) { // Support for 0D input
+            outputs.push_back(MatShape()); // Output is also a scalar.
+            return true;
+        }
+
         dims = inputs[0].size();
         if (!useGlobalStats && inputs[0][0] != 1)
             CV_Error(Error::StsNotImplemented, "Batch normalization in training mode with batch size > 1");
@@ -272,6 +277,15 @@ public:
         inputs_arr.getMatVector(inputs);
         outputs_arr.getMatVector(outputs);
 
+        if (inputs[0].dims <= 1) { // Handling for 0D and 1D
+            Mat &inpBlob = inputs[0];
+            Mat &outBlob = outputs[0];
+            CV_Assert(inpBlob.total() == weights_.total());
+            cv::multiply(inpBlob, weights_, outBlob);
+            cv::add(outBlob, bias_, outBlob);
+            return;
+        }
+
         CV_Assert(blobs.size() >= 2);
         CV_Assert(inputs.size() == 1);
 
@@ -284,7 +298,6 @@ public:
         for (size_t ii = 0; ii < outputs.size(); ii++)
         {
             Mat &outBlob = outputs[ii];
-
             for(int num = 0; num < outBlob.size[0]; num++)
             {
                 for (int n = 0; n < outBlob.size[1]; n++)

modules/dnn/test/test_layers_1d.cpp

@@ -603,6 +603,55 @@ INSTANTIATE_TEST_CASE_P(/*nothting*/, Layer_FullyConnected_Test,
                             std::vector<int>({4})
 ));
 
+typedef testing::TestWithParam<std::vector<int>> Layer_BatchNorm_Test;
+TEST_P(Layer_BatchNorm_Test, Accuracy_01D)
+{
+    std::vector<int> input_shape = GetParam();
+
+    // Layer parameters
+    LayerParams lp;
+    lp.type = "BatchNorm";
+    lp.name = "BatchNormLayer";
+    lp.set("has_weight", false);
+    lp.set("has_bias", false);
+
+    RNG& rng = TS::ptr()->get_rng();
+    float inp_value = rng.uniform(0.0, 10.0);
+
+    Mat meanMat(input_shape.size(), input_shape.data(), CV_32F, inp_value);
+    Mat varMat(input_shape.size(), input_shape.data(), CV_32F, inp_value);
+    vector<Mat> blobs = {meanMat, varMat};
+    lp.blobs = blobs;
+
+    // Create the layer
+    Ptr<Layer> layer = BatchNormLayer::create(lp);
+
+    Mat input(input_shape.size(), input_shape.data(), CV_32F, 1.0);
+    cv::randn(input, 0, 1);
+
+    std::vector<Mat> inputs{input};
+    std::vector<Mat> outputs;
+    runLayer(layer, inputs, outputs);
+
+    //create output_ref to compare with outputs
+    Mat output_ref = input.clone();
+    cv::sqrt(varMat + 1e-5, varMat);
+    output_ref = (output_ref - meanMat) / varMat;
+
+    ASSERT_EQ(outputs.size(), 1);
+    ASSERT_EQ(shape(output_ref), shape(outputs[0]));
+    normAssert(output_ref, outputs[0]);
+
+}
+INSTANTIATE_TEST_CASE_P(/*nothting*/, Layer_BatchNorm_Test,
+                        testing::Values(
+                            std::vector<int>({}),
+                            std::vector<int>({4}),
+                            std::vector<int>({1, 4}),
+                            std::vector<int>({4, 1})
+));
+
+
 typedef testing::TestWithParam<tuple<std::vector<int>>> Layer_Const_Test;
 TEST_P(Layer_Const_Test, Accuracy_01D)
 {