From c317713e91a830aa0e033ca12d2d353b23fde665 Mon Sep 17 00:00:00 2001
From: eromomon <edgar.romo.montiel@intel.com>
Date: Fri, 21 Feb 2025 11:47:29 -0600
Subject: [PATCH] Add support for Intel GPU to Siamese Network example

---
 siamese_network/README.md | 37 ++++++++++++++++++++++++++++++++++++-
 siamese_network/main.py   | 15 +++++++++++----
 2 files changed, 47 insertions(+), 5 deletions(-)

diff --git a/siamese_network/README.md b/siamese_network/README.md
index 973a0414a4..19b19f0e76 100644
--- a/siamese_network/README.md
+++ b/siamese_network/README.md
@@ -1,7 +1,42 @@
 # Siamese Network Example
 
+Siamese network for image similarity estimation.
+The network is composed of two identical networks, one for each input.
+The output of each network is concatenated and passed to a linear layer.
+The output of the linear layer passed through a sigmoid function.
+[FaceNet](https://arxiv.org/pdf/1503.03832.pdf) is a variant of the Siamese network.
+This implementation varies from FaceNet as we use the `ResNet-18` model from
+[Deep Residual Learning for Image Recognition](https://arxiv.org/pdf/1512.03385.pdf) as our feature extractor.
+In addition, we aren't using `TripletLoss` as the MNIST dataset is simple, so `BCELoss` can do the trick.
+
 ```bash
 pip install -r requirements.txt
 python main.py
-# CUDA_VISIBLE_DEVICES=2 python main.py  # to specify GPU id to ex. 2
 ```
+
+Optionally, you can add the following arguments to customize your execution.
+
+```bash
+--batch-size            input batch size for training (default: 64)
+--test-batch-size       input batch size for testing (default: 1000)
+--epochs                number of epochs to train (default: 14)
+--lr                    learning rate (default: 1.0)
+--gamma                 learning rate step gamma (default: 0.7)
+--no-cuda               disables CUDA training
+--no-xpu                disables XPU training
+--no-mps                disables macOS GPU training
+--dry-run               quickly check a single pass
+--seed                  random seed (default: 1)
+--log-interval          how many batches to wait before logging training status
+--save-model            Saving the current Model
+```
+
+If a GPU device (CUDA, XPU, or MPS) is detected, the example will be executed on the GPU by default; otherwise, it will run on the CPU.
+
+To disable the GPU option, add the appropriate argument to the command. For example:
+
+```bash
+python main.py --no-xpu
+```
+
+This command will execute the example on the CPU even if your system successfully detects an XPU.
diff --git a/siamese_network/main.py b/siamese_network/main.py
index 8f420a9b01..6bd55235e2 100644
--- a/siamese_network/main.py
+++ b/siamese_network/main.py
@@ -247,32 +247,39 @@ def main():
                         help='learning rate (default: 1.0)')
     parser.add_argument('--gamma', type=float, default=0.7, metavar='M',
                         help='Learning rate step gamma (default: 0.7)')
-    parser.add_argument('--no-cuda', action='store_true', default=False,
+    parser.add_argument('--no-cuda', action='store_true',
                         help='disables CUDA training')
-    parser.add_argument('--no-mps', action='store_true', default=False,
+    parser.add_argument('--no-xpu', action='store_true',
+                        help='disables XPU training')
+    parser.add_argument('--no-mps', action='store_true',
                         help='disables macOS GPU training')
-    parser.add_argument('--dry-run', action='store_true', default=False,
+    parser.add_argument('--dry-run', action='store_true',
                         help='quickly check a single pass')
     parser.add_argument('--seed', type=int, default=1, metavar='S',
                         help='random seed (default: 1)')
     parser.add_argument('--log-interval', type=int, default=10, metavar='N',
                         help='how many batches to wait before logging training status')
-    parser.add_argument('--save-model', action='store_true', default=False,
+    parser.add_argument('--save-model', action='store_true',
                         help='For Saving the current Model')
     args = parser.parse_args()
     
     use_cuda = not args.no_cuda and torch.cuda.is_available()
+    use_xpu = not args.no_xpu and torch.xpu.is_available()
     use_mps = not args.no_mps and torch.backends.mps.is_available()
 
     torch.manual_seed(args.seed)
 
     if use_cuda:
         device = torch.device("cuda")
+    elif use_xpu:
+        device = torch.device("xpu")
     elif use_mps:
         device = torch.device("mps")
     else:
         device = torch.device("cpu")
 
+    print('Device to use: ', device)
+
     train_kwargs = {'batch_size': args.batch_size}
     test_kwargs = {'batch_size': args.test_batch_size}
     if use_cuda: