Lifelong learning supporting non-structure

.github/workflows/main.yaml

@@ -11,6 +11,9 @@ jobs:
   verify-and-lint:
     runs-on: ubuntu-latest
     name: Verify codegen/vendor/licenses, do lint
+    strategy:
+      matrix:
+        python-version: [ "3.6", "3.7", "3.8", "3.9" ]
     env:
       GOPATH: ${{ github.workspace }}
 
@@ -50,6 +53,17 @@ jobs:
         run: pycodestyle lib
         working-directory: ${{ env.CODE_DIR }}
 
+      - name: Set python version
+        uses: actions/setup-python@v3
+        with:
+          python-version: ${{ matrix.python-version }}
+
+        - name: Run python lint test
+          run: |
+            python -m pip install  pylint
+            pylint lib
+          working-directory: ${{ env.CODE_DIR }}
+
   build:
     runs-on: ubuntu-latest
     name: build gm and lc

examples/lifelong_learning/RFNet/accuracy.py

@@ -0,0 +1,38 @@
+from basemodel import val_args
+from utils.metrics import Evaluator
+from tqdm import tqdm
+from dataloaders import make_data_loader
+from sedna.common.class_factory import ClassType, ClassFactory
+
+__all__ = ('accuracy')
+
+@ClassFactory.register(ClassType.GENERAL)
+def accuracy(y_true, y_pred, **kwargs):
+    args = val_args()
+    _, _, test_loader, num_class = make_data_loader(args, test_data=y_true)
+    evaluator = Evaluator(num_class)
+
+    tbar = tqdm(test_loader, desc='\r')
+    for i, (sample, img_path) in enumerate(tbar):
+        if args.depth:
+            image, depth, target = sample['image'], sample['depth'], sample['label']
+        else:
+            image, target = sample['image'], sample['label']
+        if args.cuda:
+            image, target = image.cuda(), target.cuda()
+            if args.depth:
+                depth = depth.cuda()
+
+        target[target > evaluator.num_class-1] = 255
+        target = target.cpu().numpy()
+        # Add batch sample into evaluator
+        evaluator.add_batch(target, y_pred[i])
+
+    # Test during the training
+    # Acc = evaluator.Pixel_Accuracy()
+    CPA = evaluator.Pixel_Accuracy_Class()
+    mIoU = evaluator.Mean_Intersection_over_Union()
+    FWIoU = evaluator.Frequency_Weighted_Intersection_over_Union()
+
+    print("CPA:{}, mIoU:{}, fwIoU: {}".format(CPA, mIoU, FWIoU))
+    return CPA