fix conflicts with dev-1.x

README_zh-CN.md

@@ -53,9 +53,9 @@ MMDeploy 是 [OpenMMLab](https://openmmlab.com/) 模型部署工具箱，**为
 
 ### 支持多种推理后端
 
-| ONNX Runtime | TensorRT | ppl.nn | ncnn | OpenVINO | LibTorch | snpe | Ascend | Core ML | RKNN | more                                           |
-| ------------ | -------- | ------ | ---- | -------- | -------- | ---- | ------ | ------- | ---- | ---------------------------------------------- |
-| ✔️           | ✔️       | ✔️     | ✔️   | ✔️       | ✔️       | ✔️   | ✔️     | ✔️      | ✔️   | [benchmark](docs/en/03-benchmark/benchmark.md) |
+| ONNX Runtime | TensorRT | ppl.nn | ncnn | OpenVINO | LibTorch | snpe | Ascend | Core ML | RKNN | more                                              |
+| ------------ | -------- | ------ | ---- | -------- | -------- | ---- | ------ | ------- | ---- | ------------------------------------------------- |
+| ✔️           | ✔️       | ✔️     | ✔️   | ✔️       | ✔️       | ✔️   | ✔️     | ✔️      | ✔️   | [benchmark](docs/zh_cn/03-benchmark/benchmark.md) |
 
 ### SDK 可高度定制化
 

mmdeploy/codebase/mmocr/deploy/mmocr.py

@@ -19,5 +19,5 @@ class MMOCR(MMCodebase):
             register_all_modules as register_all_modules_mmdet
         from mmocr.utils.setup_env import \
             register_all_modules as register_all_modules_mmocr
-        register_all_modules_mmocr(False)
-        register_all_modules_mmdet(True)
+        register_all_modules_mmocr(True)
+        register_all_modules_mmdet(False)

tests/test_codebase/test_mmdet/test_mmdet_models.py

@@ -1659,107 +1659,6 @@ def test_yolox_head_predict_by_feat_ncnn():
         assert rewrite_outputs.shape[-1] == 6
 
 
-def get_vfnet_head_model():
-    """VFNet Head Config."""
-    test_cfg = Config(
-        dict(
-            deploy_nms_pre=0,
-            min_bbox_size=0,
-            score_thr=0.05,
-            nms=dict(type='nms', iou_threshold=0.5),
-            max_per_img=100))
-    from mmdet.models.dense_heads import VFNetHead
-    model = VFNetHead(num_classes=4, in_channels=1, test_cfg=test_cfg)
-
-    model.requires_grad_(False)
-    model.cpu().eval()
-    return model
-
-
-@pytest.mark.parametrize('backend_type',
-                         [Backend.OPENVINO, Backend.ONNXRUNTIME])
-def test_predict_by_feat_of_vfnet_head(backend_type: Backend):
-    """Test predict_by_feat rewrite of VFNet head."""
-    check_backend(backend_type)
-    vfnet_head = get_vfnet_head_model()
-    vfnet_head.cpu().eval()
-    s = 16
-    batch_img_metas = [{
-        'scale_factor': np.ones(4),
-        'pad_shape': (s, s, 3),
-        'img_shape': (s, s, 3)
-    }]
-    output_names = ['dets', 'labels']
-    deploy_cfg = Config(
-        dict(
-            backend_config=dict(type=backend_type.value),
-            onnx_config=dict(output_names=output_names, input_shape=None),
-            codebase_config=dict(
-                type='mmdet',
-                task='ObjectDetection',
-                post_processing=dict(
-                    score_threshold=0.05,
-                    iou_threshold=0.5,
-                    max_output_boxes_per_class=200,
-                    pre_top_k=-1,
-                    keep_top_k=100,
-                    background_label_id=-1,
-                ))))
-
-    seed_everything(1234)
-    cls_score = [
-        torch.rand(1, vfnet_head.num_classes, pow(2, i), pow(2, i))
-        for i in range(5, 0, -1)
-    ]
-    seed_everything(5678)
-    bboxes = [torch.rand(1, 4, pow(2, i), pow(2, i)) for i in range(5, 0, -1)]
-    seed_everything(9101)
-
-    model_inputs = {
-        'cls_scores': cls_score,
-        'bbox_preds': bboxes,
-        'batch_img_metas': batch_img_metas
-    }
-    model_outputs = get_model_outputs(vfnet_head, 'predict_by_feat',
-                                      model_inputs)
-
-    batch_img_metas[0]['img_shape'] = torch.Tensor([s, s])
-    wrapped_model = WrapModel(
-        vfnet_head,
-        'predict_by_feat',
-        batch_img_metas=batch_img_metas,
-        with_nms=True)
-    rewrite_inputs = {'cls_scores': cls_score, 'bbox_preds': bboxes}
-    rewrite_outputs, is_backend_output = get_rewrite_outputs(
-        wrapped_model=wrapped_model,
-        model_inputs=rewrite_inputs,
-        deploy_cfg=deploy_cfg)
-
-    if is_backend_output:
-        # hard code to make two tensors with the same shape
-        # rewrite and original codes applied different nms strategy
-        min_shape = min(model_outputs[0].bboxes.shape[0],
-                        rewrite_outputs[0].shape[1], 1)
-        for i in range(len(model_outputs)):
-            assert np.allclose(
-                model_outputs[i].bboxes[:min_shape],
-                rewrite_outputs[0][i, :min_shape, :4],
-                rtol=1e-03,
-                atol=1e-05)
-            assert np.allclose(
-                model_outputs[i].scores[:min_shape],
-                rewrite_outputs[0][i, :min_shape, 4],
-                rtol=1e-03,
-                atol=1e-05)
-            assert np.allclose(
-                model_outputs[i].labels[:min_shape],
-                rewrite_outputs[1][i, :min_shape],
-                rtol=1e-03,
-                atol=1e-05)
-    else:
-        assert rewrite_outputs is not None
-
-
 def get_deploy_cfg(backend_type: Backend, ir_type: str):
     return Config(
         dict(

tests/test_codebase/test_mmpose/test_mmpose_models.py

@@ -49,11 +49,7 @@ def test_heatmaphead_predict(backend_type: Backend):
 def get_msmu_head():
     from mmpose.models.heads import MSPNHead
     model = MSPNHead(
-        num_stages=1,
-        num_units=1,
-        out_shape=(32, 48),
-        unit_channels=16,
-        level_indices=[0])
+        num_stages=1, num_units=1, out_shape=(32, 48), unit_channels=16)
     model.requires_grad_(False)
     return model