[Fix] Fix mmdet flops error

configs/cascade_rcnn/cascade-mask-rcnn_x101-32x8d_fpn_ms-3x_coco.py

@@ -7,7 +7,7 @@
         type='DetDataPreprocessor',
         mean=[103.530, 116.280, 123.675],
         std=[57.375, 57.120, 58.395],
-        to_rgb=False,
+        bgr_to_rgb=False,
         pad_size_divisor=32),
     backbone=dict(
         type='ResNeXt',

configs/cascade_rcnn/cascade-rcnn_r50-caffe_fpn_1x_coco.py

@@ -6,7 +6,7 @@
         type='DetDataPreprocessor',
         mean=[103.530, 116.280, 123.675],
         std=[1.0, 1.0, 1.0],
-        to_rgb=False,
+        bgr_to_rgb=False,
         pad_size_divisor=32),
     backbone=dict(
         norm_cfg=dict(requires_grad=False),

configs/dcnv2/metafile.yml

@@ -19,7 +19,7 @@ Collections:
 Models:
   - Name: faster-rcnn_r50_fpn_mdconv_c3-c5_1x_coco
     In Collection: Deformable Convolutional Networks v2
-    Config: configs/dcn/faster-rcnn_r50-mdconv-c3-c5_fpn_1x_coco.py
+    Config: configs/dcnv2/faster-rcnn_r50-mdconv-c3-c5_fpn_1x_coco.py
     Metadata:
       Training Memory (GB): 4.1
       inference time (ms/im):
@@ -39,7 +39,7 @@ Models:
 
   - Name: faster-rcnn_r50_fpn_mdconv_c3-c5_group4_1x_coco
     In Collection: Deformable Convolutional Networks v2
-    Config: configs/dcn/faster-rcnn_r50-mdconv-group4-c3-c5_fpn_1x_coco.py
+    Config: configs/dcnv2/faster-rcnn_r50-mdconv-group4-c3-c5_fpn_1x_coco.py
     Metadata:
       Training Memory (GB): 4.2
       inference time (ms/im):
@@ -59,7 +59,7 @@ Models:
 
   - Name: faster-rcnn_r50_fpn_mdpool_1x_coco
     In Collection: Deformable Convolutional Networks v2
-    Config: configs/dcn/faster-rcnn_r50_fpn_mdpool_1x_coco.py
+    Config: configs/dcnv2/faster-rcnn_r50_fpn_mdpool_1x_coco.py
     Metadata:
       Training Memory (GB): 5.8
       inference time (ms/im):
@@ -79,7 +79,7 @@ Models:
 
   - Name: mask-rcnn_r50_fpn_mdconv_c3-c5_1x_coco
     In Collection: Deformable Convolutional Networks v2
-    Config: configs/dcn/mask-rcnn_r50-mdconv-c3-c5_fpn_1x_coco.py
+    Config: configs/dcnv2/mask-rcnn_r50-mdconv-c3-c5_fpn_1x_coco.py
     Metadata:
       Training Memory (GB): 4.5
       inference time (ms/im):
@@ -103,7 +103,7 @@ Models:
 
   - Name: mask-rcnn_r50_fpn_fp16_mdconv_c3-c5_1x_coco
     In Collection: Deformable Convolutional Networks v2
-    Config: configs/dcn/mask-rcnn_r50-mdconv-c3-c5_fpn_amp-1x_coco.py
+    Config: configs/dcnv2/mask-rcnn_r50-mdconv-c3-c5_fpn_amp-1x_coco.py
     Metadata:
       Training Memory (GB): 3.1
       Training Techniques:

configs/mask2former/mask2former_r50_8xb2-lsj-50e_coco.py

@@ -1,5 +1,5 @@
 _base_ = ['./mask2former_r50_8xb2-lsj-50e_coco-panoptic.py']
-
+file_client_args = dict(backend='disk')
 num_things_classes = 80
 num_stuff_classes = 0
 num_classes = num_things_classes + num_stuff_classes
@@ -56,6 +56,17 @@
     dict(type='PackDetInputs')
 ]
 
+test_pipeline = [
+    dict(type='LoadImageFromFile', file_client_args=file_client_args),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    # If you don't have a gt annotation, delete the pipeline
+    dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+    dict(
+        type='PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+
 dataset_type = 'CocoDataset'
 data_root = 'data/coco/'
 
@@ -70,7 +81,8 @@
     dataset=dict(
         type=dataset_type,
         ann_file='annotations/instances_val2017.json',
-        data_prefix=dict(img='val2017/')))
+        data_prefix=dict(img='val2017/'),
+        pipeline=test_pipeline))
 test_dataloader = val_dataloader
 
 val_evaluator = dict(

configs/openimages/faster-rcnn_r50_fpn_32xb2-1x_openimages-challenge.py

@@ -17,6 +17,7 @@
     dataset=dict(
         type=dataset_type,
         ann_file='challenge2019/challenge-2019-validation-detection-bbox.txt',
+        data_prefix=dict(img='OpenImages/'),
         label_file='challenge2019/cls-label-description.csv',
         hierarchy_file='challenge2019/class_label_tree.np',
         meta_file='challenge2019/challenge-2019-validation-metas.pkl',

configs/retinanet/retinanet_r101-caffe_fpn_ms-3x_coco.py

@@ -1,5 +1,8 @@
 _base_ = './retinanet_r50-caffe_fpn_ms-3x_coco.py'
 # learning policy
 model = dict(
-    pretrained='open-mmlab://detectron2/resnet101_caffe',
-    backbone=dict(depth=101))
+    backbone=dict(
+        depth=101,
+        init_cfg=dict(
+            type='Pretrained',
+            checkpoint='open-mmlab://detectron2/resnet101_caffe')))

configs/retinanet/retinanet_r101_fpn_ms-640-800-3x_coco.py

@@ -1,5 +1,9 @@
 _base_ = ['../_base_/models/retinanet_r50_fpn.py', '../common/ms_3x_coco.py']
 # optimizer
-model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101))
+model = dict(
+    backbone=dict(
+        depth=101,
+        init_cfg=dict(type='Pretrained',
+                      checkpoint='torchvision://resnet101')))
 optim_wrapper = dict(
     optimizer=dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001))

configs/retinanet/retinanet_x101-64x4d_fpn_ms-640-800-3x_coco.py

@@ -1,6 +1,11 @@
 _base_ = ['../_base_/models/retinanet_r50_fpn.py', '../common/ms_3x_coco.py']
 # optimizer
 model = dict(
-    pretrained='open-mmlab://resnext101_64x4d',
-    backbone=dict(type='ResNeXt', depth=101, groups=64, base_width=4))
+    backbone=dict(
+        type='ResNeXt',
+        depth=101,
+        groups=64,
+        base_width=4,
+        init_cfg=dict(
+            type='Pretrained', checkpoint='open-mmlab://resnext101_64x4d')))
 optim_wrapper = dict(optimizer=dict(type='SGD', lr=0.01))

configs/seesaw_loss/metafile.yml

@@ -23,7 +23,7 @@ Collections:
 Models:
   - Name: mask-rcnn_r50_fpn_random_seesaw_loss_mstrain_2x_lvis_v1
     In Collection: Seesaw Loss
-    Config: seesaw_loss/mask-rcnn_r50_fpn_seesaw-loss_random-ms-2x_lvis-v1.py
+    Config: configs/seesaw_loss/mask-rcnn_r50_fpn_seesaw-loss_random-ms-2x_lvis-v1.py
     Metadata:
       Epochs: 24
     Results:
@@ -38,7 +38,7 @@ Models:
     Weights: https://download.openmmlab.com/mmdetection/v2.0/seesaw_loss/mask_rcnn_r50_fpn_random_seesaw_loss_mstrain_2x_lvis_v1-a698dd3d.pth
   - Name: mask-rcnn_r50_fpn_random_seesaw_loss_normed_mask_mstrain_2x_lvis_v1
     In Collection: Seesaw Loss
-    Config: seesaw_loss/mask-rcnn_r50_fpn_seesaw-loss-normed-mask_random-ms-2x_lvis-v1.py
+    Config: configs/seesaw_loss/mask-rcnn_r50_fpn_seesaw-loss-normed-mask_random-ms-2x_lvis-v1.py
     Metadata:
       Epochs: 24
     Results:
@@ -53,7 +53,7 @@ Models:
     Weights: https://download.openmmlab.com/mmdetection/v2.0/seesaw_loss/mask_rcnn_r50_fpn_random_seesaw_loss_normed_mask_mstrain_2x_lvis_v1-a1c11314.pth
   - Name: mask-rcnn_r101_fpn_seesaw-loss_random-ms-2x_lvis-v1
     In Collection: Seesaw Loss
-    Config: seesaw_loss/mask-rcnn_r101_fpn_seesaw-loss_random-ms-2x_lvis-v1.py
+    Config: configs/seesaw_loss/mask-rcnn_r101_fpn_seesaw-loss_random-ms-2x_lvis-v1.py
     Metadata:
       Epochs: 24
     Results:
@@ -68,7 +68,7 @@ Models:
     Weights: https://download.openmmlab.com/mmdetection/v2.0/seesaw_loss/mask_rcnn_r101_fpn_random_seesaw_loss_mstrain_2x_lvis_v1-8e6e6dd5.pth
   - Name: mask-rcnn_r101_fpn_seesaw-loss-normed-mask_random-ms-2x_lvis-v1
     In Collection: Seesaw Loss
-    Config: seesaw_loss/mask-rcnn_r101_fpn_seesaw-loss-normed-mask_random-ms-2x_lvis-v1.py
+    Config: configs/seesaw_loss/mask-rcnn_r101_fpn_seesaw-loss-normed-mask_random-ms-2x_lvis-v1.py
     Metadata:
       Epochs: 24
     Results:

mmdet/models/dense_heads/anchor_free_head.py

@@ -206,7 +206,8 @@ def _load_from_state_dict(self, state_dict: dict, prefix: str,
                                       strict, missing_keys, unexpected_keys,
                                       error_msgs)
 
-    def forward(self, x: Tuple[Tensor]) -> Tuple[List[Tensor], List[Tensor]]:
+    def forward(self, x: Tuple[Tensor],
+                *args) -> Tuple[List[Tensor], List[Tensor]]:
         """Forward features from the upstream network.
 
         Args:

mmdet/models/dense_heads/anchor_head.py

@@ -142,7 +142,7 @@ def forward_single(self, x: Tensor) -> Tuple[Tensor, Tensor]:
         bbox_pred = self.conv_reg(x)
         return cls_score, bbox_pred
 
-    def forward(self, x: Tuple[Tensor]) -> Tuple[List[Tensor]]:
+    def forward(self, x: Tuple[Tensor], *args) -> Tuple[List[Tensor]]:
         """Forward features from the upstream network.
 
         Args:

mmdet/models/dense_heads/atss_head.py

@@ -126,7 +126,7 @@ def _init_layers(self) -> None:
         self.scales = nn.ModuleList(
             [Scale(1.0) for _ in self.prior_generator.strides])
 
-    def forward(self, x: Tuple[Tensor]) -> Tuple[List[Tensor]]:
+    def forward(self, x: Tuple[Tensor], *args) -> Tuple[List[Tensor]]:
         """Forward features from the upstream network.
 
         Args:

mmdet/models/dense_heads/centernet_head.py

@@ -90,7 +90,7 @@ def init_weights(self) -> None:
                 if isinstance(m, nn.Conv2d):
                     normal_init(m, std=0.001)
 
-    def forward(self, x: Tuple[Tensor, ...]) -> Tuple[List[Tensor]]:
+    def forward(self, x: Tuple[Tensor, ...], *args) -> Tuple[List[Tensor]]:
         """Forward features. Notice CenterNet head does not use FPN.
 
         Args:

mmdet/models/dense_heads/corner_head.py

@@ -253,7 +253,7 @@ def init_weights(self) -> None:
                 self.tl_emb[i][-1].conv.reset_parameters()
                 self.br_emb[i][-1].conv.reset_parameters()
 
-    def forward(self, feats: Tuple[Tensor]) -> tuple:
+    def forward(self, feats: Tuple[Tensor], *args) -> tuple:
         """Forward features from the upstream network.
 
         Args:

mmdet/models/dense_heads/ddod_head.py

@@ -124,7 +124,7 @@ def init_weights(self) -> None:
         bias_cls = bias_init_with_prob(0.01)
         normal_init(self.atss_cls, std=0.01, bias=bias_cls)
 
-    def forward(self, x: Tuple[Tensor]) -> Tuple[List[Tensor]]:
+    def forward(self, x: Tuple[Tensor], *args) -> Tuple[List[Tensor]]:
         """Forward features from the upstream network.
 
         Args:

mmdet/models/dense_heads/deformable_detr_head.py

@@ -181,8 +181,7 @@ def forward(self, x: Tuple[Tensor],
                 enc_outputs_class, \
                 enc_outputs_coord.sigmoid()
         else:
-            return outputs_classes, outputs_coords, \
-                None, None
+            return outputs_classes, outputs_coords
 
     def loss_by_feat(
         self,

mmdet/models/dense_heads/fcos_head.py

@@ -118,9 +118,8 @@ def _init_layers(self) -> None:
         self.conv_centerness = nn.Conv2d(self.feat_channels, 1, 3, padding=1)
         self.scales = nn.ModuleList([Scale(1.0) for _ in self.strides])
 
-    def forward(
-            self, x: Tuple[Tensor]
-    ) -> Tuple[List[Tensor], List[Tensor], List[Tensor]]:
+    def forward(self, x: Tuple[Tensor],
+                *args) -> Tuple[List[Tensor], List[Tensor], List[Tensor]]:
         """Forward features from the upstream network.
 
         Args:

mmdet/models/dense_heads/gfl_head.py

@@ -171,7 +171,7 @@ def _init_layers(self) -> None:
         self.scales = nn.ModuleList(
             [Scale(1.0) for _ in self.prior_generator.strides])
 
-    def forward(self, x: Tuple[Tensor]) -> Tuple[List[Tensor]]:
+    def forward(self, x: Tuple[Tensor], *args) -> Tuple[List[Tensor]]:
         """Forward features from the upstream network.
 
         Args:

mmdet/models/dense_heads/guided_anchor_head.py

@@ -247,7 +247,7 @@ def forward_single(self, x: Tensor) -> Tuple[Tensor]:
         bbox_pred = self.conv_reg(x, mask)
         return cls_score, bbox_pred, shape_pred, loc_pred
 
-    def forward(self, x: List[Tensor]) -> Tuple[List[Tensor]]:
+    def forward(self, x: List[Tensor], *args) -> Tuple[List[Tensor]]:
         """Forward features from the upstream network."""
         return multi_apply(self.forward_single, x)
 

mmdet/models/dense_heads/reppoints_head.py

@@ -274,7 +274,7 @@ def gen_grid_from_reg(self, reg: Tensor,
         ], 1)
         return grid_yx, regressed_bbox
 
-    def forward(self, feats: Tuple[Tensor]) -> Tuple[Tensor]:
+    def forward(self, feats: Tuple[Tensor], *args) -> Tuple[Tensor]:
         return multi_apply(self.forward_single, feats)
 
     def forward_single(self, x: Tensor) -> Tuple[Tensor]:

mmdet/models/dense_heads/retina_sepbn_head.py

@@ -94,7 +94,7 @@ def init_weights(self) -> None:
         normal_init(self.retina_cls, std=0.01, bias=bias_cls)
         normal_init(self.retina_reg, std=0.01)
 
-    def forward(self, feats: Tuple[Tensor]) -> tuple:
+    def forward(self, feats: Tuple[Tensor], *args) -> tuple:
         """Forward features from the upstream network.
 
         Args:

mmdet/models/dense_heads/sabl_retina_head.py

@@ -199,7 +199,7 @@ def forward_single(self, x: Tensor) -> Tuple[Tensor, Tensor]:
         bbox_pred = (bbox_cls_pred, bbox_reg_pred)
         return cls_score, bbox_pred
 
-    def forward(self, feats: List[Tensor]) -> Tuple[List[Tensor]]:
+    def forward(self, feats: List[Tensor], *args) -> Tuple[List[Tensor]]:
         return multi_apply(self.forward_single, feats)
 
     def get_anchors(

mmdet/models/dense_heads/ssd_head.py

@@ -187,7 +187,8 @@ def _init_layers(self) -> None:
             self.cls_convs.append(nn.Sequential(*cls_layers))
             self.reg_convs.append(nn.Sequential(*reg_layers))
 
-    def forward(self, x: Tuple[Tensor]) -> Tuple[List[Tensor], List[Tensor]]:
+    def forward(self, x: Tuple[Tensor],
+                *args) -> Tuple[List[Tensor], List[Tensor]]:
         """Forward features from the upstream network.
 
         Args:

mmdet/models/dense_heads/tood_head.py

@@ -226,7 +226,7 @@ def init_weights(self) -> None:
         normal_init(self.tood_cls, std=0.01, bias=bias_cls)
         normal_init(self.tood_reg, std=0.01)
 
-    def forward(self, feats: Tuple[Tensor]) -> Tuple[List[Tensor]]:
+    def forward(self, feats: Tuple[Tensor], *args) -> Tuple[List[Tensor]]:
         """Forward features from the upstream network.
 
         Args:

mmdet/models/dense_heads/vfnet_head.py

@@ -219,7 +219,7 @@ def _init_layers(self) -> None:
         self.vfnet_cls = nn.Conv2d(
             self.feat_channels, self.cls_out_channels, 3, padding=1)
 
-    def forward(self, x: Tuple[Tensor]) -> Tuple[List[Tensor]]:
+    def forward(self, x: Tuple[Tensor], *args) -> Tuple[List[Tensor]]:
         """Forward features from the upstream network.
 
         Args:

mmdet/models/dense_heads/yolo_head.py

@@ -171,7 +171,7 @@ def init_weights(self) -> None:
                               bias_init_with_prob(8 / (608 / stride)**2))
             nn.init.constant_(bias.data[:, 5:], bias_init_with_prob(0.01))
 
-    def forward(self, x: Tuple[Tensor, ...]) -> tuple:
+    def forward(self, x: Tuple[Tensor, ...], *args) -> tuple:
         """Forward features from the upstream network.
 
         Args:

mmdet/models/dense_heads/yolox_head.py

@@ -211,7 +211,7 @@ def forward_single(self, x: Tensor, cls_convs: nn.Module,
 
         return cls_score, bbox_pred, objectness
 
-    def forward(self, x: Tuple[Tensor]) -> Tuple[List]:
+    def forward(self, x: Tuple[Tensor], *args) -> Tuple[List]:
         """Forward features from the upstream network.
 
         Args:

mmdet/models/detectors/single_stage.py

@@ -122,12 +122,18 @@ def _forward(
 
          Args:
             batch_inputs (Tensor): Inputs with shape (N, C, H, W).
+            batch_data_samples (list[:obj:`DetDataSample`]): Each item contains
+                the meta information of each image and corresponding
+                annotations.
 
         Returns:
             tuple[list]: A tuple of features from ``bbox_head`` forward.
         """
         x = self.extract_feat(batch_inputs)
-        results = self.bbox_head.forward(x)
+        batch_img_metas = [
+            data_samples.metainfo for data_samples in batch_data_samples
+        ]
+        results = self.bbox_head.forward(x, batch_img_metas)
         return results
 
     def extract_feat(self, batch_inputs: Tensor) -> Tuple[Tensor]:

mmdet/models/detectors/two_stage.py

@@ -119,6 +119,9 @@ def _forward(self, batch_inputs: Tensor,
 
         Args:
             batch_inputs (Tensor): Inputs with shape (N, C, H, W).
+            batch_data_samples (list[:obj:`DetDataSample`]): Each item contains
+                the meta information of each image and corresponding
+                annotations.
 
         Returns:
             tuple: A tuple of features from ``rpn_head`` and ``roi_head``
@@ -135,8 +138,8 @@ def _forward(self, batch_inputs: Tensor,
             rpn_results_list = [
                 data_sample.proposals for data_sample in batch_data_samples
             ]
-
-        roi_outs = self.roi_head.forward(x, rpn_results_list)
+        roi_outs = self.roi_head.forward(x, rpn_results_list,
+                                         batch_data_samples)
         results = results + (roi_outs, )
         return results