Python mmdet.core.tensor2imgs() Examples

The following are 30 code examples of mmdet.core.tensor2imgs(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module mmdet.core , or try the search function .
Example #1
Source File: rpn.py    From Feature-Selective-Anchor-Free-Module-for-Single-Shot-Object-Detection with Apache License 2.0 5 votes vote down vote up 
def forward_train(self,
                      img,
                      img_meta,
                      gt_bboxes=None,
                      gt_bboxes_ignore=None):
        if self.train_cfg.rpn.get('debug', False):
            self.rpn_head.debug_imgs = tensor2imgs(img)

        x = self.extract_feat(img)
        rpn_outs = self.rpn_head(x)

        rpn_loss_inputs = rpn_outs + (gt_bboxes, img_meta, self.train_cfg.rpn)
        losses = self.rpn_head.loss(
            *rpn_loss_inputs, gt_bboxes_ignore=gt_bboxes_ignore)
        return losses
Example #2
Source File: rpn.py    From RDSNet with Apache License 2.0 5 votes vote down vote up 
def forward_train(self,
                      img,
                      img_meta,
                      gt_bboxes=None,
                      gt_bboxes_ignore=None):
        if self.train_cfg.rpn.get('debug', False):
            self.rpn_head.debug_imgs = tensor2imgs(img)

        x = self.extract_feat(img)
        rpn_outs = self.rpn_head(x)

        rpn_loss_inputs = rpn_outs + (gt_bboxes, img_meta, self.train_cfg.rpn)
        losses = self.rpn_head.loss(
            *rpn_loss_inputs, gt_bboxes_ignore=gt_bboxes_ignore)
        return losses
Example #3
Source File: rpn.py    From RDSNet with Apache License 2.0 5 votes vote down vote up 
def show_result(self, data, result, dataset=None, top_k=20):
        """Show RPN proposals on the image.

        Although we assume batch size is 1, this method supports arbitrary
        batch size.
        """
        img_tensor = data['img'][0]
        img_metas = data['img_meta'][0].data[0]
        imgs = tensor2imgs(img_tensor, **img_metas[0]['img_norm_cfg'])
        assert len(imgs) == len(img_metas)
        for img, img_meta in zip(imgs, img_metas):
            h, w, _ = img_meta['img_shape']
            img_show = img[:h, :w, :]
            mmcv.imshow_bboxes(img_show, result, top_k=top_k)
Example #4
Source File: rpn.py    From IoU-Uniform-R-CNN with Apache License 2.0 5 votes vote down vote up 
def forward_train(self,
                      img,
                      img_meta,
                      gt_bboxes=None,
                      gt_bboxes_ignore=None):
        if self.train_cfg.rpn.get('debug', False):
            self.rpn_head.debug_imgs = tensor2imgs(img)

        x = self.extract_feat(img)
        rpn_outs = self.rpn_head(x)

        rpn_loss_inputs = rpn_outs + (gt_bboxes, img_meta, self.train_cfg.rpn)
        losses = self.rpn_head.loss(
            *rpn_loss_inputs, gt_bboxes_ignore=gt_bboxes_ignore)
        return losses
Example #5
Source File: rpn.py    From Reasoning-RCNN with Apache License 2.0 5 votes vote down vote up 
def forward_train(self, img, img_meta, gt_bboxes=None):
        if self.train_cfg.rpn.get('debug', False):
            self.rpn_head.debug_imgs = tensor2imgs(img)

        x = self.extract_feat(img)
        rpn_outs = self.rpn_head(x)

        rpn_loss_inputs = rpn_outs + (gt_bboxes, img_meta, self.train_cfg.rpn)
        losses = self.rpn_head.loss(*rpn_loss_inputs)
        return losses
Example #6
Source File: rpn.py    From Reasoning-RCNN with Apache License 2.0 5 votes vote down vote up 
def show_result(self, data, result, img_norm_cfg):
        """Show RPN proposals on the image.

        Although we assume batch size is 1, this method supports arbitrary
        batch size.
        """
        img_tensor = data['img'][0]
        img_metas = data['img_meta'][0].data[0]
        imgs = tensor2imgs(img_tensor, **img_norm_cfg)
        assert len(imgs) == len(img_metas)
        for img, img_meta in zip(imgs, img_metas):
            h, w, _ = img_meta['img_shape']
            img_show = img[:h, :w, :]
            mmcv.imshow_bboxes(img_show, result, top_k=20)
Example #7
Source File: rpn.py    From Libra_R-CNN with Apache License 2.0 5 votes vote down vote up 
def forward_train(self,
                      img,
                      img_meta,
                      gt_bboxes=None,
                      gt_bboxes_ignore=None):
        if self.train_cfg.rpn.get('debug', False):
            self.rpn_head.debug_imgs = tensor2imgs(img)

        x = self.extract_feat(img)
        rpn_outs = self.rpn_head(x)

        rpn_loss_inputs = rpn_outs + (gt_bboxes, img_meta, self.train_cfg.rpn)
        losses = self.rpn_head.loss(
            *rpn_loss_inputs, gt_bboxes_ignore=gt_bboxes_ignore)
        return losses
Example #8
Source File: rpn.py    From Libra_R-CNN with Apache License 2.0 5 votes vote down vote up 
def show_result(self, data, result, img_norm_cfg, dataset=None, top_k=20):
        """Show RPN proposals on the image.

        Although we assume batch size is 1, this method supports arbitrary
        batch size.
        """
        img_tensor = data['img'][0]
        img_metas = data['img_meta'][0].data[0]
        imgs = tensor2imgs(img_tensor, **img_norm_cfg)
        assert len(imgs) == len(img_metas)
        for img, img_meta in zip(imgs, img_metas):
            h, w, _ = img_meta['img_shape']
            img_show = img[:h, :w, :]
            mmcv.imshow_bboxes(img_show, result, top_k=top_k)
Example #9
Source File: rpn.py    From FoveaBox with Apache License 2.0 5 votes vote down vote up 
def forward_train(self,
                      img,
                      img_meta,
                      gt_bboxes=None,
                      gt_bboxes_ignore=None):
        if self.train_cfg.rpn.get('debug', False):
            self.rpn_head.debug_imgs = tensor2imgs(img)

        x = self.extract_feat(img)
        rpn_outs = self.rpn_head(x)

        rpn_loss_inputs = rpn_outs + (gt_bboxes, img_meta, self.train_cfg.rpn)
        losses = self.rpn_head.loss(
            *rpn_loss_inputs, gt_bboxes_ignore=gt_bboxes_ignore)
        return losses
Example #10
Source File: rpn.py    From FoveaBox with Apache License 2.0 5 votes vote down vote up 
def show_result(self, data, result, img_norm_cfg, dataset=None, top_k=20):
        """Show RPN proposals on the image.

        Although we assume batch size is 1, this method supports arbitrary
        batch size.
        """
        img_tensor = data['img'][0]
        img_metas = data['img_meta'][0].data[0]
        imgs = tensor2imgs(img_tensor, **img_norm_cfg)
        assert len(imgs) == len(img_metas)
        for img, img_meta in zip(imgs, img_metas):
            h, w, _ = img_meta['img_shape']
            img_show = img[:h, :w, :]
            mmcv.imshow_bboxes(img_show, result, top_k=top_k)
Example #11
Source File: rpn.py    From Cascade-RPN with Apache License 2.0 5 votes vote down vote up 
def forward_train(self,
                      img,
                      img_meta,
                      gt_bboxes=None,
                      gt_bboxes_ignore=None):
        if self.train_cfg.rpn.get('debug', False):
            self.rpn_head.debug_imgs = tensor2imgs(img)

        x = self.extract_feat(img)
        rpn_outs = self.rpn_head(x)

        rpn_loss_inputs = rpn_outs + (gt_bboxes, img_meta, self.train_cfg.rpn)
        losses = self.rpn_head.loss(
            *rpn_loss_inputs, gt_bboxes_ignore=gt_bboxes_ignore)
        return losses
Example #12
Source File: rpn.py    From Cascade-RPN with Apache License 2.0 5 votes vote down vote up 
def show_result(self, data, result, dataset=None, top_k=20):
        """Show RPN proposals on the image.

        Although we assume batch size is 1, this method supports arbitrary
        batch size.
        """
        img_tensor = data['img'][0]
        img_metas = data['img_meta'][0].data[0]
        imgs = tensor2imgs(img_tensor, **img_metas[0]['img_norm_cfg'])
        assert len(imgs) == len(img_metas)
        for img, img_meta in zip(imgs, img_metas):
            h, w, _ = img_meta['img_shape']
            img_show = img[:h, :w, :]
            mmcv.imshow_bboxes(img_show, result, top_k=top_k)
Example #13
Source File: rpn.py    From IoU-Uniform-R-CNN with Apache License 2.0 5 votes vote down vote up 
def show_result(self, data, result, dataset=None, top_k=20):
        """Show RPN proposals on the image.

        Although we assume batch size is 1, this method supports arbitrary
        batch size.
        """
        img_tensor = data['img'][0]
        img_metas = data['img_meta'][0].data[0]
        imgs = tensor2imgs(img_tensor, **img_metas[0]['img_norm_cfg'])
        assert len(imgs) == len(img_metas)
        for img, img_meta in zip(imgs, img_metas):
            h, w, _ = img_meta['img_shape']
            img_show = img[:h, :w, :]
            mmcv.imshow_bboxes(img_show, result, top_k=top_k)
Example #14
Source File: rpn.py    From Feature-Selective-Anchor-Free-Module-for-Single-Shot-Object-Detection with Apache License 2.0 5 votes vote down vote up 
def show_result(self, data, result, dataset=None, top_k=20):
        """Show RPN proposals on the image.

        Although we assume batch size is 1, this method supports arbitrary
        batch size.
        """
        img_tensor = data['img'][0]
        img_metas = data['img_meta'][0].data[0]
        imgs = tensor2imgs(img_tensor, **img_metas[0]['img_norm_cfg'])
        assert len(imgs) == len(img_metas)
        for img, img_meta in zip(imgs, img_metas):
            h, w, _ = img_meta['img_shape']
            img_show = img[:h, :w, :]
            mmcv.imshow_bboxes(img_show, result, top_k=top_k)
Example #15
Source File: rpn.py    From kaggle-imaterialist with MIT License 5 votes vote down vote up 
def forward_train(self,
                      img,
                      img_meta,
                      gt_bboxes=None,
                      gt_bboxes_ignore=None):
        if self.train_cfg.rpn.get('debug', False):
            self.rpn_head.debug_imgs = tensor2imgs(img)

        x = self.extract_feat(img)
        rpn_outs = self.rpn_head(x)

        rpn_loss_inputs = rpn_outs + (gt_bboxes, img_meta, self.train_cfg.rpn)
        losses = self.rpn_head.loss(
            *rpn_loss_inputs, gt_bboxes_ignore=gt_bboxes_ignore)
        return losses
Example #16
Source File: rpn.py    From kaggle-imaterialist with MIT License 5 votes vote down vote up 
def show_result(self, data, result, img_norm_cfg, dataset=None, top_k=20):
        """Show RPN proposals on the image.

        Although we assume batch size is 1, this method supports arbitrary
        batch size.
        """
        img_tensor = data['img'][0]
        img_metas = data['img_meta'][0].data[0]
        imgs = tensor2imgs(img_tensor, **img_norm_cfg)
        assert len(imgs) == len(img_metas)
        for img, img_meta in zip(imgs, img_metas):
            h, w, _ = img_meta['img_shape']
            img_show = img[:h, :w, :]
            mmcv.imshow_bboxes(img_show, result, top_k=top_k)
Example #17
Source File: rpn.py    From hrnet with MIT License 5 votes vote down vote up 
def forward_train(self,
                      img,
                      img_meta,
                      gt_bboxes=None,
                      gt_bboxes_ignore=None):
        if self.train_cfg.rpn.get('debug', False):
            self.rpn_head.debug_imgs = tensor2imgs(img)

        x = self.extract_feat(img)
        rpn_outs = self.rpn_head(x)

        rpn_loss_inputs = rpn_outs + (gt_bboxes, img_meta, self.train_cfg.rpn)
        losses = self.rpn_head.loss(
            *rpn_loss_inputs, gt_bboxes_ignore=gt_bboxes_ignore)
        return losses
Example #18
Source File: rpn.py    From hrnet with MIT License 5 votes vote down vote up 
def show_result(self, data, result, img_norm_cfg, dataset=None, top_k=20):
        """Show RPN proposals on the image.

        Although we assume batch size is 1, this method supports arbitrary
        batch size.
        """
        img_tensor = data['img'][0]
        img_metas = data['img_meta'][0].data[0]
        imgs = tensor2imgs(img_tensor, **img_norm_cfg)
        assert len(imgs) == len(img_metas)
        for img, img_meta in zip(imgs, img_metas):
            h, w, _ = img_meta['img_shape']
            img_show = img[:h, :w, :]
            mmcv.imshow_bboxes(img_show, result, top_k=top_k)
Example #19
Source File: rpn.py    From CenterNet with Apache License 2.0 5 votes vote down vote up 
def forward_train(self,
                      img,
                      img_meta,
                      gt_bboxes=None,
                      gt_bboxes_ignore=None):
        if self.train_cfg.rpn.get('debug', False):
            self.rpn_head.debug_imgs = tensor2imgs(img)

        x = self.extract_feat(img)
        rpn_outs = self.rpn_head(x)

        rpn_loss_inputs = rpn_outs + (gt_bboxes, img_meta, self.train_cfg.rpn)
        losses = self.rpn_head.loss(
            *rpn_loss_inputs, gt_bboxes_ignore=gt_bboxes_ignore)
        return losses
Example #20
Source File: rpn.py    From CenterNet with Apache License 2.0 5 votes vote down vote up 
def show_result(self, data, result, img_norm_cfg, dataset=None, top_k=20):
        """Show RPN proposals on the image.

        Although we assume batch size is 1, this method supports arbitrary
        batch size.
        """
        img_tensor = data['img'][0]
        img_metas = data['img_meta'][0].data[0]
        imgs = tensor2imgs(img_tensor, **img_norm_cfg)
        assert len(imgs) == len(img_metas)
        for img, img_meta in zip(imgs, img_metas):
            h, w, _ = img_meta['img_shape']
            img_show = img[:h, :w, :]
            mmcv.imshow_bboxes(img_show, result, top_k=top_k)
Example #21
Source File: rpn.py    From ttfnet with Apache License 2.0 5 votes vote down vote up 
def forward_train(self,
                      img,
                      img_meta,
                      gt_bboxes=None,
                      gt_bboxes_ignore=None):
        if self.train_cfg.rpn.get('debug', False):
            self.rpn_head.debug_imgs = tensor2imgs(img)

        x = self.extract_feat(img)
        rpn_outs = self.rpn_head(x)

        rpn_loss_inputs = rpn_outs + (gt_bboxes, img_meta, self.train_cfg.rpn)
        losses = self.rpn_head.loss(
            *rpn_loss_inputs, gt_bboxes_ignore=gt_bboxes_ignore)
        return losses
Example #22
Source File: rpn.py    From ttfnet with Apache License 2.0 5 votes vote down vote up 
def show_result(self, data, result, dataset=None, top_k=20):
        """Show RPN proposals on the image.

        Although we assume batch size is 1, this method supports arbitrary
        batch size.
        """
        img_tensor = data['img'][0]
        img_metas = data['img_meta'][0].data[0]
        imgs = tensor2imgs(img_tensor, **img_metas[0]['img_norm_cfg'])
        assert len(imgs) == len(img_metas)
        for img, img_meta in zip(imgs, img_metas):
            h, w, _ = img_meta['img_shape']
            img_show = img[:h, :w, :]
            mmcv.imshow_bboxes(img_show, result, top_k=top_k)
Example #23
Source File: rpn.py    From AugFPN with Apache License 2.0 5 votes vote down vote up 
def forward_train(self,
                      img,
                      img_meta,
                      gt_bboxes=None,
                      gt_bboxes_ignore=None):
        if self.train_cfg.rpn.get('debug', False):
            self.rpn_head.debug_imgs = tensor2imgs(img)

        x = self.extract_feat(img)
        rpn_outs = self.rpn_head(x)

        rpn_loss_inputs = rpn_outs + (gt_bboxes, img_meta, self.train_cfg.rpn)
        losses = self.rpn_head.loss(
            *rpn_loss_inputs, gt_bboxes_ignore=gt_bboxes_ignore)
        return losses
Example #24
Source File: rpn.py    From AugFPN with Apache License 2.0 5 votes vote down vote up 
def show_result(self, data, result, img_norm_cfg, dataset=None, top_k=20):
        """Show RPN proposals on the image.

        Although we assume batch size is 1, this method supports arbitrary
        batch size.
        """
        img_tensor = data['img'][0]
        img_metas = data['img_meta'][0].data[0]
        imgs = tensor2imgs(img_tensor, **img_norm_cfg)
        assert len(imgs) == len(img_metas)
        for img, img_meta in zip(imgs, img_metas):
            h, w, _ = img_meta['img_shape']
            img_show = img[:h, :w, :]
            mmcv.imshow_bboxes(img_show, result, top_k=top_k)
Example #25
Source File: rpn.py    From PolarMask with Apache License 2.0 5 votes vote down vote up 
def forward_train(self,
                      img,
                      img_meta,
                      gt_bboxes=None,
                      gt_bboxes_ignore=None):
        if self.train_cfg.rpn.get('debug', False):
            self.rpn_head.debug_imgs = tensor2imgs(img)

        x = self.extract_feat(img)
        rpn_outs = self.rpn_head(x)

        rpn_loss_inputs = rpn_outs + (gt_bboxes, img_meta, self.train_cfg.rpn)
        losses = self.rpn_head.loss(
            *rpn_loss_inputs, gt_bboxes_ignore=gt_bboxes_ignore)
        return losses
Example #26
Source File: rpn.py    From GCNet with Apache License 2.0 5 votes vote down vote up 
def show_result(self, data, result, img_norm_cfg, dataset=None, top_k=20):
        """Show RPN proposals on the image.

        Although we assume batch size is 1, this method supports arbitrary
        batch size.
        """
        img_tensor = data['img'][0]
        img_metas = data['img_meta'][0].data[0]
        imgs = tensor2imgs(img_tensor, **img_norm_cfg)
        assert len(imgs) == len(img_metas)
        for img, img_meta in zip(imgs, img_metas):
            h, w, _ = img_meta['img_shape']
            img_show = img[:h, :w, :]
            mmcv.imshow_bboxes(img_show, result, top_k=top_k)
Example #27
Source File: rpn.py    From mmdetection-annotated with Apache License 2.0 5 votes vote down vote up 
def forward_train(self,
                      img,
                      img_meta,
                      gt_bboxes=None,
                      gt_bboxes_ignore=None):
        if self.train_cfg.rpn.get('debug', False):
            self.rpn_head.debug_imgs = tensor2imgs(img)

        x = self.extract_feat(img)
        rpn_outs = self.rpn_head(x)

        rpn_loss_inputs = rpn_outs + (gt_bboxes, img_meta, self.train_cfg.rpn)
        losses = self.rpn_head.loss(
            *rpn_loss_inputs, gt_bboxes_ignore=gt_bboxes_ignore)
        return losses
Example #28
Source File: rpn.py    From mmdetection-annotated with Apache License 2.0 5 votes vote down vote up 
def show_result(self, data, result, img_norm_cfg, dataset=None, top_k=20):
        """Show RPN proposals on the image.

        Although we assume batch size is 1, this method supports arbitrary
        batch size.
        """
        img_tensor = data['img'][0]
        img_metas = data['img_meta'][0].data[0]
        imgs = tensor2imgs(img_tensor, **img_norm_cfg)
        assert len(imgs) == len(img_metas)
        for img, img_meta in zip(imgs, img_metas):
            h, w, _ = img_meta['img_shape']
            img_show = img[:h, :w, :]
            mmcv.imshow_bboxes(img_show, result, top_k=top_k)
Example #29
Source File: rpn.py    From GCNet with Apache License 2.0 5 votes vote down vote up 
def forward_train(self,
                      img,
                      img_meta,
                      gt_bboxes=None,
                      gt_bboxes_ignore=None):
        if self.train_cfg.rpn.get('debug', False):
            self.rpn_head.debug_imgs = tensor2imgs(img)

        x = self.extract_feat(img)
        rpn_outs = self.rpn_head(x)

        rpn_loss_inputs = rpn_outs + (gt_bboxes, img_meta, self.train_cfg.rpn)
        losses = self.rpn_head.loss(
            *rpn_loss_inputs, gt_bboxes_ignore=gt_bboxes_ignore)
        return losses
Example #30
Source File: rpn.py    From Grid-R-CNN with Apache License 2.0 5 votes vote down vote up 
def show_result(self, data, result, img_norm_cfg, dataset=None, top_k=20):
        """Show RPN proposals on the image.

        Although we assume batch size is 1, this method supports arbitrary
        batch size.
        """
        img_tensor = data['img'][0]
        img_metas = data['img_meta'][0].data[0]
        imgs = tensor2imgs(img_tensor, **img_norm_cfg)
        assert len(imgs) == len(img_metas)
        for img, img_meta in zip(imgs, img_metas):
            h, w, _ = img_meta['img_shape']
            img_show = img[:h, :w, :]
            mmcv.imshow_bboxes(img_show, result, top_k=top_k)