Issue with encoder.py - Githubissues

def _get_anchor_boxes(self**, input_size):** '''Compute anchor boxes for each feature map. Args: input_size: (tensor) model input size of (w,h). Returns: boxes: (list) anchor boxes for each feature map. Each of size [#anchors,4], where #anchors = fmw * fmh * #anchors_per_cell ''' num_fms = len(self.anchor_areas) **fm_sizes = [(input_size/pow(2.,i+3)).ceil() for i in range(num_fms)] # p3 -> p7 feature map sizes** boxes = [] for i in range(num_fms): **fm_size = fm_sizes[i]** grid_size = input_size / fm_size **fm_w, fm_h = int(fm_size[0]), int(fm_size[1])** xy = meshgrid(fm_w,fm_h) + 0.5 # [fm_h*fm_w, 2] xy = (xy*grid_size).view(fm_h,fm_w,1,2).expand(fm_h,fm_w,9,2) wh = self.anchor_wh[i].view(1,1,9,2).expand(fm_h,fm_w,9,2) box = torch.cat([xy,wh], 3) # [x,y,w,h] boxes.append(box.view(-1,4)) return torch.cat(boxes, 0)

Would like to clarify the input for _get_anchor_boxes function under encoder.py is a tuple or a int?

As I realised after the code went to line 50 it is not able to assign the values to fm_w and fm_h.
def _get_anchor_boxes(self**, input_size):**
        '''Compute anchor boxes for each feature map.
        Args:
          input_size: (tensor) model input size of (w,h).
        Returns:
          boxes: (list) anchor boxes for each feature map. Each of size [#anchors,4],
                        where #anchors = fmw * fmh * #anchors_per_cell
        '''
        num_fms = len(self.anchor_areas)
        **fm_sizes = [(input_size/pow(2.,i+3)).ceil() for i in range(num_fms)]  # p3 -> p7 feature map sizes**

        boxes = []
        for i in range(num_fms):
            **fm_size = fm_sizes[i]**
            grid_size = input_size / fm_size
            **fm_w, fm_h = int(fm_size[0]), int(fm_size[1])**
            xy = meshgrid(fm_w,fm_h) + 0.5  # [fm_h*fm_w, 2]
            xy = (xy*grid_size).view(fm_h,fm_w,1,2).expand(fm_h,fm_w,9,2)
            wh = self.anchor_wh[i].view(1,1,9,2).expand(fm_h,fm_w,9,2)
            box = torch.cat([xy,wh], 3)  # [x,y,w,h]
            boxes.append(box.view(-1,4))
        return torch.cat(boxes, 0)
I assign input_size as a integer for example 448, and the output of fm_size is a list of elements. Not a list of tuples. So I am confused as to what should be the values inside fm_size. And in general the purpose of doing this encoder.py

If anybody is able to explain to me the purpose of it that would be great! Thank you so much!

@kuangliu

kuangliu / pytorch-retinanet

Issue with encoder.py #79