Skip to content

issues Search Results · repo:sgrvinod/a-PyTorch-Tutorial-to-Object-Detection language:Python

Filter by

95 results
 (107 ms)

95 results

insgrvinod/a-PyTorch-Tutorial-to-Object-Detection (press backspace or delete to remove)

Hi, In the forward path of the MultiBoxLoss() class the amount of present ground truth boxes in every image is calculated: n_objects = boxes[i].size(0) overlap = find_jaccard_overlap(boxes[i],self.priors_xy) ...
  • felix-veth
  • Opened 
    on Dec 18, 2024
  • #104

I download the dataset and the model according to the tutorial but an error like TypeError: expected np.ndarray (got numpy.ndarray) plagued me the whole afternoon. I tried searching on google and got answers ...
  • suws0501
  • 1
  • Opened 
    on Oct 22, 2024
  • #103

channge the code in utils.py 235 line original_ind = torch.LongTensor(range(true_class_boxes.size(0)), device= cuda )[true_class_images == this_image][ind] original_ind = torch.tensor(range(true_class_boxes.size(0)), ...
  • kwonseungchan
  • 1
  • Opened 
    on Jun 20, 2024
  • #102

Hi. Thanks for the repository. Could you please provide instructions to execute the programs. There are many .py files
  • PalgunaGopireddy
  • Opened 
    on May 4, 2024
  • #101

The size of the feature map after the 4th max-pooling is 19x19, then it s (19 - 3) / 1 + 1 = 17 after 3x3 pooling with stride 1, and after conv6 the size is (17 + 26 - (62 + 1)) / 1 + 1 = 17, but the size ...
  • denisshaf
  • 1
  • Opened 
    on Feb 14, 2024
  • #100

Can you tell me how to export this model to ONNF format ? (Open Neural Network Exchange)
  • AnkaEsp
  • Opened 
    on Oct 11, 2023
  • #97

I try to load the pre-train model and use 8 images as test dataset but got mAP is 0, it seems SSD did not detect anything, and the reason I just use 8 images as test dataset is because model.detect_objects ...
  • AlexHunterLeo
  • Opened 
    on Aug 23, 2023
  • #96

I mentioned in comment #94 that the prior boxes were not clipped correctly. I intended to compare the performance of using correct prior boxes versus wrong prior boxes, and just leave a comment to note ...
  • Hope1337
  • 1
  • Opened 
    on Jun 14, 2023
  • #95

image As you stated, prior box will be clipped if it out side of image, but in your code : prior_boxes.clamp_(0, 1) # (8732, 4) prior_boxes still in yolo style (which mean [cx, cy, w, h]), but if we ...
  • Hope1337
  • 12
  • Opened 
    on Jun 10, 2023
  • #94
Issue origami icon

Learn how you can use GitHub Issues to plan and track your work.

Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub Issues
ProTip! 
Restrict your search to the title by using the in:title qualifier.
Issue origami icon

Learn how you can use GitHub Issues to plan and track your work.

Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub Issues
ProTip! 
Press the
/
key to activate the search input again and adjust your query.
Issue search results · GitHub