locating-objects-without-bboxes
locating-objects-without-bboxes copied to clipboard
javiribera
PyTorch code for "Locating objects without bounding boxes" - Loss function and trained models
Hello Javier, I'm trying to understand your WHD forward function, but fail to understand the dimension of `normalized_y`. ```python # One by one prob_map_b = prob_map[b, :, :] gt_b =...
The maximum possible distance is calculated with resized image size. https://github.com/javiribera/locating-objects-without-bboxes/blob/e51f75ec925f67bb4054ab4a6e9b20d1d8e689cc/object-locator/losses.py#L143 But this should be calculated with the original image size, as bellow code also calculates distances in the original...
Hi, thanks for the great work! When I was training with my own data, the bottleneck of the whole training was apparently the validation process since it's using batch size...
In your paper, figure 8 shows the f1-scores on three dataset are over 88.6 on r=5. however,in my opinion, the figure 6 shows the f1-scores on r=5 is under 60....
Hi, I was wandering what are is the difference between "np.sum(detected_pts)" (true positives count) and "np.sum(detected_gt)" which is used to estimate false negatives count?. My understanding is that gt are...
Hello, Thanks for this nice paper and the code. Of my understanding, in you code (WeightedHausdorffDistance class), the ground truth gt is a list of point corresponding to different objects....
I'm trying to replicate your training process using the “mall,lambdaa=1,BS=32,Adam,LR1e-4.ckpt”. I find that there is still training space after loading weights, and the loss of verification set is very large....
Can anyone provide the link to download the dataset? Thank you!
The requested URL /~ccloy/downloads_mall_dataset.html was not found on this server.
Hi, @chenyuhao @javiribera @dguera Your Pupil Dataset's Link page is failed. I me this internet error message. "Link page could not be found." How can I get the Pupil dataset?...
Metadata
Owner
Metadata
PyTorch code for "Locating objects without bounding boxes" - Loss function and trained models