hdjsjyl

How to computer FLOPs and number of parameters?

3

How to computer FLOPs and number of parameters?

Any module is used to cope with ignore annotations automatically?

3

Thanks for your excellent work. Does the code have a specific module to cope with ignore annotations automatically? Thanks

Advice for checking the loss to finetune the parameters to fit Faster R-CNN to our own dataset?

1

Advice for checking the loss to finetune the parameters to fit Faster R-CNN to our own dataset?

Is the ground truth mask a binary mask (only 0 or 1)?

2

Hi Author, Thanks for your excellent work! I would like to ask whether the ground truth and prediction are binary masks (only includes 0 or 1)? If the prediction and...

Does it require the input and output have the same size?

3

Hi Authors, Thanks for your excellent work. I just want to know whether I can use different sizes of the input and output to train the model. For example, the...

Each layer is a patch or each spatial location is a patch? What is the code part corresponding “patch” in patch-NCE?

1

Each layer is a patch or each spatial location is a patch? What is the code part corresponding “patch” in patch-NCE? Any advice would be appreciated, thanks!

IOError: [Errno 2] No such file or directory: 'res/org0.jpg'

2

When I run FCN.py to get prediction result, it shows that " IOError: [Errno 2] No such file or directory: 'res/org0.jpg' ", what should I do? Before prediction, I must...

Hi Author, Thanks for your excellent work. I would like to ask whether the ground truth and prediction are binary masks (only includes 0 or 1)? If the prediction and...

Hi Bowen, Thanks for your excellent work. I am newer about segmentation tasks. I would like to ask could you point the Mask IoU you are using in the paper...

/rfcn/../lib/bbox/bbox_transform.py:82: RuntimeWarning: divide by zero encountered in divide targets_dw = np.log(gt_widths / ex_widths) /rfcn/../lib/bbox/bbox_transform.py:114: RuntimeWarning: overflow encountered in exp pred_w = np.exp(dw) * widths[:, np.newaxis] /rfcn/../lib/bbox/bbox_transform.py:115: RuntimeWarning: overflow encountered in exp pred_h = np.exp(dh) * heights[:, np.newaxis]

3

Dear author, thanks for you code. When I change it to my own dataset, I met this problem which makes the RPNL1Loss very big such as 22719 or nan. Do...