Mask_RCNN

Mask_RCNN copied to clipboard

model.detect with tf-gpu has a slow speed

1

It tooks 50s to detect a picture with i5-8700 CPU and GTX 1060. tensorflow-gpu 1.5.0 Keras 2.2.0 You see many of the same problems in `Issues` as follow: Detecion time...

KainanSu

OSError: Unable to open file (truncated file: eof = 74436151, sblock->base_addr = 0, stored_eof = 257557808)

30

I want to use Mask-RCNN demo.py in my jupyter notebook but when i ran the the demo code , i faced such a problem OSError Traceback (most recent call last)...

farzadzare

mrcnn_class_loss() keeps fluctuating

5

Hi all, I am currently using the [Mask_RCNN Model](https://github.com/Kamlesh364/Mask-RCNN-TF2.7.0-keras2.7.0) for a object tracking project. I have completed the training process successfully, with the loss functions displayed below (read from the...

ErinYang96

IndexError: list index out of range

3

here is the error i got it . Traceback (most recent call last): File "C:\Users\刘\Desktop\yolov3-coco-tower\yolo_custom_detection\yolo_object_detection.py", line 68, in label = str(classes[class_ids[i]]) IndexError: list index out of range Process finished with...

fatana1

could anybody help?

2


STRUGGLE1999

Hi everyone, is the parameter train_rois_per_image meant per class or in general per image? As an example: I have 3 classes and I know that each image has exactly one...

Testbild

Bug/fix parallel mode

1

svbeuningen

How augmentation is done in this implementation of mask rcnn?

7

When I apply following data augmentation technique > iaa.Sequential([iaa.Fliplr(0.5)]) will the augmentation be applied to each training set and both non augmented and augmented images are used as training sample...

hrithikpuri5

Custom training using different sizes of images in dataset

4

Hi I am doing a custom training of Mask RCNN with my dataset of different sizes and resolution of images. I have already done annotating using VGG annotating tool. I...

MatchaCookies

STRUGGLE1999