Pramay
Pramay
Hi, I was going through the reconstruction code and had some doubts regarding the reference coordinate frame. Here https://github.com/mapillary/OpenSfM/blob/d087aa64159d18e919ac4c5bd25ab0d27b497fad/opensfm/reconstruction.py#L597 we set the reference in some world coordinate frame. And during...
1) ImportError: cannot import name ‘bernoulli’ 2) AttributeError: module ‘tensorflow.python.platform.flags’ has no attribute ‘_FlagValues’ 3) ValueError: num_units is not a valid argument for GRUCell class. Available arguments are: set()
I tested the model as it is and got very poor results. Any idea why??   
Hi I trained the model on colab. How can I restore the last saved checkpoints?
I have a trained Mask RCNN model using detectron2. I need to retrain the model from scratch with the KL loss and need box standard deviations also as outputs. Can...
Can you provide pre trained model file ?
Hi, I did not find an option to resize images for training. Also while inferencing if I resize the images to 384 by changing these lines https://github.com/Wovchena/text-detection-fots.pytorch/blob/04b969c87491630dce38cdb48932aa33115798c6/test.py#L20 nothing is predicted...
I am facing this issue - ```Epoch 0 Test: 0%| | 0/500 [00:00
How to handle the case when my dataset contains images with no texts. .i.e empty annotations files Right now it gives - ```ValueError: need at least one array to stack```...
Hi In code, if we set use_tensorrt as True the tensorrt context is being created at runtime. Can I save the tensorrt engine before running the model, and load it...