faster-rcnn | some tricks on faster-rcnn to improve performance | Machine Learning library

I'm trying to switch off batch norm layers in a faster-rcnn model for evaluation mode.

I'm doing a sanity check atm:

Similar to this question:

Where can I find model.ckpt in faster_rcnn_resnet50_coco model? (this solution doesn't work for me)

I have downloaded the ssd_resnet152_v1_fpn_1024x1024_coco17_tpu-8 with the intention of using it as a starting point. I am using the sample model configuration associated with that model in the TF model zoo.

I am only changing the num classes and paths for tuning, training and eval.

With:

I am trying to train the torchvision Faster R-CNN model for object detection on my custom data. I used the code in torchvision object detection fine-tuning tutorial. But getting this error:

I use the Tensorflow Object Detection API to create an AI for Faster-RCNN. GitHub:Tensorflow/models

What kind of resizing function does "keep_aspect_ratio_resizer {" in the config file have?

I prepared images of 1920 x 1080 pixels and set "min dimension:" and "max dimension:" described immediately after "keep_aspect_ratio_resizer {" in the config file to 768 respectively.

In this case, the 1920x1080 pixel image would be resized to 768x768 pixels and input to the CNN. At this time, will the original ratio of the image (16: 9) be maintained? Namely, when the image is resized to 768x768 pixels, will the long sides of the image be converted to 768 pixels and black bars will be added in the margin of the image?

Or does the image ratio change from 16: 9 to 1: 1 and become contort when this setting?

If anyone knows about this, please let me know.

Thank you!

I have a multi-output model in Keras (18 outputs to be precise), with a loss function for each output. I am trying to mimick the Region Proposal Network in faster-RCNN. Before training I want to make sure the gradients of my model are in order, where I have a snippet as follows:

I am training a Faster-RCNN model by Detectron2 in Google Colab. I would like to track my experiments with Weights and Biases (WandB).

My dataset is uploaded to Google Drive and mounted to the session via:

I'm trying to replicate bounding box regression technique used in faster-rcnn as given here. I've made a decoding fuunction and an encoding function. Ideally, when passing a bounding box to the encoder and then decoding it, I should get the same bounding box.

Here, are my input bounding boxes:

there!

When running test_net.py in pytorch1.0 Faster R-CNN and demo.py on coco dataset with faster_rcnn_1_10_9771.pth(the pretrained resnet101 model on coco dataset provided by jwyang), I encounter the same errors below :

I am trying to train MaskRCNN to detect and segment apples using the dataset from this paper,

github link to code being used

I am simply following the instructions as provided in the ReadMe file..

Here is the output on console