Objectness | BING Objectness proposal estimator linux/mac/windows | Computer Vision library

I am trying to train an object detection algorithm with samples that I have labeled using Label-img. My images have dimensions of 1100 x 1100 pixels. The algorithm I am using is the Faster R-CNN Inception ResNet V2 1024x1024, found on the TensorFlow 2 Detection Model Zoo. The specs of my operation are as follows:

• TensorFlow 2.3.1
• Python 3.8.6
• GPU: NVIDIA GEFORCE RTX 2060 (laptop has 16 GB RAM and 6 processing cores)
• CUDA: 10.1
• cuDNN: 7.6
• Anaconda 3 command prompt

The .config file is as follows:

• GPU: NVIDIA GEFORCE RTX 2060
• GPU: 16GB RAM, 6 processor cores
• TensorFlow: 2.3.1
• Python: 3.8.6
• CUDA: 10.1
• cuDNN: 7.6

I am training a Mask R-CNN Inception ResNet V2 1024x1024 algorithm (on my computer's GPU), as downloaded from the TensorFlow 2 Detection Model Zoo. I am training this algorithm on my custom dataset, which I have labeled using Label-img . When I train the model using the Anaconda command python model_main_tf2.py --model_dir=models/my_faster_rcnn --pipeline_config_path=models/my_faster_rcnn/pipeline.config, I get the following error:

Feature Pyramid Networks for Object Detection adopt RPN technique to create the detector, and it use sliding window technique to classify. How come there is a statement for "non-sliding window" in 5.2 section?

The extended statement in the paper : 5.2. Object Detection with Fast/Faster R-CNN Next we investigate FPN for region-based (non-sliding window) detectors.

In my understanding, FPN using sliding window in detection task. This is also mentioned in https://medium.com/@jonathan_hui/understanding-feature-pyramid-networks-for-object-detection-fpn-45b227b9106c the statement is

"FPN extracts feature maps and later feeds into a detector, says RPN, for object detection. RPN applies a sliding window over the feature maps to make predictions on the objectness (has an object or not) and the object boundary box at each location."

Thank you in advanced.

I am trying to extract the pre-output feature-map for the Panoptic Output of Detectron2 ResNet50 - based FPN model.

Hence, In order to get partial model outputs, I am following the official Detectron2 Modeling Documentation to Partially Execute Models.

Please find the code below:

I'm using Keras and Tensorflow to perform object detection using Yolov3 standard as well as Yolov3-Tiny (about 10x faster). Everything is working but performance is fairly poor, I'm getting about one frame every 2 seconds on the GPU and one frame every 4 seconds or so on the CPU. In profiling the code, it turns out the decode_netout method is taking a lot of time. I was generally following this tutorial as an example.

1. Can someone help walk me through what it's doing?
2. Are there alternative methods baked into Tensorflow (or other libraries) that could do these calculations? I swapped out some custom Python for tf.image.non_max_suppression for example and it helped out quite a bit in terms of performance.

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