image_resizer | time Image Processing. Tiny library written | Computer Vision library

I follow all the steps and read everything online and I trained successfully SSD-MobileNetV1 from Model Zoo of TF2 OD API.

I fine-tuned this model with new classes "Handgun" and "Knife" and I use a balanced dataset of 3500 images. The training proceeds well, but when I run the evaluation process (for validation) with "pascal_voc_detection_metrics" I achieved 0.005 AP@0.5 (The detection model manages to reach only 0.005 more or less of AP) with the class "Handgun" which is very low, but 0.93 AP@0.5 with the class "Knife".

I didn't understand why. I really read everything but I can't find the solution.

config of SDD-MobileNetV1:

I am having trouble evaluating my training process during training a Tensorflow2 Custom Object Detector. After reading several issues related to this problem I found that evaluation and training should be treated as two separate processes therefore I should use a new anaconda prompt for starting the evaluation job. I am training on the ssd_mobilenetv2 640x640 version. My pipeline configuration:

I've downloaded the EfficientDet D0 512x512 model from the object detection API model zoo, downloaded the PASCAL VOC dataset and preprocessed it with the create_pascal_tf_record.py file. Next I took one of the config files and adjusted it to fit the architecture and VOC dataset. When evaluating the resulting network with the pascal_voc_detection_metrics it gives me a near zero mAP for the first class (airplane), the other classes are performing fine. I'm assuming one of my settings in the config file is wrong (pasted down below), why does this happen and how do i fix this?

I am trying to create an instance of this proto template. Compiled and imported, I run the following code:

I used the Tensorflow Object Detection API (TF1) and created a file of frozen_inference_graph.pb of Faster R-CNN. After that, I was able to apply object detection to the image using "Object_detection_image.py" in the GitHub repository below.

EdjeElectronics/TensorFlow-Object-Detection-API-Tutorial-Train-Multiple-Objects-Windows-10

When I use this code, how large is the input size of images to Faster R-CNN? I set both "min_dimension" and "max_dimension" of "image_resizer {" in the config file to 768. When I perform object detection, is the input size of images to Faster R-CNN automatically resized to this size? The size of my images I prepared is 1920 x 1080 pixels, and I think it has been resized to 768 x 768 pixels.

If anyone knows about this, please let me know.

Thank you!

• Python: 3.7
• TF-gpu==1.15
• Quadro RTX 4000
• 8 GB VRAM, 64GB System Memory
• Pretrained model: ssd_mobilenet_v1_pets.config

Relatively new to the Tensorflow Object Detection API here and wanted to apply it to my own set of images. I want to teach it to discern between the top, bottom, and side view of a BGA chip (or a table if there is one that has the dimensions there) from images of what are called datasheets, which show the precise dimensions of the aforementioned components.

images/train = 565 images images/test = 24 images

I don't understand why only the label 'top' is being recognized. Been having this problem all day and I know its not because of my csv's or tf records because I made sure those were normal after a bunch of fiddling around.

Config File:

I am doing tensorflow (v1.14) object detection api. I was using faster_rcnn_inception_resnet_v2_atrous_coco with num_of_stages : 1 in config. I tried generating inference graph using command:

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: