I have taken the stock ResNet and trained it only to identify a small set of custom objects. My training set is comprised of images of these custom objects and their associated bounding box tags. I then train the ResNet model via TensorFlow and try to test it on a few other images, which do not have associated tags/bounding boxes. When I do the testing, the model identifies the objects with a bounding box, which is great, but those boxes each come with an accuracy percentage, i.e. 92%. How is ResNet calculating this accuracy percentage?? I can't seem to find the actual calculation it is doing.
Thanks
Related
I'm using Tensorflow 2 Model Maker to perform transfer training of EfficientDet-Lite (ultimately to run on a Coral EdgeTPU) and I care much more about the classification output and much less about the precision of the bounding boxes. Is there a way to modify some training parameters to improve the accuracy of the classes at the expense of the accuracy of the bounding boxes? Or does this not make sense?
Unfortunately, TensorFlow 2 Model Maker doesn't support such customization at this moment.
If you want to do so, you can bypass Model Maker and directly use AutoML repo. The technical detail is to adjust weights for different losses by adding loss_weights in compile() function.
I am working on object detection model to identify two classes. I am using Faster RCNN on customized dataset in tensorflow api. The dataset contains 20k images (augmented) with two classes. While training the model the loss is not decreasing properly as it reach to 100k steps. It has lot of variation as shown in image. Can someone tell me where i am making mistake.
enter image description here
I am using Tensorflow Object Detection API for fine-tuning, using my own data. The goal is to detect 2 classes of objects. I am using the pre-trained faster_rcnn_resnet101_coco model.
The various detection box precision and recall measures are generally increasing (see screenshots below) and are fairly high:
The box classifier losses are decreasing. HOWEVER, the RPN losses are increasing (see screenshots below) -- It looks that the model is having a hard time distinguishing foregrounds from backgrounds (hence, the increasing RPN losses), but once the model is able to identify and locate the right foreground, it classifies well (hence, the decreasing box classifier losses)? I think this can be observed in the model's performance on test images: the false positive rate (on images that do not contain any of the two classes of target objects) is rather high. On the other hand, on images that do contain those target objects, the model does a fantastic job in accurately identifying and locating those objects.
So my question is essentially: what are some of the things I could try to help make sure RPN losses are also decreasing.
I have configured SSD mobilenet v1 and have trained the model previously as well. However in my dataset for each of the bounding box there are multiple class labels. My dataset is of faces each face have 2 labels: age and gender. Both these labels have the same bounding box coordinates.
After training on this dataset the problem that I encounter is that the model only labels the gender of the face and not the age. In yolo however both gender and age can be shown.
Is it possible to achieve multiple labels on a single bounding box using SSD mobile net ?
It depends on the implementation but SSD uses a softmax layer to predict a single class per bounding box, whereas YOLO predicts individual sigmoid confidence scores for each class. So in SSD a single class with argmax gets picked but in YOLO you can accept multiple classes above a threshold.
However you are really doing a multi-task learning problem with two types of outputs, so you should extend these models to predict both types of classes jointly.
I'm training a model to detect meteors within a picture of the night sky and I have a fairly small dataset with about 85 images and each image is annotated with a bounding box. I'm using the transfer learning technique starting with the ssd_mobilenet_v1_coco_11_06_2017 checkpoint and Tensorflow 1.4. I'm resizing images to 600x600pixels during training. I'm using data augmentation in the pipeline configuration to randomly flip the images horizontally, vertically and rotate 90 deg. After 5000 steps, the model converges to a loss of about 0.3 and will detect meteors but it seems to matter where in the image the meteor is located. Do I have to train the model by giving examples of every possible location? I've attached a sample of a detection run where I tiled a meteor over the entire image and received various levels of detection (filtered to 50%). How can I improve this?detected meteors in image example
It could very well be your data and I think you are making a prudent move by improving the heterogeneity of your dataset, BUT it could also be your choice of model.
It is worth noting that ssd_mobilenet_v1_coco has the lowest COCO mAP relative to the other models in the TensorFlow Object Detection API model zoo. You aren't trying to detect a COCO object, but the mAP numbers are a reasonable aproximation for generic model accuracy.
At the highest possible level, the choice of model is largely a tradeoff between speed/accuracy. The model you chose, ssd_mobilenet_v1_coco, favors speed over accuracy. Consequently, I would reccomend you try one of the Faster RCNN models (e.g., faster_rcnn_inception_v2_coco) before you spend a signifigant amount of time preprocessing images.