I have a weight file already trained. I want to add more images to the dataset and improve recognition. Is it possible to continue training with a ready-made weight, if so, how or will I have to train again?
Related
What is the best way to train TensorFlow for custom keypoint tracking that can work on the web?
Right now I'm using CenterNet MobileNetV2 FPN Keypoints 512x512 to train, but the outcome is not good enough keypoints confidence is significantly less approx 30%, but the bounding box is fine. So is there any way I can improve the model confidence for keypoints?
Config which im using:
steps 25000
epoch 12
learning rate 0.01
train dataset 1280
test dataset 319
Im trying to train a ml model using tensorflow that can track custom kwypoints but my tain model is not working as im expecting
I just finished training a yolov3 tiny model via google colab. I need the information regarding its accuracy in detection. How do I perform the evaluation for this model in terms of confusion matrix?
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.
SCENARIO
What if my intention is to train for a dataset of medical images and I have chosen a coco pre-trained model.
My Doubts
1 Since I have chosen medical images there is no point of train it on COCO dataset, right? if so what is a possible solution to do the same?
2 Adding more layers to a pre-trained model will screw the entire model? with classes of around 10 plus and 10000's of training datasets?
3 Without train from scratch what are the possible solutions , like fine-tuning the model?
PS - let's assume this scenario is based on deploying the model for business purposes.
Thanks-
Yes, it is a good idea to reuse the Pre-Trained Models or Transfer Learning in Real World Projects, as it saves Computation Time and as the Architectures are proven.
If your use case is to classify the Medical Images, that is, Image Classification, then
Since I have chosen medical images there is no point of train it on
COCO dataset, right? if so what is a possible solution to do the same?
Yes, COCO Dataset is not a good idea for Image Classification as it is efficient for Object Detection. You can reuse VGGNet or ResNet or Inception Net or EfficientNet. For more information, refer TF HUB Modules.
Adding more layers to a pre-trained model will screw the entire model?
with classes of around 10 plus and 10000's of training datasets?
No. We can remove the Top Layer of the Pre-Trained Model and can add our Custom Layers, without affecting the performance of the Pre-Trained Model.
Without train from scratch what are the possible solutions , like
fine-tuning the model?
In addition to using the Pre-Trained Models, you can Tune the Hyper-Parameters of the Model (Custom Layers added by you) using HParams of Tensorboard.
How do you guys visualize the training history of your pytorch model like in keras here.
I have a pytorch trained model and I want to see the graph of its training.
Can I do this using only matplotlib? If yes, can someone give me resources to follow.
You have to save the loss while training. A trained model won't have history of its loss. You need to train again.
Save the loss while training then plot it against the epochs using matplotlib. In your training function, where loss is being calculated save that to a file and visualize it later.
Also, you can use tensorboardX if you want to visualize in realtime.
This is a tutorial for tensorboardX: http://www.erogol.com/use-tensorboard-pytorch/