all.
I got segmentation fault when I try to fit train data into xgboost model in python.
Do you know how to solve this problem?
Please help me.
Related
I train a model by tensorflow 2 to detecting vehicles, but I want to Convert tensorflow saved_model to frozen inference graph.
Can any one help?
It is not the recommended way to save your model and i would suggest you use saved model.
People around here can help if you explain why you want to use frozen graph specifically and saved model won't help.
If you still want to try freezing you can use this internal method to do so.
I am facing a similar question as here [How to Pre-train the Resnet101 for a Faster RCNN in Object Detection API of Tensorflow.
I use a pre-trained faster R-CNN Resnet101 model and want to fine-tune it with similar data. Currently, I am working with the TF OD API.
Until now, I only run the code here [https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/running_locally.md#running-the-training-job]. However, the accuracy of the validation set is either -1.000 or 0.02% after 10k iterations.
Is the model_main.py function the correct way to fine-tune a model or do I miss a step in between.
Any help/remark/hint is highly appreciated.
Thanks a lot in advance
I followed the tutorial of adanet:
https://github.com/tensorflow/adanet/tree/master/adanet/examples/tutorials
and was able to apply adanet to my own binary classification problem.
But how can I predict using the train model? I have a very little knowledge of TensorFlow. Any helps would be really appreciated
You can immediately call estimator.predict on a new unlabeled example and get a prediction.
I am using deepLab to generate semantic segmentation masked images for a video in cityscapes datasets. So, I started with the pre-trained model xception65_cityscapes_trainfine provided on the modelzoo and trained it further on the dataset.
I am curious to know How I can start training it from scratch? and not end up just using the pre-trained model? could anyone suggest a direction on How I can achieve it?
Any contribution from the community will be helpful and appreciated.
I trained a keras model inspired by the Inception Model on Tensorflow backend.
The problem is, the ouput is always the same, for differents images I tested.
However, model.evaluate give me a high accuracy percentage, so, the model seems to work.
Have you an idea ? Thanks!
Finally found the answer.
I just forgot to preprocess my input for the prediction.
All is clear now!