What is the last fixed image size when training FasterRCNN_Resnet101 model? #10162
Description
Prerequisites
Please answer the following question for yourself before submitting an issue.
- I checked to make sure that this feature has not been requested already.
1. The entire URL of the file you are using
https://github.com/tensorflow/models/blob/master/research/object_detection/legacy/**train.py**
2. Describe the feature you request
The size of the input image is not limited, but the size of the input model is fixed during the training process. I can't find the corresponding code and can't obtain the fixed size of the model input. Please let me know
3. Additional context
none
4. Are you willing to contribute it? (Yes or No)
Yes