keras-rcnn
keras-rcnn copied to clipboard
Keras package for region-based convolutional neural networks (RCNNs)
In an effort to further simplify the existing interface and to improve self-documentation I’d like to rename a few layers and backend functions to be clearer. I’d like to rename...
The following code: ```Python model = keras_rcnn.models.RPN(image, classes) model.compile("adam") prediction = model.predict_generator(generator) ``` throws the following `InvalidArgumentError` exception: ``` InvalidArgumentError: You must feed a value for placeholder tensor 'proposal_target_1/keras_learning_phase' with...
![image](https://user-images.githubusercontent.com/32117207/85638056-dfebc200-b6bf-11ea-8f7e-2dddc1e81dab.png) I shouldn't fix it from _feature_pyramid_2d.py to tensorflow.keras.layers.Conv2D.
Hello and thank you for sharing your work! Could you please provide the last checkpoint for the pretrained model? Thank you in advance, Lucia
Do admins have any pipeline for a tensorflow 2.x upgrade?
I got this erro,and I didn't see this module ModuleNotFoundError: No module named 'keras_resnet'
keras-rcnn should provide a mean average precision (mAP) [Keras-compatiable metric](https://keras.io/metrics/) that can be used to evaluate the performance of a model during training.