Anchor parameters passing to Keras-retinanet to convert model to serving format

[ajinkya933]

@faustomorales @hgaiser
I am referring to Keras retinanet . My target is to deploy model.h5 on tensorflow serving. To do that I use below script (script reference: https://github.com/fizyr/keras-retinanet/issues/676#issuecomment-508958949 )for converting model to tf-serving format

from keras import backend as K
import tensorflow as tf
from tensorflow.python import saved_model
from tensorflow.python.saved_model.signature_def_utils_impl import (
    build_signature_def, predict_signature_def
)
from keras_retinanet import models
import shutil
import os

export_path = 'retinanet_savedmodel'
model = models.convert_model(
    model=models.backbone(backbone_name='resnet50').retinanet(num_classes=8),
    nms=True,
    class_specific_filter=True,
    anchor_params=None
)
model.load_weights('model.h5')

print('Output layers', [o.name[:-2] for o in model.outputs])
print('Input layer', model.inputs[0].name[:-2])
if os.path.isdir(export_path):
    shutil.rmtree(export_path)
builder = saved_model.builder.SavedModelBuilder(export_path)

signature = predict_signature_def(
    inputs={'images': model.input},
    outputs={
        'output1': model.outputs[0],
        'output2': model.outputs[1],
        'output3': model.outputs[2]
    }
)

sess = K.get_session()
builder.add_meta_graph_and_variables(sess=sess,
                                     tags=[saved_model.tag_constants.SERVING],
                                     signature_def_map={'predict': signature})
builder.save()

I am able to get successful prediction. But the successful predictions are observed only for default anchor parameters. In my code I have changed the anchor parameters. These changed anchor parameters are stored in config.ini file

[anchor_parameters] 
sizes   = 16 32 64 128 256 
strides = 8 16 32 64 128 
ratios  = 0.5 1 2 3 
scales  = 1 1.2 1.6

How do I pass changed anchor params to above script?

[stale[bot]]

This issue has been automatically marked as stale due to the lack of recent activity. It will be closed if no further activity occurs. Thank you for your contributions.

[Mps24-7uk]

@ajinkya933 I tried to convert the generated models to TF servable model. It doesn't work for me, can you please help me out with this?