SSD-MobilenetV2 - Preprocessing for inference from saved_model_tf2

[Shubhambindal2017]

I have fine-tuned an SSD-Mobilenetv2 with train config fixed resize 300x300 built using tensorflow objection detection API and saved in TF Saved_Model format. Questions:

• How during inference it is able to accept input images of any shape (not 300x300) without the need for any preprocessing to resize to 300x300 first and then pass to the model.
• Does it is because saved_model by default does resize during inference? (If yes, does it also normalize them because before doing convolution operations) (I am new to saved_model format but I think it is not because of saved_model, but then how is it possible - as I think SSD-Mobilenet includes FC layers which require fixed input size) OR does the architecture uses AdaptivePooling in b/w to achieve this.

In simple words - Documentation is not clear - regarding what pre-processing (Resize / Normalization) steps are required to inference from saved_model format. Here too - no pre-processing like resizing and normalization is applied to input image. https://github.com/tensorflow/models/blob/master/research/object_detection/colab_tutorials/inference_from_saved_model_tf2_colab.ipynb

[krishnaaxo]

ok

[thmsgntz]

That's an excellent question. I am facing the same kind of problem where I try to load my Object Detection model from a saved_model and unable to use it as this example.

I found this in the documentation about saved_model :

When you save a tf.Module, any tf.Variable attributes, tf.function-decorated methods, and tf.Modules found via recursive traversal are saved.

I am guessing that somewhere in the SSD-Mobilenetv2 architecture, it implements this tf.Module. Hope it can give you some hints to find a good explanation.

For me, I just stopped using saved_model for Object Detection object, I just load the last trained checkpoints of my model to use it.

[toborobot]

In addition to this topic... when I've saved tflite it works better with normalization and ONLY with 300x300 like in conf file... why the model has name "SSD-MobilenetV2 320x320"? this is the question...