Avi Ziskind

I have the same issue. Top-1 accuracy is 64% for Resnet18 instead of the promised 68%.

I have modified the functions available in the neurite library (neurite.plot.flow, specifically), which, by the way, is also published by the authors of this (voxelmorph) repo. I can push my...

Hi @adalca , I created Pull Requests for the neurite and voxelmorph repos to merge in the capabilities for the new Baker et al. colors scheme and for the HyperConv2D...

I had the same error. I discovered that the weight size discrepancy is because the aspect_ratios variable is different between the train_mobilenet_ssd.py script and infer_mobilenet_ssd_py script. The first difference is...

make sure to use these aspect ratios if you're trying to load the ported caffe weights (converted_model.h5) aspect ratios = [[1.001, 2.0, 0.5], [1.0, 2.0, 0.5, 3.0, 1.0 / 3.0],...

When running the training script, i do not get the performance claimed in the Readme (I might be missing something, but in fact the process for loading mobilenet imagenet weights...

I would recommend starting with https://github.com/pierluigiferrari/ssd_keras/ and getting that code running. Then copy over the mobilenet_v1.py code from this repo for an example of how to implement the mobilenet code...

If you really want to use the ported weights, you could try build the caffe repo (https://github.com/chuanqi305/MobileNet-SSD) and inspect the outputs of each layer, and making sure it matches with...

Update: I tried running the evaluation script from the https://github.com/pierluigiferrari/ssd_keras/ repo (using code from this notebook: https://github.com/pierluigiferrari/ssd_keras/blob/master/ssd300_evaluation.ipynb) using the ported mobilenet-ssd weights, and get mAP of 0.68, which is a...

I'm not sure.. i didn't encounter that error. Looks like you're trying to run the code under section "1.2. Load a trained model" instead of "1.1. Build the model and...