Jonathan Mitchell

Hi @GustavZ @ha5463 I attempted to train with a MobileNetV2 version about a week ago, it did not train properly, but I was also modifying certain hyperparameters such as: 1....

@GustavZ MobileNet is simply a feature extractor the same way ResNet is a feature extractor. It can be considered a "base network", and you can attach any head to it....

@betterclever I have the same issue when running the inspect_model.ipynb notebook that @betterclever has. Working on a solution now...

@Cpruce I actually implemented a very similar MobileNet 224 backbone, it appears to be the same as the one I saw on your repository. Did you try training it on...

I am still trying to get rid of NaN errors on rpn_bbox_loss when lowering the image dimensions. I have a thread here [321](https://github.com/matterport/Mask_RCNN/issues/321)

@Cpruce Is there an advantage to include stage 13 (block 13) of the mobilenet base in your architecture? As can be seen [here](https://github.com/Cpruce/Mask_RCNN/blob/master/model.py#L544). The spatial dimensions of block 12 are...

@Cpruce It appears that you are using trainable Batch Normalization layers in your MobileNet graph, whereas the current master branch implementation sets the BatchNorm layers to `non trainable`. You can...

@ps48 The TimeDistributed layer is a means of performing the 2D convolution on each feature map from the feature pyramid network. So if the FPN contains four stages (C2, C3,...

@wangx1996 Can you describe what the issue was and what the solution was? Is your insertion of the second roll operation necessary?

Hi yes would you mind sharing them? I could really use them right now. Thanks!