Avinash

The ‘model.load_weights’ seem to load the weights incorrectly due to version compatibility issues, resulting in training from scratch. So during training and evaluation, the coco and the previously trained weights...

The ‘model.load_weights’ seem to load the weights incorrectly due to version compatibility issues, resulting in training from scratch. So during training and evaluation, the coco and the previously trained weights...

The ‘model.load_weights’ seem to load the weights incorrectly due to version compatibility issues, resulting in training from scratch. So during training and evaluation, the coco and the previously trained weights...

Getting this same error ```raise ValueError("len(output_shape) cannot be smaller than the image " ValueError: len(output_shape) cannot be smaller than the image dimensions ``` Anyone solved this??

> Apply if your dataset has imbalance, you have to apply multi-class sparse focal loss in all three. checkout here [Multi-class Focal loss](https://github.com/charlie6echo/TF-MaskRCNN-VBDLDSCC/blob/e4b0ca942b7b036c4a30068db1fa08e16f50da99/mrcnn/model.py#L1021) on mask RCNN. I am getting this...

Same here. The training runs for one epoch and nothing happens not even error. can anyone help?

> Hi guys, do you mind sharing your colab code ? I runs alot of compatibility issue (tensorflow and python version related) when using colab and was wondering if anyone...

> Was anyone able to resolve this issue? Is there a way to see current iteration number within an epoch to see if the training is actually going on? Try...

i am facing similar issue. the training and validation loss is around 0.3. but the mAp is0. and my detections are similar to the image of @devacharan

I downgraded my tensorflow version from 2.7 to 2.5 - worked !!! Now the mAp, mAR, F1 score are around 60%.