search

anshkumar / yolact

Tensorflow 2.x implementation YOLACT
33 stars 9 forks source link

Where to get weights? #5

Open dexter2406 opened 3 years ago

dexter2406 commented 3 years ago

Hi, thanks for your work. But where could I got the weights file, e.g. saved_model_0.19968511 ? I don't find link in your description.

Thanks for your time!

anshkumar commented 3 years ago

Currently, I'm not providing pre-trained checkpoints. Will add coco pre-trained checkpoints in future.

Ankur-singh commented 1 year ago

any updates on it? At least can you tell how to train the model & generate the weights.

anshkumar commented 1 year ago

@Ankur-singh For training you have to just change the path in train.sh file. And for creating tfrecord you have to use create_coco_tfrecord.sh file.

Ankur-singh commented 1 year ago

I think, one will have to download the coco dataset and unzip it before creating tfrecords. Because, I cannot find the code to download the dataset. Please correct me if am wrong or if I am missing something.

anshkumar commented 1 year ago

Yes, you have to download the dataset.

shashank-sharma333 commented 1 year ago

@Ankur-singh Were you able to train the model? I am getting the below error while running train.sh with the required parameters

tensorflow.python.framework.errors_impl.InvalidArgumentError: buffer_size must be greater than zero.

Ankur-singh commented 1 year ago

@shashank-sharma333 yes I was able to train the model. I had to make quite a few changes to make it work. But in the process, I never came across this error. 😅

shashank-sharma333 commented 1 year ago

Thank you @Ankur-singh for your comment. Which environment you are using for the training model? Also, Can you list down the changes you made? It would be helpful.

Ankur-singh commented 1 year ago

I have a 3060Ti, so I followed GPU installation instruction from the readme file. Its pretty straight forward. Just make sure your compile the protobufs. Just run this from the root directory of the project

protoc protos/*.proto --python_out=.

Regarding the changes, TBH, I don't remember all of them. It was a couple of weeks ago. One was regarding SGD optimizer, the API has changed, so you should use legacy version. And there were quite a few data type issue, you should be able to fix them with basic type casting. Hope this helps.