KARTIK SIRWANI

thanks for this great work, I was wondering if we can use this model for commercial usage.

Is alpha loss calculated for all the pixels or just for certain pixels that are unknown in trimap

1

Hi in the repo https://github.com/huochaitiantang/pytorch-deep-image-matting/ the alpha prediction loss is calculated only for pixels that are unknown in trimap """ wi = torch.zeros(trimap.shape) wi[trimap == 128] = 1. t_wi =...

when are you planning to release training code ?

1

Thanks for this really impressive work. The model does extremely well. I wanted to know when are you guys planning to release the training code ?

Error while training fashion detector

1

python mmdetection/tools/train.py \ configs/fashion_parsing_segmentation/mask_rcnn_r50_fpn_1x.py This command was mentioned in Getting_started.md page. But when I run this I get the error :- KeyError: 'mmfashionDataset is not in the dataset registry'

Hi I have a fashion dataset that I want to train. The issue is I have only bbox coordinates with me. I dont want to train segmentation . I am...

Deploying to production error

1

I tried to follow commands to deploy but it didn't work out. Config validation error : child MONGO_HOST fails. because ["Mongo_host is required"]

Thanks for this amazing work. Would it be possible for you to share the link to the trained model. I wanted to see the inference results. Thanks in advance

Getting destination as None. When training the model

2

Hi I am running this code: training = replicate.trainings.create( destination="kartikwar/business-card", model="stability-ai/sdxl", version="39ed52f2a78e934b3ba6e2a89f5b1c712de7dfea535525255b1aa35c5565e08b", input={ "input_images": "https://uploads.documents.cimpress.io/v1/uploads/94bc6c51-8cfc-4bbd-96fe-389facc3c0c5~122?tenant=furl", "token_string": "business card", "caption_prefix": "an image of business card", "max_train_steps": 1000, "use_face_detection_instead": False, "crop_based_on_salience": False...