Open abhinavisgood opened 2 years ago
please reply
Hi, @abhinavisgood ,
Sorry for the delayed reply and thanks for your interests!
The current inference.py
only support the images and masks provided in the config file, which will be used to create a dataloader for data loading. You can modify the configures of 'validation_datasets' in the config file of your model (OUTPUT/000044e_600524iter.pth
), then the inference script will load the given data. You can have a look at the following configuration for example ().
I will provide a much simpler script for inference when I am avaliable and it will not take longer.
Best wishes!
here's the output to my code :: python inference.py --name OUTPUT/000044e_600524iter.pth --func inference_complet_sample_in_feature_for_evaluation --batch_size 1
I didn't know where to put the actual jpg image file , so i put in OUTPUT folder only , and also in the asset folder
Traceback (most recent call last): File "inference.py", line 859, in launch(inference_func_map[args.func], args.ngpus_per_node, args.num_node, args.node_rank, args.dist_url, args=(args,)) File "C:\Users\91809\Desktop\cut\create\image_synthesis\distributed\launch.py", line 52, in launch fn(local_rank, *args) File "inference.py", line 530, in inference_complet_sample_in_feature_for_evaluation info = get_model_and_dataset(args=args, model_name=args.name) File "inference.py", line 71, in get_model_and_dataset model_name = model_name.split(os.path.sep)[-3] IndexError: list index out of range