Dhruv Awasthi
Dhruv Awasthi
Hey, I am also looking for the same. If you found something related to this, can you please update it here. Thanks, Dhruv
For anybody who comes here searching for the same problem, you can get the cropped out image from coordinates stored in .txt files using the code snippet below: ``` from...
Did you solved out this issue? I am facing the same thing, it will really help!
Okay. I will try this. On a side note, is it because of the config parameters? And if yes, is there no way to update that so that it outputs...
@karthikdatta98 While finetuning the SAM, I resized all my images to the desired target image size that I wanted the model to be trained on. And once fine-tuned, when using...
@karthikdatta98 It worked well. I fine-tuned with 1200x1200 images and the results were pretty good actually. I initially fine-tuned the model with 150 images just to get an idea of...
@karthikdatta98 The dataset I fine tuned on, contained the data that SAM hasn't been trained on, and without fine-tuning the results were not good but they improved a lot after...
@karthikdatta98 I upscaled it.
I am facing the same issue. Were you able to solve this. Can you help please?
Try using the below code for creating the dataset: ``` dataset_dir = "path_to_dataset_dir" # assuming the dataset dir contains two subdirectories - "images" containing images, and "masks" containing masks image_paths...