Medical-SAM2
Medical-SAM2 copied to clipboard
Medical SAM 2: Segment 3D Medical Images Via Segment Anything Model 2
I used train3d.py for training, saved the weights after training, and then loaded them. We found that regardless of which parameters I set as trainable, the network converged based on...
May I ask if the pretraining weights (MedSAM_2prepatrian) are the final segmentation model weights you trained?
Hi Thank you for sharing your code. How can I train on multiple datasets ( or a single dataset with multiple class of images) simultaneously while making sure different classes...
- created examples folder - added quick start colab notebook that trains&validates 2d refuge data
您好, 想问下,目前代码中3d训练部分,是整个video计算平均loss然后梯度回传更新参数。是否可以每一帧计算loss进行梯度回传并更新参数,这样是否就可以把video的length从2变为整个video的长度? 涉及到memory相关的代码,应该如何修改呢? 期待并感谢您的回复!
Thank you for your remarkable work. MedSAM2 used a mask prompt on the STARE dataset, as shown in Figure 4 of the paper. I would like to know whether the...
Dear Authors, Congratulations on your excellent work. I wanted to address some open issues that have been mentioned regarding the evaluation on the pretrained weights of the REFUGE Dataset. It...
Hello, I am trying to further finetune MedSAM2 as I have quite a niche imaging application. I have set the model to training mode by doing: `predictor.train(True) predictor.sam_mask_decoder.train() ` However,...
Could you please share the hardware configurations and the overall computational power you employed during the training phase? I encountered with "CUDA OUT OF MEMORY" error when using 4090. I'm...
Dear Authours, Many thanks for your efforts on this great work and releasing the code! I have some questions that (I guess others may also be interested in): ### Q1....