Alxemade

Thanks for your work! Here, I want to use nii.gz format to test my MRI segment, so how should I deal with this format data for segement, can you kindly...

Question about discriminating the size of the network output

3

Hi, @twtygqyy Thank you very much for the work. I read your code, but I feel confused about your annotation in [srresnet.py](https://github.com/twtygqyy/pytorch-SRResNet/blob/master/srresnet.py). ``` class _NetD(nn.Module): def __init__(self): super(_NetD, self).__init__() self.features...

It seems that there is no use for adversarial losses

1

Thank you for your code. I read the code, but can't find the adversarial losses anywhere. The _NetD network is not used, right?

Why do you set config.TRAIN.n_epoch_init = 0 in the config.py

1

Hello, when I read your code, I have some questions about the code. Why do you set config.TRAIN.n_epoch_init=0 in the [config.py?](https://github.com/JustinhoCHN/SRGAN_Wasserstein/blob/master/config.py). This is different from the original [SRGAN Code](https://github.com/tensorlayer/srgan/blob/master/config.py).And I...

Fine-tuning results are not satisfactory

2

### 起始日期 | Start Date _No response_ ### 实现PR | Implementation PR By using this script: [finetune_ds.sh](https://github.com/OpenBMB/MiniCPM-V/blob/main/finetune/finetune_ds.sh)[finetune_ds.sh](https://github.com/OpenBMB/MiniCPM-V/blob/main/finetune/finetune_ds.sh) --llm_type "llama3" \ --tune_vision false \ --per_device_train_batch_size 2 \ --per_device_eval_batch_size 1 \ --gradient_accumulation_steps...

💡 [REQUEST] - <MiniCPM-V-2_6的int4量化>

1

### 起始日期 | Start Date _No response_ ### 实现PR | Implementation PR _No response_ ### 相关Issues | Reference Issues _No response_ ### 摘要 | Summary MiniCPM-V-2_6的int4量化是啥样的，直接使用 bnb_quantize.py 好像会报错。 ``` next_tokens...