lovepan1

======> Epoch: 8, global_step: 33209.0, lr: 0.0001

first stage: i restore yolov3 darknet weights and update yolov3_head, second stage: i update darknet53 and yolov3_head this is my train process

this is my arg.py: first_stage: use darknet weights, restore darknet53, update yolov3_head second_stage: use first_stage trained weights , restored darkent53 and yolov3_head， update darkent53 and yolov3_head [first_stage.txt](https://github.com/wizyoung/YOLOv3_TensorFlow/files/3389577/first_stage.txt) [second_stage.txt](https://github.com/wizyoung/YOLOv3_TensorFlow/files/3389579/second_stage.txt)

> > this is my arg.py: > > first_stage: use darknet weights, restore darknet53, update yolov3_head > > second_stage: use first_stage trained weights , restored darkent53 and yolov3_head， update darkent53...

> @lovepan1 , hope it works. Can you update your running result when you finish the running? ok, in this weekend, i will retrain my model to use appropriate lr,...

hi，thanks for the works， i read the questions and discussions， but don`t understand this code: optimizer.zero_grad() loss.backward() # Mask grad for iteration m.do_grad_mask() optimizer.step() in pruning_imagenet.py line 281: m.do_grad_mask() if...

> Thank you for reviewing my issue! I’ll try a new one. Have you solved this problem? I also encountered this problem

> [@lovepan1](https://github.com/lovepan1) I tested with the new model and actually it worked well. > > For the Stage 2 model, you can try this one: https://huggingface.co/OpenGVLab/InternVideo2-Stage2_6B-224p-f4/tree/main Oh however, it seems...

@leexinhao 6b/1b model text encoder shape is different 

> [@lovepan1](https://github.com/lovepan1) I think you’ll need to modify the model configuration, especially the parameter shapes, to ensure the pretrained weights load correctly. I actually refactored the model loading process myself...