LUO
LUO
Hi, I downloaded your model fasterrcnn_resnet50_fpn_coco-258fb6c6.pth, but when i try to load this model using model.load_state_dict(checkpoint['model]), it shows "key error 'model'" so i try to print keys in model dictionaries...
载入模型报错
博主你好， 我在运行你的train_model的时候在已经将模型放到weights后，运行到model.load_weights('weights/faster_rcnn.h5', by_name = True)这行报错 ValueError: Unable to load weights saved in HDF5 format into a subclassed Model which has not created its variables yet. Call the Model first, then...
Hi, I'd like to ask the question about the training strategy, As I am using both mmdetection3d and openpcdet frameworks and both found in it that they require to train...
Hi, Thanks for your great work, i would like to ask a question about DP. If some new coming request in another batch has different sequence length of the current...
ring attention本质是flash attention的分布式版本，flash attentionV2里面会维护softmax分母但是在更新out的时候好像只会更新最大值不会更新分母用于减少计算吧？在Q和一圈KV算完了以后最后除以一个softmax的global分母就可以了，所以作者这个ring attention实现的分布式FA可以理解成是v1版本的FA吗？