Closed lzhnb closed 4 years ago
Oh i find me copied part of the training command so that misiing meta_loss=True
in phase1 so i miss the meta loss branch.
But i think the parameter should modify.
Yes, the saving weight'name is different depending on the training parameters. Thanks for reminding, the parameter has been modified.
I‘ve finished the first phase training, and i also read your code about testing, i have few question about the hold processing:
meta_dataset
, the shots=200
means the number of each class_set, right?. And during training, the metadataset will be shuffled each item and pick up 1 shot for each classes(15 classes) to generate attentions and select batch_size
images to be query, right?roidb
for query, it will contain all base instances and 10 instances for each novel classes, right?1_shots_1_mean_class_attentions.pkl
, but it should mean by 200(real shots) and i think it's useless, right? The valid attentions should be generated after the second phase training, which should name 2_shots_10_mean_class_attentions.pkl
for all classes(20 classes) in your training example, right?mean_class_attentions
can generate independently, so can i use the 10-shots
trained weight to generate the 30-mean
attentions? Doesn't it work? even i use the first phase trained weight to generate the mean_class_attentions
without the 'finetuning'. I want to analyze its generalization, and for the few-shot learning the novel classes should not affect the model. Are the baselines that your paper lists train independently?@lzhnb What's ur facility to run the first stage, or in other words, how much memory required? It seems 10G GPU cards cannot obtain the baseline due to memory issue.
@lzhnb What's ur facility to run the first stage, or in other words, how much memory required? It seems 10G GPU cards cannot obtain the baseline due to memory issue.
My GPU is Titan XP whose memory is 12G.
@yanxp hi, can u provide the pre-trained models of ResNet-50 and ResNet-34 converted from caffe? I found the pytorch pretrain models perform inferior to the caffe version.
@lzhnb
@XiongweiWu we just used the pytorch pretrained model of ResNet-50 and ResNet-34.
The training Phase1 is finished, although it met some error about dataset load and i run in the screen but forgor to record, fortunately i got the weight of 20 epoch. First is about your example command for the phase2 training, i put my modification into pull requests but i still have some problem
I see your code
My weight's name is pascal_voc_0712_metarcnn_200_20_1540.pth which depends on dataset, network, shots, epoch and step
But in your loading code
It depends on dataset, network(constant), checksession, checkepoch, checkpoint The checksession and checkpoint is different from the training parameter which gives to the saving wight'name shot and step, isn't it right?
And also i change it myself, but i fail in load weight
Thanks