few-shot-gnn

few-shot-gnn copied to clipboard

When I run the main.py, it comes out the question. How can I solve it?

yanghhx

Questions about the model saving and the test after training

1

Dear author Thanks for sharing your code. I learned a lot from it. But I have two confusions about the experiment for 5way 1shot under mini-imagenet. 1.the first is about...

LiaoYujia

samples = random.sample(self.data[class_], num_shots+1) I'm not sure if I understand it right, can you explain it? thank you very much! best wishes!

Daniel123jia

How I can use this project to classify my own images dataset

5

sousoufa

for batch_counter in range(batch_size): positive_class = random.randint(0, n_way - 1) # Sample random classes for this TASK classes_ = list(self.data.keys()) sampled_classes = random.sample(classes_, n_way) indexes_perm = np.random.permutation(n_way * num_shots) counter...

ranyaphat29

Hi there, I'd like to ask which part of the code is responsible for the adaptation phase during testing. From what I understand, test.test_one_shot(...) is responsible for testing but I...

eugenelet

1. replacing `conv2,conv3,conv4` to `layer2 ,layer3 ,layer4` 2. changing the `fc_last` layer to `fc_last2` with shape from `3 * 3` to `2*2` and `x = x.view(-1, 2 * 2 *...

chg0901