RecurrentAttentionConvolutionalNeuralNetwork

RecurrentAttentionConvolutionalNeuralNetwork copied to clipboard

Have you modified the batch_size?

Y-YWang

Hi, where is the "apn.pt.pt" file?

2

Hi, where is the "apn.pt.pt" file? def init_with_apn2(self): ckpt = torch.load('../checkpoints/CUBS/apn2.pt.pt') self.apn1.load_state_dict(ckpt['apn1_state_dict'])

heyongcs

ask for help

6

Sorry， I want to know can the code run？ how to get dataset，Thanks ModuleNotFoundError: No module named 'torchnet' where is the torchnet

22wei22

I am interested in your code. I want to know the accuracy can you get after three steps in the CUBS database.

momoComeOn

RuntimeError: grad can be implicitly created only for scalar outputs

2

when use batch_size=32 not 1, get this error info: File "/mnt/workspace/py/RA_CNN/src/manager.py", line 163, in train self.do_epoch(epoch_idx, optimizer, optimize_class=optimize_class) File "/mnt/workspace/py/RA_CNN/src/manager.py", line 113, in do_epoch self.do_batch(optimizer, batch, label, optimize_class=optimize_class) File "/mnt/workspace/py/RA_CNN/src/manager.py",...

heyongcs

cnn_params_to_optimize = model.cnn1.parameters() + model.cnn2.parameters() TypeError: unsupported operand type(s) for +: 'generator' and 'generator'

1

cnn_params_to_optimize = model.cnn1.parameters() + model.cnn2.parameters() TypeError: unsupported operand type(s) for +: 'generator' and 'generator'

heyongcs