1, debugging what cyber-shot Object Detection via Feature Reweighting code, model has good training
To Evaluate the Model, the error RuntimeError: CUDA error: out of memory


An error as below

` ` `
===& gt; Generating dynamic weights...
===& gt; 0/374
Valid_ensemble. Py: 94: UserWarning: volatile was removed and now has no effect. Use ` with torch. No_grad () : ` home.
Metax, mask=Variable (metax, volatile=True), Variable (mask, volatile=True)
===& gt; 1/374
Traceback (the most recent call last) :
The File "valid_ensemble. Py", line 215, in & lt; module>
Valid (datacfg darknet, learnet weightfile, outfile, use_baserw)
The File "valid_ensemble. Py", line 95, valid in
DWS=m.m eta_forward (metax, mask)
The File "/home/song/code/Fewshot_Detection - master/darknet_meta py", line 122, in meta_forward
Metax=model (metax)
The File "/home/song/anaconda3/envs/python27/lib/python2.7/site - packages/torch/nn/modules/module. Py", line 477, in __call__
Input result=self. Forward (* and * * kwargs)
The File "/home/song/anaconda3/envs/python27/lib/python2.7/site - packages/torch/nn/modules/container. Py", line 91, in the forward
Input=module (input)
The File "/home/song/anaconda3/envs/python27/lib/python2.7/site - packages/torch/nn/modules/module. Py", line 477, in __call__
Input result=self. Forward (* and * * kwargs)
The File "/home/song/anaconda3/envs/python27/lib/python2.7/site - packages/torch/nn/modules/batchnorm py", line 66, in the forward
Exponential_average_factor, self. Eps)
The File "/home/song/anaconda3/envs/python27/lib/python2.7/site - packages/torch/nn/functional. Py", line 1254, in batch_norm
Training, momentum, eps, torch. Backends. Cudnn. Enabled
RuntimeError: CUDA error: out of memory

` ` `
Thank you master!!!!!!