zhanglijian

Results 7 comments of zhanglijian

hen I make './libs/', there is a problem as follows.

it should be cuda8.0, cudnn7.5

Hello ,everyone !!!Now,python train/train.py meet this issue:ResourceExhaustedError (see above for traceback): OOM when allocating tensor with shape[1,256,160,551] Is my NIVIDA out of memory? GPU device:GeForce GTX 1050 Ti 4.0G

@kevinkit @blitu12345 @PavlosMelissinos Thanks a lot!

Hello ,everyone !!!Now,python train/train.py meet this issue:ResourceExhaustedError (see above for traceback): OOM when allocating tensor with shape[1,256,160,551] Is my NIVIDA out of memory? GPU device:GeForce GTX 1050 Ti 4.0G

@kevinkit can I reduce the mount of images to resolve that problems?

After runing train.py for 3 hours, GPU is out of memory trying to allocate 146.88MiB

@mattdingmeng Hi, Can you tell me, how do you fix this problems,when 'python trian.py',I have meet the same problems! thank you very much ![63865893-92ba-4ba4-b709-dfa21a417eec](https://cloud.githubusercontent.com/assets/12655032/26390139/d20d5102-408f-11e7-8fd3-68799cc7a423.png)

After runing train.py for 3 hours, GPU is out of memory trying to allocate 146.88MiB

@mattdingmeng Hi, my problems like this . ![d147834a-a97d-45d6-8d2b-3d0520c5b0ef](https://cloud.githubusercontent.com/assets/12655032/26437871/35db44e2-4152-11e7-99ef-583df9ce5eff.png) my coco data placed lieke this: ![3d08e450-7f1b-40b3-ac1b-0ffb2fde6ca9](https://cloud.githubusercontent.com/assets/12655032/26437912/74cd7864-4152-11e7-9473-eba20ad47da5.png)

After runing train.py for 3 hours, GPU is out of memory trying to allocate 146.88MiB

@mattdingmeng Thanks a lot

int pack_image the 'subtract the black level and scale the data' :why is im = np.maximum(im - 512, 0) / (16383 - 512)

@cchen156 Thanks a lot ! OK,I have know that and I have test the Sony pre_Trained_modele on my own dataset, the result is good, but when I process the Bayer...