passion3394

Results 44 comments of passion3394

why does the testing process need more GPU memory than the training process

@Huyhust13 You could resize the pic to the size which could be loaded by the GPUs.

How to Test my own dataset

I also want to know this.

Some problems occurred in testing

@NickZhung I trained the dataset, but I don't know which is the trained model. when I complete the training, I get three file after the last iteration. they are save.ckpt-15000.data-00000-of-00001,save.ckpt-15000.index...

Some problems occurred in testing

I think I have solute my own problem. In test.py, modify the following two lines like this: parser.add_argument('--weights', default="save.ckpt-15000", type=str) parser.add_argument('--weight_dir', default='pascal_voc/output/2017_11_26_09_36/', type=str)

why calculating the input_calibration is so slow?

@AlexeyAB thanks for your reply, I will try it.

training scheme

I also want to get the answer.

training scheme

I think I have found the answer from the caffe doc. * Fine-tuning requires the `-weights model.caffemodel` argument for the model initialization. For example, you can run: # train LeNet...

The loss value didn't drop when it came down to about 7.X?

@Hanlos the value of use_global_stats is false when in phrase TRAIN, so I think it's no correctional with use_global_stats, did you modify some other values?

try to implement PSMNet use yours instructions

@AlessioTonioni Sure, I will create a pull request soon.

try to implement PSMNet use yours instructions

I have created a pull request, thanks for your help.