search

jiangsutx / SRN-Deblur

Repository for Scale-recurrent Network for Deep Image Deblurring
http://www.xtao.website/projects/srndeblur/srndeblur_cvpr18.pdf
MIT License
714 stars 184 forks source link

I trained the color deblur model according to the method in the article, #23

Open Courageux-J opened 5 years ago

Courageux-J commented 5 years ago

I trained the color deblur model according to the method in the article, the psnr_ave = 29.8877 on gopro dataset, psnr_ave = 26.8082 on kohler dataset. and i test color model,the value are psnr_ave = 30.2456 and psnr_ave = 27.0550，is this normal?

jiangsutx commented 5 years ago

I think maybe you need train longer time and pick a best model from last few checkpoints.

Courageux-J commented 5 years ago

the loss is 0.004 after 4000 epoch. i want to kown the loss of the network at steps=523000 ，What is the approximate value of loss?

oywstju commented 3 years ago

I trained the color deblur model according to the method in the article, the psnr_ave = 29.8877 on gopro dataset, psnr_ave = 26.8082 on kohler dataset. and i test color model,the value are psnr_ave = 30.2456 and psnr_ave = 27.0550，is this normal?

Hello, could you tell me how to download the kohler datasets? Or could you send it to me? Thank you a lot~

noranali commented 2 years ago

I trained the color deblur model according to the method in the article, the psnr_ave = 29.8877 on gopro dataset, psnr_ave = 26.8082 on kohler dataset. and i test color model,the value are psnr_ave = 30.2456 and psnr_ave = 27.0550，is this normal?

hello , i had an error while training could you help me ? /tensorflow-1.15.2/python3.7/tensorflow_core/python/ops/variable_scope.py in _get_single_variable(self, name, shape, dtype, initializer, regularizer, partition_info, reuse, trainable, collections, caching_device, validate_shape, use_resource, constraint, synchronization, aggregation) 866 tb = [x for x in tb if "tensorflow/python" not in x[0]][:5] 867 raise ValueError("%s Originally defined at:\n\n%s" % --> 868 (err_msg, "".join(traceback.format_list(tb)))) 869 found_var = self._vars[name] 870 if not shape.is_compatible_with(found_var.get_shape()):

ValueError: Variable g_net/enc1_1/weights/Adam/ already exists, disallowed. Did you mean to set reuse=True or reuse=tf.AUTO_REUSE in VarScope? Originally defined at