niopeng / chimle Goto Github PK

Hello,

Thanks for sharing your creative work. I want to reproduce the colourization result and run your code on single V100 GPU of HPC server. However, in the beginning of print_log.txt I found something very strange:

Random Seed: 0
read lmdb keys from cache: /home/chihchieh/CHIMLE/code/data/colorization_dataset/c_filename.lmdb/_keys_cache.p
Dataset [ColourizationDataset - Train_Colourization] is created.
Number of train images: 721, iters: 2
Total epochs needed: 20 for iters 400,000
read lmdb keys from cache: /home/chihchieh/CHIMLE/code/data/colorization_dataset/c_filename.lmdb/_keys_cache.p
Dataset [ColourizationDataset - Validation_Colourization] is created.
Number of val images in [Validation_Colourization]: 721
initialization method [kaiming]
Remove pixel loss.
Loading model from: /home/chihchieh/CHIMLE/code/models/weights/v0.1/vgg.pth
Mapping network param multiplier: 0.010000 with total length 64
---------- Model initialized ------------------
Number of parameters in G: 210,614,288
Number of parameters in F: 14,714,688

Model [CHIMLEModel] is created.
---------- Start training -------------
---------- validation -------------
Random Seed: 0
read lmdb keys from cache: /home/chihchieh/CHIMLE/code/data/colorization_dataset/c_filename.lmdb/_keys_cache.p
Dataset [ColourizationDataset - Train_Colourization] is created.
Number of train images: 721, iters: 2
Total epochs needed: 20 for iters 400,000
read lmdb keys from cache: /home/chihchieh/CHIMLE/code/data/colorization_dataset/c_filename.lmdb/_keys_cache.p
Dataset [ColourizationDataset - Validation_Colourization] is created.
Number of val images in [Validation_Colourization]: 721
initialization method [kaiming]
Remove pixel loss.
Loading model from: /home/chihchieh/CHIMLE/code/models/weights/v0.1/vgg.pth
Mapping network param multiplier: 0.010000 with total length 64
---------- Model initialized ------------------
Number of parameters in G: 210,614,288
Number of parameters in F: 14,714,688

Model [CHIMLEModel] is created.
---------- Start training -------------
---------- validation -------------
Random Seed: 0
read lmdb keys from cache: /home/chihchieh/CHIMLE/code/data/colorization_dataset/c_filename.lmdb/_keys_cache.p
Dataset [ColourizationDataset - Train_Colourization] is created.
Number of train images: 721, iters: 2
Total epochs needed: 20 for iters 400,000
read lmdb keys from cache: /home/chihchieh/CHIMLE/code/data/colorization_dataset/c_filename.lmdb/_keys_cache.p
Dataset [ColourizationDataset - Validation_Colourization] is created.
Number of val images in [Validation_Colourization]: 721
initialization method [kaiming]
Remove pixel loss.
Loading model from: /home/chihchieh/CHIMLE/code/models/weights/v0.1/vgg.pth
Mapping network param multiplier: 0.010000 with total length 64
---------- Model initialized ------------------
Number of parameters in G: 210,614,288
Number of parameters in F: 14,714,688

Model [CHIMLEModel] is created.
---------- Start training -------------
---------- validation -------------
Random Seed: 0
read lmdb keys from cache: /home/chihchieh/CHIMLE/code/data/colorization_dataset/c_filename.lmdb/_keys_cache.p
Dataset [ColourizationDataset - Train_Colourization] is created.
Number of train images: 721, iters: 2
Total epochs needed: 20 for iters 400,000
read lmdb keys from cache: /home/chihchieh/CHIMLE/code/data/colorization_dataset/c_filename.lmdb/_keys_cache.p
Dataset [ColourizationDataset - Validation_Colourization] is created.
Number of val images in [Validation_Colourization]: 721
initialization method [kaiming]
Remove pixel loss.
Loading model from: /home/chihchieh/CHIMLE/code/models/weights/v0.1/vgg.pth
Mapping network param multiplier: 0.010000 with total length 64
---------- Model initialized ------------------
Number of parameters in G: 210,614,288
Number of parameters in F: 14,714,688

Model [CHIMLEModel] is created.

I mean, looks like training steps are repeated several times but I do not find anything related to parallel/distributed training on train.py. Is it normal or did I do anything wrong? Could you give me some suggestions?

Thanks for your help.

Thanks for your great work. Here's a question about super-resolution task. I downloaded the butterfly datasets (n02279982) and try to generate the SR results under 16x factor. I don't know how you divided the training and testing datasets, so i tested on the whole datasets. However, i didn't get the similar results with yours, some samples showcase significant errors. All the conditions are following your file, except for the down-sampling strategy. Is that possible that the down-sampling method can cause these errors? Looking forward to your reply.

Will a demo be released on Google Colab or Huggingface, Replicate? Thanks

Very interesting technology