Download mnist_bw/vsq/config.yaml from Potpov/grimoire-checkpoints: direct link, hf CLI and curl.
- Browser
- Download file 2.25 kB
-
https://huggingface.co/Potpov/grimoire-checkpoints/resolve/dc58d19ab33de36b0c4e990039cde3447ef9b1cf/mnist_bw/vsq/config.yaml
- Command line
-
hf download hf://Potpov/grimoire-checkpoints@dc58d19ab33de36b0c4e990039cde3447ef9b1cf/mnist_bw/vsq/config.yaml
-
curl -L -o config.yaml https://huggingface.co/Potpov/grimoire-checkpoints/resolve/dc58d19ab33de36b0c4e990039cde3447ef9b1cf/mnist_bw/vsq/config.yaml
2.25 kB
| model_params: | |
| name: "VSQ" # always keep this "VectorGPT" | |
| vector_decoder_model: "cnn" # "mlp" or "raster_conv" | |
| quantized_dim: 512 | |
| codebook_size: 4096 # will be ignored for FSQ | |
| image_loss: "pyramid" # "pyramid" or "mse" | |
| single_code_representation: true | |
| vq_method: "fsq" # "vqvae", "FSQ", "vqtorch" | |
| fsq_levels: [7,5,5,5,5] # will determine codebook_size, see Table 1 of FSQ paper - [7,5,5,5,5] for 4096 (e.g. StrokeNUWA), [8,5,5,5] for 1024 | |
| num_segments: 15 # default 15 - or 64 | |
| pred_color: false | |
| data_params: | |
| dataset: "mnistPrecomputed" | |
| data_path: "/raid/marco.cipriano/data/SVG/Grimoire/MNIST/mnist_pretiled/P128_T6_P20_TH0.1" | |
| train_batch_size: 2048 | |
| val_batch_size: 64 | |
| patch_size: 128 # HAS TO BE 224 FOR CLIP RES50 TO WORK, otherwise take 128 | |
| num_workers: 16 | |
| num_tiles_per_row: 6 | |
| random_colors: false | |
| use_palette: false # use a color palette of 9 colors rather than random colors | |
| padding_frac: 0.1 # fraction of the image that is padded with white background | |
| exp_params: | |
| lr: 0.00002 # 0.00002 | |
| weight_decay: 1.e-4 # specify positive float to enable, start experimenting with 1.e-4/1.e-3 | |
| scheduler_gamma: 0.98 # 0.95 is a good starting value | |
| train_log_interval: 0.025 # len(dataset) / train_batch_size / desired_logging_frequency | |
| manual_seed: 1265 | |
| schedule_pyramid_method: "linear" # "linear" or "exponential" or null to disable scheduling, default disabled | |
| trainer_params: | |
| devices: -1 # always keep at -1 as this takes all available GPUs specified through CUDA_VISIBLE_DEVICES | |
| max_epochs: 250 # dsnt matter too much, got early stopping implemented | |
| # accumulate_grad_batches: 2 | |
| logging_params: | |
| entity: "aiis-chair" # comment to use default wandb entity "aiis-chair" | |
| project: "grimoire-2" # your wandb project name | |
| save_dir: "/raid/marco.cipriano/results/svg/Grimoire/VSQ" | |
| # name: "VSQ_MNIST_BW_P128_T14_P20_TH0.2_S64" # name of the run in wandb | |
| name: "SQ_MNIST_BW_P128_T6_P20_TH0.1" # name of the run in wandb | |
| version: 1 | |
| author: "Marco" # will be a tag in wandb | |
| # id: null # id of wandb run to continue | |
| # allow_val_change: False # allow changing values in this config w.r.t. the run that you're continuing (good for changing loss weightings mid-run) | |