Files
DALLE2-pytorch/configs/train_decoder_config.test.json
2022-07-09 07:48:07 -07:00

103 lines
2.3 KiB
JSON

{
"decoder": {
"unets": [
{
"dim": 16,
"image_embed_dim": 768,
"cond_dim": 16,
"channels": 3,
"dim_mults": [1, 2, 4, 8],
"attn_dim_head": 16,
"attn_heads": 4,
"self_attn": [false, true, true, true]
}
],
"clip": {
"make": "openai",
"model": "ViT-L/14"
},
"timesteps": 10,
"image_sizes": [64],
"channels": 3,
"loss_type": "l2",
"beta_schedule": ["cosine"],
"learned_variance": true
},
"data": {
"webdataset_base_url": "test_data/{}.tar",
"num_workers": 4,
"batch_size": 4,
"start_shard": 0,
"end_shard": 9,
"shard_width": 1,
"index_width": 1,
"splits": {
"train": 0.75,
"val": 0.15,
"test": 0.1
},
"shuffle_train": false,
"resample_train": true,
"preprocessing": {
"RandomResizedCrop": {
"size": [224, 224],
"scale": [0.75, 1.0],
"ratio": [1.0, 1.0]
},
"ToTensor": true
}
},
"train": {
"epochs": 1,
"lr": 1e-16,
"wd": 0.01,
"max_grad_norm": 0.5,
"save_every_n_samples": 100,
"n_sample_images": 1,
"device": "cpu",
"epoch_samples": 50,
"validation_samples": 5,
"use_ema": true,
"ema_beta": 0.99,
"amp": false,
"save_all": false,
"save_latest": true,
"save_best": true,
"unet_training_mask": [true]
},
"evaluate": {
"n_evaluation_samples": 2,
"FID": {
"feature": 64
},
"IS": {
"feature": 64,
"splits": 10
},
"KID": {
"feature": 64,
"subset_size": 2
},
"LPIPS": {
"net_type": "vgg",
"reduction": "mean"
}
},
"tracker": {
"overwrite_data_path": true,
"log": {
"log_type": "console"
},
"load": {
"load_from": null
},
"save": [{
"save_to": "local"
}]
}
}