Hugging Face's logo

P-RAJIV
/
cxr_stable_diffusion_v1_5

Text-to-Image
Diffusers
TensorBoard
Safetensors
StableDiffusionPipeline
stable-diffusion
medical-imaging
chest-xray
generative-model
diffusion
Model card Files
xet
 Metrics Community
P-RAJIV commited on
Commit
01c4867
·
verified ·
1 Parent(s): fc3afb6

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. checkpoint-30000/optimizer.bin +3 -0
  2. checkpoint-30000/random_states_0.pkl +3 -0
  3. checkpoint-30000/scaler.pt +3 -0
  4. checkpoint-30000/scheduler.bin +3 -0
  5. checkpoint-30000/unet/config.json +68 -0
  6. checkpoint-30000/unet/diffusion_pytorch_model.safetensors +3 -0
  7. checkpoint-30000/unet_ema/config.json +75 -0
  8. checkpoint-30000/unet_ema/diffusion_pytorch_model.safetensors +3 -0
  9. feature_extractor/preprocessor_config.json +27 -0
  10. logs/text2image-fine-tune/1773313946.2800422/events.out.tfevents.1773313946.WellsFargo.1767867.1 +3 -0
  11. logs/text2image-fine-tune/1773313946.281736/hparams.yml +56 -0
  12. logs/text2image-fine-tune/1773314143.1666863/events.out.tfevents.1773314143.WellsFargo.1775805.1 +3 -0
  13. logs/text2image-fine-tune/1773314143.1684391/hparams.yml +56 -0
  14. logs/text2image-fine-tune/1773314385.1689467/events.out.tfevents.1773314385.WellsFargo.1784007.1 +3 -0
  15. logs/text2image-fine-tune/1773314385.1789281/hparams.yml +56 -0
  16. logs/text2image-fine-tune/1773314609.096439/events.out.tfevents.1773314609.WellsFargo.1791860.1 +3 -0
  17. logs/text2image-fine-tune/1773314609.09864/hparams.yml +56 -0
  18. logs/text2image-fine-tune/1773328547.0271382/events.out.tfevents.1773328547.WellsFargo.2198663.1 +3 -0
  19. logs/text2image-fine-tune/1773328547.0285063/hparams.yml +56 -0
  20. logs/text2image-fine-tune/1773341258.0622778/events.out.tfevents.1773341258.WellsFargo.2566051.1 +3 -0
  21. logs/text2image-fine-tune/1773341258.0645905/hparams.yml +56 -0
  22. logs/text2image-fine-tune/1773341453.8851287/events.out.tfevents.1773341453.WellsFargo.2572900.1 +3 -0
  23. logs/text2image-fine-tune/1773341453.8868177/hparams.yml +56 -0
  24. logs/text2image-fine-tune/1773343021.0437884/events.out.tfevents.1773343021.WellsFargo.2608126.1 +3 -0
  25. logs/text2image-fine-tune/1773343021.0454438/hparams.yml +56 -0
  26. logs/text2image-fine-tune/1773961364.019682/events.out.tfevents.1773961364.WellsFargo.1983485.1 +3 -0
  27. logs/text2image-fine-tune/1773961364.0217724/hparams.yml +56 -0
  28. logs/text2image-fine-tune/1773962083.1942053/events.out.tfevents.1773962083.WellsFargo.2002346.1 +3 -0
  29. logs/text2image-fine-tune/1773962083.1961029/hparams.yml +56 -0
  30. logs/text2image-fine-tune/1774001463.3417916/events.out.tfevents.1774001463.WellsFargo.2847786.1 +3 -0
  31. logs/text2image-fine-tune/1774001463.3435822/hparams.yml +56 -0
  32. logs/text2image-fine-tune/1774077639.0161753/events.out.tfevents.1774077639.WellsFargo.1025630.1 +3 -0
  33. logs/text2image-fine-tune/1774077639.0331078/hparams.yml +56 -0
  34. logs/text2image-fine-tune/events.out.tfevents.1773313946.WellsFargo.1767867.0 +3 -0
  35. logs/text2image-fine-tune/events.out.tfevents.1773314143.WellsFargo.1775805.0 +3 -0
  36. logs/text2image-fine-tune/events.out.tfevents.1773314385.WellsFargo.1784007.0 +3 -0
  37. logs/text2image-fine-tune/events.out.tfevents.1773314609.WellsFargo.1791860.0 +3 -0
  38. logs/text2image-fine-tune/events.out.tfevents.1773328547.WellsFargo.2198663.0 +3 -0
  39. logs/text2image-fine-tune/events.out.tfevents.1773341258.WellsFargo.2566051.0 +3 -0
  40. logs/text2image-fine-tune/events.out.tfevents.1773341453.WellsFargo.2572900.0 +3 -0
  41. logs/text2image-fine-tune/events.out.tfevents.1773343021.WellsFargo.2608126.0 +3 -0
  42. logs/text2image-fine-tune/events.out.tfevents.1773952929.WellsFargo.1798694.0 +0 -0
  43. logs/text2image-fine-tune/events.out.tfevents.1773961364.WellsFargo.1983485.0 +3 -0
  44. logs/text2image-fine-tune/events.out.tfevents.1773962083.WellsFargo.2002346.0 +3 -0
  45. logs/text2image-fine-tune/events.out.tfevents.1774001463.WellsFargo.2847786.0 +3 -0
  46. logs/text2image-fine-tune/events.out.tfevents.1774077639.WellsFargo.1025630.0 +3 -0
  47. model_index.json +38 -0
  48. remove_ckpts.sh +17 -0
  49. safety_checker/config.json +46 -0
  50. safety_checker/model.safetensors +3 -0
checkpoint-30000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92229899dd93c63609ca7bb3bc339341147994975053fd3c64e023a73cc1c188
3
+ size 6876766873
checkpoint-30000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdb95badf5d935cf2dc9f61b7b70ebfeeb7ee4e9d0db143b84e3916754bbc080
3
+ size 15081
checkpoint-30000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e6b3abeb3f827a4b31dd55303846dd695c516167438b444ce4c480a14f3b241
3
+ size 1383
checkpoint-30000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6e4517e3b8f93f4d51313c9617eb3b984119789387c4e58dcc7509774782b10
3
+ size 1401
checkpoint-30000/unet/config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.38.0.dev0",
4
+ "_name_or_path": "/data4/scratch/rajiv/sd_v_1_5_mimic/cxr_mimic_sd_v1_5/checkpoint-25000",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": null,
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": null,
9
+ "attention_head_dim": 8,
10
+ "attention_type": "default",
11
+ "block_out_channels": [
12
+ 320,
13
+ 640,
14
+ 1280,
15
+ 1280
16
+ ],
17
+ "center_input_sample": false,
18
+ "class_embed_type": null,
19
+ "class_embeddings_concat": false,
20
+ "conv_in_kernel": 3,
21
+ "conv_out_kernel": 3,
22
+ "cross_attention_dim": 768,
23
+ "cross_attention_norm": null,
24
+ "down_block_types": [
25
+ "CrossAttnDownBlock2D",
26
+ "CrossAttnDownBlock2D",
27
+ "CrossAttnDownBlock2D",
28
+ "DownBlock2D"
29
+ ],
30
+ "downsample_padding": 1,
31
+ "dropout": 0.0,
32
+ "dual_cross_attention": false,
33
+ "encoder_hid_dim": null,
34
+ "encoder_hid_dim_type": null,
35
+ "flip_sin_to_cos": true,
36
+ "freq_shift": 0,
37
+ "in_channels": 4,
38
+ "layers_per_block": 2,
39
+ "mid_block_only_cross_attention": null,
40
+ "mid_block_scale_factor": 1,
41
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
42
+ "norm_eps": 1e-05,
43
+ "norm_num_groups": 32,
44
+ "num_attention_heads": null,
45
+ "num_class_embeds": null,
46
+ "only_cross_attention": false,
47
+ "out_channels": 4,
48
+ "projection_class_embeddings_input_dim": null,
49
+ "resnet_out_scale_factor": 1.0,
50
+ "resnet_skip_time_act": false,
51
+ "resnet_time_scale_shift": "default",
52
+ "reverse_transformer_layers_per_block": null,
53
+ "sample_size": 64,
54
+ "time_cond_proj_dim": null,
55
+ "time_embedding_act_fn": null,
56
+ "time_embedding_dim": null,
57
+ "time_embedding_type": "positional",
58
+ "timestep_post_act": null,
59
+ "transformer_layers_per_block": 1,
60
+ "up_block_types": [
61
+ "UpBlock2D",
62
+ "CrossAttnUpBlock2D",
63
+ "CrossAttnUpBlock2D",
64
+ "CrossAttnUpBlock2D"
65
+ ],
66
+ "upcast_attention": false,
67
+ "use_linear_projection": false
68
+ }
checkpoint-30000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57b966dc09875c376d06a18d2af7bf8a24417a406c7a741ca143494c5b7514d3
3
+ size 3438167536
checkpoint-30000/unet_ema/config.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.38.0.dev0",
4
+ "_name_or_path": "stable-diffusion-v1-5/stable-diffusion-v1-5",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": null,
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": null,
9
+ "attention_head_dim": 8,
10
+ "attention_type": "default",
11
+ "block_out_channels": [
12
+ 320,
13
+ 640,
14
+ 1280,
15
+ 1280
16
+ ],
17
+ "center_input_sample": false,
18
+ "class_embed_type": null,
19
+ "class_embeddings_concat": false,
20
+ "conv_in_kernel": 3,
21
+ "conv_out_kernel": 3,
22
+ "cross_attention_dim": 768,
23
+ "cross_attention_norm": null,
24
+ "decay": 0.9999,
25
+ "down_block_types": [
26
+ "CrossAttnDownBlock2D",
27
+ "CrossAttnDownBlock2D",
28
+ "CrossAttnDownBlock2D",
29
+ "DownBlock2D"
30
+ ],
31
+ "downsample_padding": 1,
32
+ "dropout": 0.0,
33
+ "dual_cross_attention": false,
34
+ "encoder_hid_dim": null,
35
+ "encoder_hid_dim_type": null,
36
+ "flip_sin_to_cos": true,
37
+ "freq_shift": 0,
38
+ "in_channels": 4,
39
+ "inv_gamma": 1.0,
40
+ "layers_per_block": 2,
41
+ "mid_block_only_cross_attention": null,
42
+ "mid_block_scale_factor": 1,
43
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
44
+ "min_decay": 0.0,
45
+ "norm_eps": 1e-05,
46
+ "norm_num_groups": 32,
47
+ "num_attention_heads": null,
48
+ "num_class_embeds": null,
49
+ "only_cross_attention": false,
50
+ "optimization_step": 30000,
51
+ "out_channels": 4,
52
+ "power": 0.6666666666666666,
53
+ "projection_class_embeddings_input_dim": null,
54
+ "resnet_out_scale_factor": 1.0,
55
+ "resnet_skip_time_act": false,
56
+ "resnet_time_scale_shift": "default",
57
+ "reverse_transformer_layers_per_block": null,
58
+ "sample_size": 64,
59
+ "time_cond_proj_dim": null,
60
+ "time_embedding_act_fn": null,
61
+ "time_embedding_dim": null,
62
+ "time_embedding_type": "positional",
63
+ "timestep_post_act": null,
64
+ "transformer_layers_per_block": 1,
65
+ "up_block_types": [
66
+ "UpBlock2D",
67
+ "CrossAttnUpBlock2D",
68
+ "CrossAttnUpBlock2D",
69
+ "CrossAttnUpBlock2D"
70
+ ],
71
+ "upcast_attention": false,
72
+ "update_after_step": 0,
73
+ "use_ema_warmup": false,
74
+ "use_linear_projection": false
75
+ }
checkpoint-30000/unet_ema/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f563dc539ddbfe8cdda254f90819bcb5a93d5f1ae0408440d60e538d12aa5fa
3
+ size 3438167536
feature_extractor/preprocessor_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 224,
4
+ "width": 224
5
+ },
6
+ "do_center_crop": true,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "image_mean": [
12
+ 0.48145466,
13
+ 0.4578275,
14
+ 0.40821073
15
+ ],
16
+ "image_processor_type": "CLIPImageProcessor",
17
+ "image_std": [
18
+ 0.26862954,
19
+ 0.26130258,
20
+ 0.27577711
21
+ ],
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "shortest_edge": 224
26
+ }
27
+ }
logs/text2image-fine-tune/1773313946.2800422/events.out.tfevents.1773313946.WellsFargo.1767867.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e50c54d855dccb0e694d9d3113c90e58d539692b6d6f075f2424ea4ca9df909c
3
+ size 2570
logs/text2image-fine-tune/1773313946.281736/hparams.yml ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ cache_dir: null
7
+ caption_column: text
8
+ center_crop: true
9
+ checkpointing_steps: 500
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: null
14
+ dream_detail_preservation: 1.0
15
+ dream_training: false
16
+ enable_xformers_memory_efficient_attention: true
17
+ foreach_ema: false
18
+ gradient_accumulation_steps: 4
19
+ gradient_checkpointing: true
20
+ hub_model_id: null
21
+ hub_token: null
22
+ image_column: image
23
+ image_interpolation_mode: lanczos
24
+ input_perturbation: 0
25
+ learning_rate: 1.0e-05
26
+ local_rank: 0
27
+ logging_dir: logs
28
+ lr_scheduler: constant
29
+ lr_warmup_steps: 0
30
+ max_grad_norm: 1.0
31
+ max_train_samples: null
32
+ max_train_steps: 15000
33
+ mixed_precision: fp16
34
+ noise_offset: 0
35
+ non_ema_revision: null
36
+ num_train_epochs: 1
37
+ offload_ema: false
38
+ output_dir: cxr_mimic_sd_v1_5
39
+ prediction_type: null
40
+ pretrained_model_name_or_path: stable-diffusion-v1-5/stable-diffusion-v1-5
41
+ push_to_hub: false
42
+ random_flip: true
43
+ report_to: tensorboard
44
+ resolution: 512
45
+ resume_from_checkpoint: null
46
+ revision: null
47
+ scale_lr: false
48
+ seed: null
49
+ snr_gamma: null
50
+ tracker_project_name: text2image-fine-tune
51
+ train_batch_size: 1
52
+ train_data_dir: /data3/scratch/rajiv/cxr_gen_thesis/data/train
53
+ use_8bit_adam: false
54
+ use_ema: true
55
+ validation_epochs: 5
56
+ variant: null
logs/text2image-fine-tune/1773314143.1666863/events.out.tfevents.1773314143.WellsFargo.1775805.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5eee9376eb50cb4c85bc32b61a6bb74f30eacaa13f5954c8ddca962669b5047
3
+ size 2570
logs/text2image-fine-tune/1773314143.1684391/hparams.yml ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ cache_dir: null
7
+ caption_column: text
8
+ center_crop: true
9
+ checkpointing_steps: 500
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: null
14
+ dream_detail_preservation: 1.0
15
+ dream_training: false
16
+ enable_xformers_memory_efficient_attention: true
17
+ foreach_ema: false
18
+ gradient_accumulation_steps: 4
19
+ gradient_checkpointing: true
20
+ hub_model_id: null
21
+ hub_token: null
22
+ image_column: image
23
+ image_interpolation_mode: lanczos
24
+ input_perturbation: 0
25
+ learning_rate: 1.0e-05
26
+ local_rank: 0
27
+ logging_dir: logs
28
+ lr_scheduler: constant
29
+ lr_warmup_steps: 0
30
+ max_grad_norm: 1.0
31
+ max_train_samples: null
32
+ max_train_steps: 15000
33
+ mixed_precision: fp16
34
+ noise_offset: 0
35
+ non_ema_revision: null
36
+ num_train_epochs: 2
37
+ offload_ema: false
38
+ output_dir: cxr_mimic_sd_v1_5
39
+ prediction_type: null
40
+ pretrained_model_name_or_path: stable-diffusion-v1-5/stable-diffusion-v1-5
41
+ push_to_hub: false
42
+ random_flip: true
43
+ report_to: tensorboard
44
+ resolution: 512
45
+ resume_from_checkpoint: null
46
+ revision: null
47
+ scale_lr: false
48
+ seed: null
49
+ snr_gamma: null
50
+ tracker_project_name: text2image-fine-tune
51
+ train_batch_size: 4
52
+ train_data_dir: /data3/scratch/rajiv/cxr_gen_thesis/data/train
53
+ use_8bit_adam: false
54
+ use_ema: true
55
+ validation_epochs: 5
56
+ variant: null
logs/text2image-fine-tune/1773314385.1689467/events.out.tfevents.1773314385.WellsFargo.1784007.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cc7d35b14d45ef0a4512565d171548a196c4e98e4653c17f0daa5f84b41a1a8
3
+ size 2570
logs/text2image-fine-tune/1773314385.1789281/hparams.yml ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ cache_dir: null
7
+ caption_column: text
8
+ center_crop: true
9
+ checkpointing_steps: 500
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: null
14
+ dream_detail_preservation: 1.0
15
+ dream_training: false
16
+ enable_xformers_memory_efficient_attention: true
17
+ foreach_ema: false
18
+ gradient_accumulation_steps: 4
19
+ gradient_checkpointing: true
20
+ hub_model_id: null
21
+ hub_token: null
22
+ image_column: image
23
+ image_interpolation_mode: lanczos
24
+ input_perturbation: 0
25
+ learning_rate: 1.0e-05
26
+ local_rank: 0
27
+ logging_dir: logs
28
+ lr_scheduler: constant
29
+ lr_warmup_steps: 0
30
+ max_grad_norm: 1.0
31
+ max_train_samples: null
32
+ max_train_steps: 100000
33
+ mixed_precision: fp16
34
+ noise_offset: 0
35
+ non_ema_revision: null
36
+ num_train_epochs: 70
37
+ offload_ema: false
38
+ output_dir: cxr_mimic_sd_v1_5
39
+ prediction_type: null
40
+ pretrained_model_name_or_path: stable-diffusion-v1-5/stable-diffusion-v1-5
41
+ push_to_hub: false
42
+ random_flip: true
43
+ report_to: tensorboard
44
+ resolution: 512
45
+ resume_from_checkpoint: null
46
+ revision: null
47
+ scale_lr: false
48
+ seed: null
49
+ snr_gamma: null
50
+ tracker_project_name: text2image-fine-tune
51
+ train_batch_size: 32
52
+ train_data_dir: /data3/scratch/rajiv/cxr_gen_thesis/data/train
53
+ use_8bit_adam: false
54
+ use_ema: true
55
+ validation_epochs: 5
56
+ variant: null
logs/text2image-fine-tune/1773314609.096439/events.out.tfevents.1773314609.WellsFargo.1791860.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cdbf69d798317d88e5fcb8bfe12e2da6bac8fdcd5fb79e6fca0b5530ad3a2f2
3
+ size 2570
logs/text2image-fine-tune/1773314609.09864/hparams.yml ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ cache_dir: null
7
+ caption_column: text
8
+ center_crop: true
9
+ checkpointing_steps: 500
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: null
14
+ dream_detail_preservation: 1.0
15
+ dream_training: false
16
+ enable_xformers_memory_efficient_attention: true
17
+ foreach_ema: false
18
+ gradient_accumulation_steps: 4
19
+ gradient_checkpointing: true
20
+ hub_model_id: null
21
+ hub_token: null
22
+ image_column: image
23
+ image_interpolation_mode: lanczos
24
+ input_perturbation: 0
25
+ learning_rate: 1.0e-05
26
+ local_rank: 0
27
+ logging_dir: logs
28
+ lr_scheduler: constant
29
+ lr_warmup_steps: 0
30
+ max_grad_norm: 1.0
31
+ max_train_samples: null
32
+ max_train_steps: 100000
33
+ mixed_precision: fp16
34
+ noise_offset: 0
35
+ non_ema_revision: null
36
+ num_train_epochs: 35
37
+ offload_ema: false
38
+ output_dir: cxr_mimic_sd_v1_5
39
+ prediction_type: null
40
+ pretrained_model_name_or_path: stable-diffusion-v1-5/stable-diffusion-v1-5
41
+ push_to_hub: false
42
+ random_flip: true
43
+ report_to: tensorboard
44
+ resolution: 512
45
+ resume_from_checkpoint: null
46
+ revision: null
47
+ scale_lr: false
48
+ seed: null
49
+ snr_gamma: null
50
+ tracker_project_name: text2image-fine-tune
51
+ train_batch_size: 16
52
+ train_data_dir: /data3/scratch/rajiv/cxr_gen_thesis/data/train
53
+ use_8bit_adam: false
54
+ use_ema: true
55
+ validation_epochs: 5
56
+ variant: null
logs/text2image-fine-tune/1773328547.0271382/events.out.tfevents.1773328547.WellsFargo.2198663.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae652dc0cbda32bdc509042dd2ac9e5bd29931bc5ced545fb2c727c2af026b0b
3
+ size 2570
logs/text2image-fine-tune/1773328547.0285063/hparams.yml ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ cache_dir: null
7
+ caption_column: text
8
+ center_crop: true
9
+ checkpointing_steps: 500
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: null
14
+ dream_detail_preservation: 1.0
15
+ dream_training: false
16
+ enable_xformers_memory_efficient_attention: true
17
+ foreach_ema: false
18
+ gradient_accumulation_steps: 4
19
+ gradient_checkpointing: true
20
+ hub_model_id: null
21
+ hub_token: null
22
+ image_column: image
23
+ image_interpolation_mode: lanczos
24
+ input_perturbation: 0
25
+ learning_rate: 1.0e-05
26
+ local_rank: 0
27
+ logging_dir: logs
28
+ lr_scheduler: constant
29
+ lr_warmup_steps: 0
30
+ max_grad_norm: 1.0
31
+ max_train_samples: null
32
+ max_train_steps: 100000
33
+ mixed_precision: fp16
34
+ noise_offset: 0
35
+ non_ema_revision: null
36
+ num_train_epochs: 18
37
+ offload_ema: false
38
+ output_dir: cxr_mimic_sd_v1_5
39
+ prediction_type: null
40
+ pretrained_model_name_or_path: stable-diffusion-v1-5/stable-diffusion-v1-5
41
+ push_to_hub: false
42
+ random_flip: true
43
+ report_to: tensorboard
44
+ resolution: 512
45
+ resume_from_checkpoint: null
46
+ revision: null
47
+ scale_lr: false
48
+ seed: null
49
+ snr_gamma: null
50
+ tracker_project_name: text2image-fine-tune
51
+ train_batch_size: 8
52
+ train_data_dir: /data3/scratch/rajiv/cxr_gen_thesis/data/train
53
+ use_8bit_adam: false
54
+ use_ema: true
55
+ validation_epochs: 5
56
+ variant: null
logs/text2image-fine-tune/1773341258.0622778/events.out.tfevents.1773341258.WellsFargo.2566051.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44f8efcc72b791281c41b814fb11b39c30b2faecde4e912fb0ff3bb293363e16
3
+ size 2670
logs/text2image-fine-tune/1773341258.0645905/hparams.yml ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ cache_dir: null
7
+ caption_column: text
8
+ center_crop: true
9
+ checkpointing_steps: 500
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: null
14
+ dream_detail_preservation: 1.0
15
+ dream_training: false
16
+ enable_xformers_memory_efficient_attention: true
17
+ foreach_ema: false
18
+ gradient_accumulation_steps: 4
19
+ gradient_checkpointing: true
20
+ hub_model_id: null
21
+ hub_token: null
22
+ image_column: image
23
+ image_interpolation_mode: lanczos
24
+ input_perturbation: 0
25
+ learning_rate: 1.0e-05
26
+ local_rank: 0
27
+ logging_dir: logs
28
+ lr_scheduler: constant
29
+ lr_warmup_steps: 0
30
+ max_grad_norm: 1.0
31
+ max_train_samples: null
32
+ max_train_steps: 100000
33
+ mixed_precision: fp16
34
+ noise_offset: 0
35
+ non_ema_revision: null
36
+ num_train_epochs: 18
37
+ offload_ema: false
38
+ output_dir: /data4/scratch/rajiv/sd_v_1_5_mimic/cxr_mimic_sd_v1_5
39
+ prediction_type: null
40
+ pretrained_model_name_or_path: stable-diffusion-v1-5/stable-diffusion-v1-5
41
+ push_to_hub: false
42
+ random_flip: true
43
+ report_to: tensorboard
44
+ resolution: 512
45
+ resume_from_checkpoint: latest
46
+ revision: null
47
+ scale_lr: false
48
+ seed: null
49
+ snr_gamma: null
50
+ tracker_project_name: text2image-fine-tune
51
+ train_batch_size: 8
52
+ train_data_dir: /data3/scratch/rajiv/cxr_gen_thesis/data/train
53
+ use_8bit_adam: false
54
+ use_ema: true
55
+ validation_epochs: 5
56
+ variant: null
logs/text2image-fine-tune/1773341453.8851287/events.out.tfevents.1773341453.WellsFargo.2572900.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fdb73951157c64fe3ca03b1341c9fa626ee3769da3e1e9f2db0e6edac1d7132
3
+ size 2606
logs/text2image-fine-tune/1773341453.8868177/hparams.yml ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ cache_dir: null
7
+ caption_column: text
8
+ center_crop: true
9
+ checkpointing_steps: 500
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: null
14
+ dream_detail_preservation: 1.0
15
+ dream_training: false
16
+ enable_xformers_memory_efficient_attention: true
17
+ foreach_ema: false
18
+ gradient_accumulation_steps: 4
19
+ gradient_checkpointing: true
20
+ hub_model_id: null
21
+ hub_token: null
22
+ image_column: image
23
+ image_interpolation_mode: lanczos
24
+ input_perturbation: 0
25
+ learning_rate: 1.0e-05
26
+ local_rank: 0
27
+ logging_dir: logs
28
+ lr_scheduler: constant
29
+ lr_warmup_steps: 0
30
+ max_grad_norm: 1.0
31
+ max_train_samples: null
32
+ max_train_steps: 100000
33
+ mixed_precision: fp16
34
+ noise_offset: 0
35
+ non_ema_revision: null
36
+ num_train_epochs: 18
37
+ offload_ema: false
38
+ output_dir: /data4/scratch/rajiv/sd_v_1_5_mimic/cxr_mimic_sd_v1_5
39
+ prediction_type: null
40
+ pretrained_model_name_or_path: stable-diffusion-v1-5/stable-diffusion-v1-5
41
+ push_to_hub: false
42
+ random_flip: true
43
+ report_to: tensorboard
44
+ resolution: 512
45
+ resume_from_checkpoint: null
46
+ revision: null
47
+ scale_lr: false
48
+ seed: null
49
+ snr_gamma: null
50
+ tracker_project_name: text2image-fine-tune
51
+ train_batch_size: 8
52
+ train_data_dir: /data3/scratch/rajiv/cxr_gen_thesis/data/train
53
+ use_8bit_adam: false
54
+ use_ema: true
55
+ validation_epochs: 5
56
+ variant: null
logs/text2image-fine-tune/1773343021.0437884/events.out.tfevents.1773343021.WellsFargo.2608126.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b94d2b6dcd24e48044781d484956c3fc68224b7ae0db989c92db94c1a35c0f9c
3
+ size 2606
logs/text2image-fine-tune/1773343021.0454438/hparams.yml ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ cache_dir: null
7
+ caption_column: text
8
+ center_crop: true
9
+ checkpointing_steps: 500
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: null
14
+ dream_detail_preservation: 1.0
15
+ dream_training: false
16
+ enable_xformers_memory_efficient_attention: true
17
+ foreach_ema: false
18
+ gradient_accumulation_steps: 4
19
+ gradient_checkpointing: true
20
+ hub_model_id: null
21
+ hub_token: null
22
+ image_column: image
23
+ image_interpolation_mode: lanczos
24
+ input_perturbation: 0
25
+ learning_rate: 1.0e-05
26
+ local_rank: 0
27
+ logging_dir: logs
28
+ lr_scheduler: constant
29
+ lr_warmup_steps: 0
30
+ max_grad_norm: 1.0
31
+ max_train_samples: null
32
+ max_train_steps: 30000
33
+ mixed_precision: fp16
34
+ noise_offset: 0
35
+ non_ema_revision: null
36
+ num_train_epochs: 6
37
+ offload_ema: false
38
+ output_dir: /data4/scratch/rajiv/sd_v_1_5_mimic/cxr_mimic_sd_v1_5
39
+ prediction_type: null
40
+ pretrained_model_name_or_path: stable-diffusion-v1-5/stable-diffusion-v1-5
41
+ push_to_hub: false
42
+ random_flip: true
43
+ report_to: tensorboard
44
+ resolution: 512
45
+ resume_from_checkpoint: null
46
+ revision: null
47
+ scale_lr: false
48
+ seed: null
49
+ snr_gamma: null
50
+ tracker_project_name: text2image-fine-tune
51
+ train_batch_size: 8
52
+ train_data_dir: /data3/scratch/rajiv/cxr_gen_thesis/data/train
53
+ use_8bit_adam: false
54
+ use_ema: true
55
+ validation_epochs: 5
56
+ variant: null
logs/text2image-fine-tune/1773961364.019682/events.out.tfevents.1773961364.WellsFargo.1983485.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71d3a6815ce68bdaec62103c350349583f8d969283782ed07cf3eb1f45f9d7d5
3
+ size 2670
logs/text2image-fine-tune/1773961364.0217724/hparams.yml ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ cache_dir: null
7
+ caption_column: text
8
+ center_crop: true
9
+ checkpointing_steps: 5000
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: null
14
+ dream_detail_preservation: 1.0
15
+ dream_training: false
16
+ enable_xformers_memory_efficient_attention: true
17
+ foreach_ema: false
18
+ gradient_accumulation_steps: 4
19
+ gradient_checkpointing: true
20
+ hub_model_id: null
21
+ hub_token: null
22
+ image_column: image
23
+ image_interpolation_mode: lanczos
24
+ input_perturbation: 0
25
+ learning_rate: 1.0e-05
26
+ local_rank: 0
27
+ logging_dir: logs
28
+ lr_scheduler: constant
29
+ lr_warmup_steps: 0
30
+ max_grad_norm: 1.0
31
+ max_train_samples: null
32
+ max_train_steps: 30000
33
+ mixed_precision: fp16
34
+ noise_offset: 0
35
+ non_ema_revision: null
36
+ num_train_epochs: 2
37
+ offload_ema: false
38
+ output_dir: /data4/scratch/rajiv/sd_v_1_5_mimic/cxr_mimic_sd_v1_5
39
+ prediction_type: null
40
+ pretrained_model_name_or_path: stable-diffusion-v1-5/stable-diffusion-v1-5
41
+ push_to_hub: false
42
+ random_flip: true
43
+ report_to: tensorboard
44
+ resolution: 512
45
+ resume_from_checkpoint: latest
46
+ revision: null
47
+ scale_lr: false
48
+ seed: null
49
+ snr_gamma: null
50
+ tracker_project_name: text2image-fine-tune
51
+ train_batch_size: 2
52
+ train_data_dir: /data3/scratch/rajiv/cxr_gen_thesis/data/train
53
+ use_8bit_adam: false
54
+ use_ema: true
55
+ validation_epochs: 5
56
+ variant: null
logs/text2image-fine-tune/1773962083.1942053/events.out.tfevents.1773962083.WellsFargo.2002346.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0af647ca1b1fb0cb9006c1da4d3c8dcb7a723b6445fefcc2121c6180d7945b48
3
+ size 2670
logs/text2image-fine-tune/1773962083.1961029/hparams.yml ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ cache_dir: null
7
+ caption_column: text
8
+ center_crop: true
9
+ checkpointing_steps: 5000
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: null
14
+ dream_detail_preservation: 1.0
15
+ dream_training: false
16
+ enable_xformers_memory_efficient_attention: true
17
+ foreach_ema: false
18
+ gradient_accumulation_steps: 4
19
+ gradient_checkpointing: true
20
+ hub_model_id: null
21
+ hub_token: null
22
+ image_column: image
23
+ image_interpolation_mode: lanczos
24
+ input_perturbation: 0
25
+ learning_rate: 1.0e-05
26
+ local_rank: 0
27
+ logging_dir: logs
28
+ lr_scheduler: constant
29
+ lr_warmup_steps: 0
30
+ max_grad_norm: 1.0
31
+ max_train_samples: null
32
+ max_train_steps: 30000
33
+ mixed_precision: fp16
34
+ noise_offset: 0
35
+ non_ema_revision: null
36
+ num_train_epochs: 2
37
+ offload_ema: false
38
+ output_dir: /data4/scratch/rajiv/sd_v_1_5_mimic/cxr_mimic_sd_v1_5
39
+ prediction_type: null
40
+ pretrained_model_name_or_path: stable-diffusion-v1-5/stable-diffusion-v1-5
41
+ push_to_hub: false
42
+ random_flip: true
43
+ report_to: tensorboard
44
+ resolution: 512
45
+ resume_from_checkpoint: latest
46
+ revision: null
47
+ scale_lr: false
48
+ seed: null
49
+ snr_gamma: null
50
+ tracker_project_name: text2image-fine-tune
51
+ train_batch_size: 2
52
+ train_data_dir: /data3/scratch/rajiv/cxr_gen_thesis/data/train
53
+ use_8bit_adam: false
54
+ use_ema: true
55
+ validation_epochs: 5
56
+ variant: null
logs/text2image-fine-tune/1774001463.3417916/events.out.tfevents.1774001463.WellsFargo.2847786.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:528cd61af8161a4bdcf1c006dc9f6d168479511955768c4289dd9d4a5f9c40a3
3
+ size 2670
logs/text2image-fine-tune/1774001463.3435822/hparams.yml ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ cache_dir: null
7
+ caption_column: text
8
+ center_crop: true
9
+ checkpointing_steps: 5000
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: null
14
+ dream_detail_preservation: 1.0
15
+ dream_training: false
16
+ enable_xformers_memory_efficient_attention: true
17
+ foreach_ema: false
18
+ gradient_accumulation_steps: 4
19
+ gradient_checkpointing: true
20
+ hub_model_id: null
21
+ hub_token: null
22
+ image_column: image
23
+ image_interpolation_mode: lanczos
24
+ input_perturbation: 0
25
+ learning_rate: 1.0e-05
26
+ local_rank: 0
27
+ logging_dir: logs
28
+ lr_scheduler: constant
29
+ lr_warmup_steps: 0
30
+ max_grad_norm: 1.0
31
+ max_train_samples: null
32
+ max_train_steps: 30000
33
+ mixed_precision: fp16
34
+ noise_offset: 0
35
+ non_ema_revision: null
36
+ num_train_epochs: 2
37
+ offload_ema: false
38
+ output_dir: /data4/scratch/rajiv/sd_v_1_5_mimic/cxr_mimic_sd_v1_5
39
+ prediction_type: null
40
+ pretrained_model_name_or_path: stable-diffusion-v1-5/stable-diffusion-v1-5
41
+ push_to_hub: false
42
+ random_flip: true
43
+ report_to: tensorboard
44
+ resolution: 512
45
+ resume_from_checkpoint: latest
46
+ revision: null
47
+ scale_lr: false
48
+ seed: null
49
+ snr_gamma: null
50
+ tracker_project_name: text2image-fine-tune
51
+ train_batch_size: 2
52
+ train_data_dir: /data3/scratch/rajiv/cxr_gen_thesis/data/train
53
+ use_8bit_adam: false
54
+ use_ema: true
55
+ validation_epochs: 5
56
+ variant: null
logs/text2image-fine-tune/1774077639.0161753/events.out.tfevents.1774077639.WellsFargo.1025630.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a970fb6e79af501ada40e3d61a4710654df346595623cca9714724882e4daf9
3
+ size 2670
logs/text2image-fine-tune/1774077639.0331078/hparams.yml ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ cache_dir: null
7
+ caption_column: text
8
+ center_crop: true
9
+ checkpointing_steps: 5000
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: null
14
+ dream_detail_preservation: 1.0
15
+ dream_training: false
16
+ enable_xformers_memory_efficient_attention: true
17
+ foreach_ema: false
18
+ gradient_accumulation_steps: 4
19
+ gradient_checkpointing: true
20
+ hub_model_id: null
21
+ hub_token: null
22
+ image_column: image
23
+ image_interpolation_mode: lanczos
24
+ input_perturbation: 0
25
+ learning_rate: 1.0e-05
26
+ local_rank: 0
27
+ logging_dir: logs
28
+ lr_scheduler: constant
29
+ lr_warmup_steps: 0
30
+ max_grad_norm: 1.0
31
+ max_train_samples: null
32
+ max_train_steps: 30000
33
+ mixed_precision: fp16
34
+ noise_offset: 0
35
+ non_ema_revision: null
36
+ num_train_epochs: 2
37
+ offload_ema: false
38
+ output_dir: /data4/scratch/rajiv/sd_v_1_5_mimic/cxr_mimic_sd_v1_5
39
+ prediction_type: null
40
+ pretrained_model_name_or_path: stable-diffusion-v1-5/stable-diffusion-v1-5
41
+ push_to_hub: false
42
+ random_flip: true
43
+ report_to: tensorboard
44
+ resolution: 512
45
+ resume_from_checkpoint: latest
46
+ revision: null
47
+ scale_lr: false
48
+ seed: null
49
+ snr_gamma: null
50
+ tracker_project_name: text2image-fine-tune
51
+ train_batch_size: 2
52
+ train_data_dir: /data3/scratch/rajiv/cxr_gen_thesis/data/train
53
+ use_8bit_adam: false
54
+ use_ema: true
55
+ validation_epochs: 5
56
+ variant: null
logs/text2image-fine-tune/events.out.tfevents.1773313946.WellsFargo.1767867.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e89fae5f7fd806ce133d05c7e6290a26b85be656d8670a718b5354bc3a8583bc
3
+ size 760
logs/text2image-fine-tune/events.out.tfevents.1773314143.WellsFargo.1775805.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f46c05f72dd0b0c214c503ca9502e4eb7bbaf1e3ff7dee89edcabe4c952ea534
3
+ size 952
logs/text2image-fine-tune/events.out.tfevents.1773314385.WellsFargo.1784007.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a744a46027369cc6c0018c4845712f942ff6c45f8c4a3ce6a49c2f276c959d55
3
+ size 136
logs/text2image-fine-tune/events.out.tfevents.1773314609.WellsFargo.1791860.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c83f3c3b8c8f84327b94b5c59d67fa0e07810b00d4efb9acf5be38ad32f074ca
3
+ size 424
logs/text2image-fine-tune/events.out.tfevents.1773328547.WellsFargo.2198663.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:559c65099e600c001f6bf110ad822c7c6c529d3063e9d13b2a07ae1316f70c9b
3
+ size 48961
logs/text2image-fine-tune/events.out.tfevents.1773341258.WellsFargo.2566051.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85a558ca11e1a12545f17715581b085c9d62448a79eae92f94f3efd1961d1744
3
+ size 88
logs/text2image-fine-tune/events.out.tfevents.1773341453.WellsFargo.2572900.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d434b2dbda3026d30505e05ffa497714d69b609668ca259d6432c40acd5ddde9
3
+ size 7164
logs/text2image-fine-tune/events.out.tfevents.1773343021.WellsFargo.2608126.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50bfbe6fa42adf0fbfbfc78c63a947aff0f662a5522dd88d95e6747dd9aadd5a
3
+ size 1033578
logs/text2image-fine-tune/events.out.tfevents.1773952929.WellsFargo.1798694.0 ADDED
File without changes
logs/text2image-fine-tune/events.out.tfevents.1773961364.WellsFargo.1983485.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ae4d9883a9edbd250e88e3371552fc8b33c9de05ca2a8c5a21ec1fddcc32976
3
+ size 88
logs/text2image-fine-tune/events.out.tfevents.1773962083.WellsFargo.2002346.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:925a095daf8dd18755570f4ccb8780a46f529bfd8d6e5b654257d903d2e5c7ae
3
+ size 88
logs/text2image-fine-tune/events.out.tfevents.1774001463.WellsFargo.2847786.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26f0609b0fcec0cd7b8d39df0e85602f8785563463a4b50320ba0a8b1dc41e59
3
+ size 250088
logs/text2image-fine-tune/events.out.tfevents.1774077639.WellsFargo.1025630.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86da872309a4428cc176d5dfc25d25aa68d0fdc051ecddc065b4ff5f3ae8ae37
3
+ size 250088
model_index.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableDiffusionPipeline",
3
+ "_diffusers_version": "0.38.0.dev0",
4
+ "_name_or_path": "stable-diffusion-v1-5/stable-diffusion-v1-5",
5
+ "feature_extractor": [
6
+ "transformers",
7
+ "CLIPImageProcessor"
8
+ ],
9
+ "image_encoder": [
10
+ null,
11
+ null
12
+ ],
13
+ "requires_safety_checker": true,
14
+ "safety_checker": [
15
+ "stable_diffusion",
16
+ "StableDiffusionSafetyChecker"
17
+ ],
18
+ "scheduler": [
19
+ "diffusers",
20
+ "PNDMScheduler"
21
+ ],
22
+ "text_encoder": [
23
+ "transformers",
24
+ "CLIPTextModel"
25
+ ],
26
+ "tokenizer": [
27
+ "transformers",
28
+ "CLIPTokenizer"
29
+ ],
30
+ "unet": [
31
+ "diffusers",
32
+ "UNet2DConditionModel"
33
+ ],
34
+ "vae": [
35
+ "diffusers",
36
+ "AutoencoderKL"
37
+ ]
38
+ }
remove_ckpts.sh ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ rm -rf checkpoint-500
2
+ rm -rf checkpoint-2000
3
+ rm -rf checkpoint-2500
4
+ rm -rf checkpoint-3000
5
+ rm -rf checkpoint-3500
6
+ rm -rf checkpoint-4000
7
+ rm -rf checkpoint-4500
8
+ rm -rf checkpoint-5000
9
+ rm -rf checkpoint-5500
10
+ rm -rf checkpoint-6000
11
+ rm -rf checkpoint-6500
12
+ rm -rf checkpoint-7000
13
+ rm -rf checkpoint-7500
14
+ rm -rf checkpoint-8000
15
+ rm -rf checkpoint-8500
16
+ rm -rf checkpoint-9000
17
+ rm -rf checkpoint-9500
safety_checker/config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "StableDiffusionSafetyChecker"
4
+ ],
5
+ "dtype": "float32",
6
+ "initializer_factor": 1.0,
7
+ "logit_scale_init_value": 2.6592,
8
+ "model_type": "clip",
9
+ "projection_dim": 768,
10
+ "text_config": {
11
+ "attention_dropout": 0.0,
12
+ "dropout": 0.0,
13
+ "dtype": "float32",
14
+ "hidden_act": "quick_gelu",
15
+ "hidden_size": 768,
16
+ "initializer_factor": 1.0,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "layer_norm_eps": 1e-05,
20
+ "max_position_embeddings": 77,
21
+ "model_type": "clip_text_model",
22
+ "num_attention_heads": 12,
23
+ "num_hidden_layers": 12,
24
+ "projection_dim": 512,
25
+ "vocab_size": 49408
26
+ },
27
+ "transformers_version": "4.56.1",
28
+ "vision_config": {
29
+ "attention_dropout": 0.0,
30
+ "dropout": 0.0,
31
+ "dtype": "float32",
32
+ "hidden_act": "quick_gelu",
33
+ "hidden_size": 1024,
34
+ "image_size": 224,
35
+ "initializer_factor": 1.0,
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": 4096,
38
+ "layer_norm_eps": 1e-05,
39
+ "model_type": "clip_vision_model",
40
+ "num_attention_heads": 16,
41
+ "num_channels": 3,
42
+ "num_hidden_layers": 24,
43
+ "patch_size": 14,
44
+ "projection_dim": 512
45
+ }
46
+ }
safety_checker/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb351a5ded815c3ff744968ad9c6b218d071b9d313d04f35e813b84b4c0ffde8
3
+ size 1215979664