Upload 58 files

.cache/huggingface/.gitignore

@@ -0,0 +1 @@
+*

.cache/huggingface/download/.gitattributes.metadata

@@ -0,0 +1,3 @@
+0dc214611dc58da03fb20ee8e4d47deb59f7fea0
+a6344aac8c09253b3b630fb776ae94478aa0275b
+1773846373.4656885

.cache/huggingface/download/README.md.metadata

@@ -0,0 +1,3 @@
+0dc214611dc58da03fb20ee8e4d47deb59f7fea0
+7292654f556a822b79e97ef676238903a401114f
+1773894212.5980058

.cache/huggingface/download/feature_extractor/preprocessor_config.json.metadata

@@ -0,0 +1,3 @@
+0dc214611dc58da03fb20ee8e4d47deb59f7fea0
+5294955ff7801083f720b34b55d0f1f51313c5c5
+1773846372.894359

.cache/huggingface/download/generation_config.json.metadata

@@ -0,0 +1,3 @@
+0dc214611dc58da03fb20ee8e4d47deb59f7fea0
+33825d8033baa729154aaec313e5893c3d3747c0
+1773846366.4987843

.cache/huggingface/download/model_index.json.metadata

@@ -0,0 +1,3 @@
+0dc214611dc58da03fb20ee8e4d47deb59f7fea0
+1fbe22a12d88bd0400b58a50bde90a71e4d40621
+1773846365.994845

.cache/huggingface/download/safety_checker/config.json.metadata

@@ -0,0 +1,3 @@
+0dc214611dc58da03fb20ee8e4d47deb59f7fea0
+be236c8f35b9d4dde6dfd5490be20e290ef822b6
+1773846366.1904252

.cache/huggingface/download/safety_checker/pytorch_model.bin.metadata

@@ -0,0 +1,3 @@
+0dc214611dc58da03fb20ee8e4d47deb59f7fea0
+193490b58ef62739077262e833bf091c66c29488058681ac25cf7df3d8190974
+1773847474.440043

.cache/huggingface/download/scheduler/scheduler_config.json.metadata

@@ -0,0 +1,3 @@
+0dc214611dc58da03fb20ee8e4d47deb59f7fea0
+9c382873d2b2bbcfe5a1d356098db239c905c229
+1773846366.3865142

.cache/huggingface/download/text_encoder/config.json.metadata

@@ -0,0 +1,3 @@
+0dc214611dc58da03fb20ee8e4d47deb59f7fea0
+9698f365ef341e65771781de1093d67a1f3a3bf3
+1773846366.9243197

.cache/huggingface/download/text_encoder/pytorch_model.bin.metadata

@@ -0,0 +1,3 @@
+0dc214611dc58da03fb20ee8e4d47deb59f7fea0
+be86b069fa04a2e52a7184c13f84fd2cbdbdb86f54914cc21fc597e0bb6386f7
+1773847169.862294

.cache/huggingface/download/tokenizer/added_tokens.json.metadata

@@ -0,0 +1,3 @@
+0dc214611dc58da03fb20ee8e4d47deb59f7fea0
+ff030f995a7f9be9483b19d955bef43631931f9e
+1773846368.0718708

.cache/huggingface/download/tokenizer/merges.txt.metadata

@@ -0,0 +1,3 @@
+0dc214611dc58da03fb20ee8e4d47deb59f7fea0
+76e821f1b6f0a9709293c3b6b51ed90980b3166b
+1773846368.869421

.cache/huggingface/download/tokenizer/special_tokens_map.json.metadata

@@ -0,0 +1,3 @@
+0dc214611dc58da03fb20ee8e4d47deb59f7fea0
+2c2130b544c0c5a72d5d00da071ba130a9800fb2
+1773846367.944107

.cache/huggingface/download/tokenizer/tokenizer_config.json.metadata

@@ -0,0 +1,3 @@
+0dc214611dc58da03fb20ee8e4d47deb59f7fea0
+e0bd623fa60aea1c308fb76cfa241be9a153901d
+1773846370.0398214

.cache/huggingface/download/tokenizer/vocab.json.metadata

@@ -0,0 +1,3 @@
+0dc214611dc58da03fb20ee8e4d47deb59f7fea0
+469be27c5c010538f845f518c4f5e8574c78f7c8
+1773846371.7449872

.cache/huggingface/download/unet/config.json.metadata

@@ -0,0 +1,3 @@
+0dc214611dc58da03fb20ee8e4d47deb59f7fea0
+9dd29801de8482c225cc5774bbdf5ee71cbfe4f6
+1773846371.7785661

.cache/huggingface/download/unet/diffusion_pytorch_model.bin.metadata

@@ -0,0 +1,3 @@
+0dc214611dc58da03fb20ee8e4d47deb59f7fea0
+d09deaf206e287f4b2aa5ae6036ebc94faa477059d3bcb97186276a4fc2643c2
+1773894530.9242246

.cache/huggingface/download/vae/config.json.metadata

@@ -0,0 +1,3 @@
+0dc214611dc58da03fb20ee8e4d47deb59f7fea0
+652db8e68fbf030ced4ed0a880fbf0ab03eff1f3
+1773846373.2987053

.cache/huggingface/download/vae/diffusion_pytorch_model.bin.metadata

@@ -0,0 +1,3 @@
+0dc214611dc58da03fb20ee8e4d47deb59f7fea0
+9cab9e6ef49532bd47bb0dbfa8f6adab999c2ee36a6c6d33791177018bddbe7a
+1773890901.9516609

README.md

@@ -0,0 +1,5 @@
+---
+license: mit
+---
+# GDCC-Generation Model Card
+GDCC is a detection data generation model fine-tuned from [GeoDiffusion](https://huggingface.co/KaiChen1998/geodiffusion-coco-stuff-256x256). This repo contains the GDCC checkpoint trained on **COCO-stuff** dataset under **256x256**. Check detailed usage in our [Github repo](https://github.com/NUST-Machine-Intelligence-Laboratory/GDCC).

feature_extractor/preprocessor_config.json

@@ -0,0 +1,20 @@
+{
+  "crop_size": 224,
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_resize": true,
+  "feature_extractor_type": "CLIPFeatureExtractor",
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "size": 224
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+ "dataset": "coco_stuff",
+ "num_bucket_per_side": [256, 256],
+ "width": 256,
+ "height": 256,
+ "prompt_template": "An image with {bbox}",
+ "cfg_scale": 4.0,
+ "num_inference_steps": 50,
+ "max_num_bbox": 18
+}

model_index.json

@@ -0,0 +1,32 @@
+{
+  "_class_name": "StableDiffusionPipeline",
+  "_diffusers_version": "0.4.1",
+  "feature_extractor": [
+    "transformers",
+    "CLIPFeatureExtractor"
+  ],
+  "safety_checker": [
+    "stable_diffusion",
+    "StableDiffusionSafetyChecker"
+  ],
+  "scheduler": [
+    "diffusers",
+    "PNDMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

safety_checker/config.json

@@ -0,0 +1,179 @@
+{
+  "_commit_hash": null,
+  "_name_or_path": "work_dirs/diffusion/stable-diffusion-v1-5/",
+  "architectures": [
+    "StableDiffusionSafetyChecker"
+  ],
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "clip",
+  "projection_dim": 768,
+  "text_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 77,
+    "min_length": 0,
+    "model_type": "clip_text_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.24.0",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "vocab_size": 49408
+  },
+  "text_config_dict": {
+    "hidden_size": 768,
+    "intermediate_size": 3072,
+    "num_attention_heads": 12,
+    "num_hidden_layers": 12
+  },
+  "torch_dtype": "float32",
+  "transformers_version": null,
+  "vision_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 224,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "clip_vision_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_hidden_layers": 24,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 14,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.24.0",
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "vision_config_dict": {
+    "hidden_size": 1024,
+    "intermediate_size": 4096,
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "patch_size": 14
+  }
+}

safety_checker/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:193490b58ef62739077262e833bf091c66c29488058681ac25cf7df3d8190974
+size 1216061799

scheduler/scheduler_config.json

@@ -0,0 +1,12 @@
+{
+  "_class_name": "PNDMScheduler",
+  "_diffusers_version": "0.4.1",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "num_train_timesteps": 1000,
+  "set_alpha_to_one": false,
+  "skip_prk_steps": true,
+  "steps_offset": 1,
+  "trained_betas": null
+}

text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "work_dirs/diffusion/stable-diffusion-v1-5/",
+  "architectures": [
+    "CLIPTextModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "quick_gelu",
+  "hidden_size": 768,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "projection_dim": 768,
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0",
+  "vocab_size": 114944
+}

text_encoder/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be86b069fa04a2e52a7184c13f84fd2cbdbdb86f54914cc21fc597e0bb6386f7
+size 693634679