Upload config.json with huggingface_hub

config.json

@@ -0,0 +1,119 @@
+{
+  "save_path": "saved_fixcursor_lr8e5",
+  "model": {
+    "base_learning_rate": 8e-05,
+    "target": "latent_diffusion.ldm.models.diffusion.ddpm.LatentDiffusion",
+    "params": {
+      "linear_start": 0.0015,
+      "linear_end": 0.0195,
+      "num_timesteps_cond": 1,
+      "log_every_t": 200,
+      "timesteps": 1000,
+      "first_stage_key": "image",
+      "cond_stage_key": "action_",
+      "scheduler_sampling_rate": 0.0,
+      "hybrid_key": "c_concat",
+      "image_size": 64,
+      "channels": 3,
+      "cond_stage_trainable": true,
+      "conditioning_key": "hybrid",
+      "monitor": "val/loss_simple_ema",
+      "unet_config": {
+        "target": "latent_diffusion.ldm.modules.diffusionmodules.openaimodel.UNetModel",
+        "params": {
+          "image_size": 64,
+          "in_channels": 24,
+          "out_channels": 3,
+          "model_channels": 192,
+          "attention_resolutions": [
+            8,
+            4,
+            2
+          ],
+          "num_res_blocks": 2,
+          "channel_mult": [
+            1,
+            2,
+            3,
+            5
+          ],
+          "num_head_channels": 32,
+          "use_spatial_transformer": true,
+          "transformer_depth": 1,
+          "context_dim": 640
+        }
+      },
+      "first_stage_config": {
+        "target": "latent_diffusion.ldm.models.autoencoder.VQModelInterface",
+        "params": {
+          "embed_dim": 3,
+          "n_embed": 8192,
+          "monitor": "val/rec_loss",
+          "ddconfig": {
+            "double_z": false,
+            "z_channels": 3,
+            "resolution": 256,
+            "in_channels": 3,
+            "out_ch": 3,
+            "ch": 128,
+            "ch_mult": [
+              1,
+              2,
+              4
+            ],
+            "num_res_blocks": 2,
+            "attn_resolutions": [],
+            "dropout": 0.0
+          },
+          "lossconfig": {
+            "target": "torch.nn.Identity"
+          }
+        }
+      },
+      "cond_stage_config": {
+        "target": "latent_diffusion.ldm.modules.encoders.modules.BERTEmbedder",
+        "params": {
+          "n_embed": 640,
+          "n_layer": 32
+        }
+      }
+    }
+  },
+  "data": {
+    "target": "data.data_processing.datasets.DataModule",
+    "params": {
+      "batch_size": 32,
+      "num_workers": 1,
+      "wrap": false,
+      "shuffle": true,
+      "drop_last": true,
+      "pin_memory": true,
+      "prefetch_factor": 2,
+      "persistent_workers": true,
+      "train": {
+        "target": "data.data_processing.datasets.ActionsData",
+        "params": {
+          "data_csv_path": "train_dataset/train_dataset_14frames.csv"
+        }
+      },
+      "validation": {
+        "target": "data.data_processing.datasets.ActionsData",
+        "params": {
+          "data_csv_path": "train_dataset/train_dataset_14frames.csv"
+        }
+      }
+    }
+  },
+  "lightning": {
+    "trainer": {
+      "benchmark": false,
+      "max_epochs": 3,
+      "limit_val_batches": 0,
+      "accelerator": "gpu",
+      "gpus": 1,
+      "accumulate_grad_batches": 4,
+      "gradient_clip_val": 1,
+      "checkpoint_callback": true
+    }
+  }
+}