Update demo

Author: lizekai-richard

configs/Demo_Hard_Label.yaml

@@ -1,7 +1,18 @@
+
+# real data
 dataset: "CIFAR10"
 real_data_path: "./dataset/"
+custom_val_trans: None
+
+# synthetic data
 ipc: 10
+im_size: (32, 32)
+
+# agent model
 model_name: "ConvNet-3"
+use_torchvision: False
+
+# data augmentation
 data_aug_func: "dsa"
 aug_params: {
   "prob_flip": 0.5, 
@@ -13,16 +24,20 @@ aug_params: {
   "ratio_crop_pad": 0.125, 
   "ratio_cutout": 0.5
 }
+use_zca: False
+
+# training specifics
 optimizer: "sgd"
 lr_scheduler: "step"
 weight_decay: 0.0005
 momentum: 0.9
 num_eval: 5
-im_size: (32, 32)
 num_epochs: 1000
-use_zca: False
-batch_size: 256
+syn_batch_size: 128
+real_batch_size: 256
 default_lr: 0.01
 num_workers: 4
-save_path: "./results/my_method_hard_label_scores.csv"
-device: "cuda"
+device: "cuda"
+
+# save path
+save_path: "./results/my_method_hard_label_scores.csv"

configs/Demo_Soft_Label.yaml

@@ -1,7 +1,19 @@
+# real data
 dataset: "CIFAR10"
 real_data_path: "./dataset/"
+custom_val_trans: None
+
+# synthetic data
 ipc: 10
+im_size: (32, 32)
+
+# agent model
 model_name: "ConvNet-3"
+stu_use_torchvision: False
+tea_use_torchvision: False
+teacher_dir: "./teacher_models"
+
+# data augmentation
 data_aug_func: "dsa"
 aug_params: {
     "prob_flip": 0.5,
@@ -13,19 +25,25 @@ aug_params: {
     "ratio_crop_pad": 0.125,
     "ratio_cutout": 0.5
 }
+use_zca: True
+
+# soft label settings
 soft_label_mode: "S"
 soft_label_criterion: "sce"
+temperature: 1.0
+
+# training specifics
 optimizer: "sgd"
 lr_scheduler: "step"
-temperature: 20.0
 weight_decay: 0.0005
 momentum: 0.9
 num_eval: 5
-im_size: (32, 32)
 num_epochs: 1000
-use_zca: True
-batch_size: 256
 default_lr: 0.01
 num_workers: 4
-save_path: "./results/my_method_soft_label_scores.csv"
 device: "cuda"
+syn_batch_size: 128
+real_batch_size: 256
+
+# save path
+save_path: "./results/my_method_soft_label_scores.csv"

demo_hard.py

@@ -4,14 +4,14 @@
 from dd_ranking.config import Config
 
 
-"""Use config file to specify the parameters (Recommended)"""
+""" Use config file to specify the arguments (Recommended) """
 config = Config.from_file("./configs/Demo_Hard_Label.yaml")
 convd3_hard_obj = Hard_Label_Objective_Metrics(config)
 syn_images = torch.load(os.path.join("./DC/CIFAR10/IPC10/", f"images.pt"), map_location='cpu')
 print(convd3_hard_obj.compute_metrics(syn_images, syn_lr=0.01))
 
 
-"""Use hardcoded parameters"""
+""" Use keyword arguments """
 device = "cuda"
 method_name = "DM"                    # Specify your method name
 ipc = 10                              # Specify your IPC
@@ -51,6 +51,10 @@
     im_size=im_size,
     num_epochs=1000,
     num_workers=4,
+    use_torchvision=False,
+    syn_batch_size=128,
+    real_batch_size=256,
+    custom_val_trans=None,
     device=device,
     save_path=save_path
 )

demo_soft.py

@@ -4,15 +4,16 @@
 from dd_ranking.config import Config
 
 
-"""Use config file to specify the parameters (Recommended)"""
+""" Use config file to specify the arguments (Recommended) """
 config = Config.from_file("./configs/Demo_Soft_Label.yaml")
 convd3_soft_obj = Soft_Label_Objective_Metrics(config)
 syn_images = torch.load(os.path.join(syn_data_dir, f"images.pt"), map_location='cpu')
 soft_labels = torch.load(os.path.join(syn_data_dir, f"labels.pt"), map_location='cpu')
-print(convd3_soft_obj.compute_metrics(syn_images, soft_labels, syn_lr=0.01))
+syn_lr = torch.load(os.path.join(syn_data_dir, f"lr.pt"), map_location='cpu')
+print(convd3_soft_obj.compute_metrics(syn_images, soft_labels, syn_lr=syn_lr))
 
 
-"""Use hardcoded parameters"""
+""" Use keyword arguments """
 device = "cuda"
 method_name = "DATM"                    # Specify your method name
 ipc = 10                                # Specify your IPC
@@ -54,6 +55,12 @@
     im_size=im_size,
     num_epochs=1000,
     num_workers=4,
+    stu_use_torchvision=False,
+    tea_use_torchvision=False,
+    custom_val_trans=None,
+    syn_batch_size=128,
+    real_batch_size=256,
+    teacher_dir='./teacher_models',
     device=device,
     save_path=save_path
 )