configs for yolo

src/configs/algo_config.py

@@ -18,10 +18,10 @@
 
 traditional_fl = {
     "algo": "fedavg",
-    "exp_id": "no_mixed_precision_more_users",
+    "exp_id": "test_modular_yolo",
     "exp_type": "test",
     # Learning setup
-    "epochs": 1000,
+    "epochs": 10,
     "model": "yolo",
     "model_lr": 1e-5,
     "batch_size": 8,

src/configs/sys_config.py

@@ -20,17 +20,17 @@
 }
 
 object_detect_system_config = {
-    "num_users": 5,
+    "num_users": 1,
     "experiment_path": "./experiments/",
     "dset": "pascal",
     "dump_dir": "./expt_dump/",
     "dpath": "./datasets/pascal/VOCdevkit/VOC2012/",
-    "seed": 31,
+    "seed": 37,
     # node_0 is a server currently
     # The device_ids dictionary depicts the GPUs on which the nodes reside.
     # For a single-GPU environment, the config will look as follows (as it follows a 0-based indexing):
-    "device_ids": {"node_0": [1], "node_1": [2], "node_2": [3], "node_3": [4], "node_4": [5], "node_5": [7]},
-    "samples_per_user": 1000, #TODO: To model scenarios where different users have different number of samples
+    "device_ids": {"node_0": [1], "node_1": [2]},
+    "samples_per_user": 100, #TODO: To model scenarios where different users have different number of samples
     # we need to make this a dictionary with user_id as key and number of samples as value
     "train_label_distribution": "iid",
     "test_label_distribution": "iid",