diff --git a/configs/mainmodel2.yaml b/configs/mainmodel2.yaml
index 7806dd2..2ded6fd 100644
--- a/configs/mainmodel2.yaml
+++ b/configs/mainmodel2.yaml
@@ -1,7 +1,7 @@
 model:
   name: mainmodel2
   config:
-    meta_head: true
+    meta_head: false
     nonhrv_channels: 
       # - IR_016
       - VIS008
@@ -22,7 +22,7 @@ eval:
 data:
   num_workers: 16
   root: /data/climatehack/
-  train_start_date: 2021-01-01 00:00:00
+  train_start_date: 2020-01-01 00:00:00
   train_end_date: 2022-01-01 00:00:00
   # subsets are randomly sampled from the full dataset using a seed of 21
   # 0 means use all data
diff --git a/data/random_data.py b/data/random_data.py
index 05d368c..fb61403 100644
--- a/data/random_data.py
+++ b/data/random_data.py
@@ -18,8 +18,8 @@
 
 # Think about whether all channels need to be flipped together or not
 TRAIN_TRANSFORM = transforms.Compose([
-    # transforms.RandomErasing(p=0.25, scale=(0.02, 0.33), ratio=(0.3, 3.3), value=0, inplace=True),
-    # transforms.RandomHorizontalFlip(p=0.5),
+    transforms.RandomErasing(p=0.25, scale=(0.02, 0.33), ratio=(0.3, 3.3), value=0, inplace=True),
+    transforms.RandomHorizontalFlip(p=0.5),
     # # transforms.RandomVerticalFlip(p=0.5),
     # transforms.RandomApply([
     #     transforms.GaussianBlur(kernel_size=3, sigma=(0.1, 2.0)),
diff --git a/main.py b/main.py
index 6f9b3a1..1158d61 100644
--- a/main.py
+++ b/main.py
@@ -50,7 +50,14 @@ def _eval(dataloader, model, criterion=nn.L1Loss(), preds_save_path=None, ground
             pv_features = pv_features.to(device, dtype=torch.float)
             pv_targets = pv_targets.to(device, dtype=torch.float)
 
-            predictions = model(pv_features, features)
+            predictions0 = model(pv_features, features)
+
+            features[NONHRV.VIS008] = features[NONHRV.VIS008].flip(-1)
+
+            predictions1 = model(pv_features, features)
+
+            predictions = (predictions0 + predictions1) / 2
+            # predictions = predictions0
 
             gt[i * dataloader.batch_size: (i + 1) * dataloader.batch_size] = pv_targets.cpu().numpy()
             preds[i * dataloader.batch_size: (i + 1) * dataloader.batch_size] = predictions.cpu().numpy()
diff --git a/submission/models/models.py b/submission/models/models.py
index 045171e..6d570ad 100644
--- a/submission/models/models.py
+++ b/submission/models/models.py
@@ -87,9 +87,9 @@ def __init__(self, config) -> None:
 
         self.meta_and_pv = MetaAndPv()
 
-        self.nonhrv_backbones = nn.ModuleList([models.resnet18() for i in range(len(self.nonhrv_channels))])
+        self.nonhrv_backbones = nn.ModuleList([models.resnext50_32x4d() for i in range(len(self.nonhrv_channels))])
         for bone in self.nonhrv_backbones:
-            bone.conv1 = nn.Conv2d(12, 64, kernel_size=7, stride=2, padding=3, bias=False)
+            bone.conv1 = nn.Conv2d(6, 64, kernel_size=7, stride=2, padding=3, bias=True)
             bone.fc = nn.Identity()
 
         self.weather_backbones = nn.ModuleList([models.resnet18() for i in range(len(self.weather_channels))])
@@ -99,20 +99,21 @@ def __init__(self, config) -> None:
 
         if self.meta_head:
             self.linear1 = nn.Linear(
-                    len(self.nonhrv_channels) * 512 +
+                    len(self.nonhrv_channels) * 512 * 4 +
                     len(self.weather_channels) * 512 +
                     self.meta_and_pv.output_dim,
                 256)
         else:
             self.linear1 = nn.Linear(
-                    len(self.nonhrv_channels) * 512 +
+                    len(self.nonhrv_channels) * 512 * 4 +
                     len(self.weather_channels) * 512 +
                     12 + 12,
-                256)
+                384, bias=True)
 
-        self.linear2 = nn.Linear(256, 256, bias=True)
-        self.linear3 = nn.Linear(256, 48)
-        self.r = nn.ReLU(inplace=True)
+        self.linear2 = nn.Linear(384, 384)
+        self.dropout = nn.Dropout(0.25)
+        self.linear3 = nn.Linear(384, 48)
+        self.r = nn.GELU()
 
     @property
     def required_features(self):
@@ -120,7 +121,7 @@ def required_features(self):
 
     def forward(self, pv, features):
         if self.nonhrv_channels:
-            feat1 = torch.concat([self.nonhrv_backbones[i](features[key]) for i, key in enumerate(self.nonhrv_channels)], dim=-1)
+            feat1 = torch.concat([self.nonhrv_backbones[i](features[key][:, 1::2]) for i, key in enumerate(self.nonhrv_channels)], dim=-1)
         else:
             feat1 = torch.Tensor([]).to("cuda")
 
@@ -140,6 +141,7 @@ def forward(self, pv, features):
         all_feat = torch.concat([feat1, feat2, feat3], dim=-1)
 
         x = self.r(self.linear1(all_feat))
+        x = self.dropout(x)
         x = self.r(self.linear2(x))
         x = torch.sigmoid(self.linear3(x))
 
diff --git a/submission/run.py b/submission/run.py
index 04c00c7..804cc2c 100644
--- a/submission/run.py
+++ b/submission/run.py
@@ -101,7 +101,16 @@ def predict(self, features: h5py.File):
                 # site_features = util.site_normalize(torch.from_numpy(site_features).to(device))
                 input_data = util.dict_to_device(input_data, device)
 
-                yield self.model(pv, input_data).cpu()
+                predictions0 = self.model(pv, input_data)
+
+                input_data[NONHRV.VIS008] = input_data[NONHRV.VIS008].flip(-1)
+
+                predictions1 = self.model(pv, input_data)
+
+                predictions = (predictions0 + predictions1) / 2
+
+                # yield self.model(pv, input_data).cpu()
+                yield predictions.cpu()
 
 
 if __name__ == "__main__":