Upload model

modeling_spice_cnn.py

@@ -14,24 +14,32 @@ class SpiceCNNModelForImageClassification(PreTrainedModel):
             nn.Conv2d(
                 config.in_channels,
                 32,
-                kernel_size=config.kernel_size,
-                stride=config.stride,
-                padding=config.padding,
+                kernel_size=3,
             ),
             nn.ReLU(),
-            nn.MaxPool2d(kernel_size=config.pooling_size),
-            nn.Conv2d(
-                32,
-                64,
-                kernel_size=config.kernel_size,
-                stride=config.stride,
-                padding=config.padding,
-            ),
+            nn.BatchNorm2d(32),
+            nn.Conv2d(32, 32, kernel_size=3),
             nn.ReLU(),
-            nn.MaxPool2d(kernel_size=config.pooling_size),
-            nn.Flatten(),
-            nn.Linear(7 * 7 * 64, 128),
+            nn.BatchNorm2d(32),
+            nn.Conv2d(32, 32, kernel_size=5, stride=2),
             nn.ReLU(),
+            nn.Dropout(0.4),
+
+            nn.Conv2d(32, 64, kernel_size=3),
+            nn.ReLU(),
+            nn.BatchNorm2d(64),
+            nn.Conv2d(64, 64, kernel_size=3),
+            nn.ReLU(),
+            nn.BatchNorm2d(64),
+            nn.Conv2d(64, 64, kernel_size=5, stride=2),
+            nn.ReLU(),
+            nn.BatchNorm2d(64),
+            nn.Dropout(0.4),
+            
+            nn.Flatten(),
+            nn.Linear(64 * 28 * 28, 128),
+            nn.BatchNorm1d(128),
+            nn.Dropout(0.4),
             nn.Linear(128, config.num_classes),
         ]
         self.model = nn.Sequential(*layers)

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e376b1a3eb5151032ae94a61eec980ba20ce42cb3ba4699a3f98de9c106eda7
-size 1689227
+oid sha256:60d140c12a803582c4e3e7b0d2e52fbfb492477523541fa0ec719ce40b47358d
+size 26487547