Fix linear layer

cnn.py

@@ -52,7 +52,7 @@ class CNNetwork(nn.Module):
             nn.MaxPool2d(kernel_size=2)
         )
         self.flatten = nn.Flatten()
-        self.linear = nn.Linear(128 * 5 * 11, 10)
+        self.linear = nn.Linear(128 * 5 * 11, 3)
         self.softmax = nn.Softmax(dim=1)
 
     def forward(self, input_data):

notebooks/playground.ipynb

@@ -3,7 +3,7 @@
   {
    "cell_type": "code",
    "execution_count": 8,
-   "id": "aa1911f5",
+   "id": "9db7bd27",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -14,7 +14,7 @@
   {
    "cell_type": "code",
    "execution_count": 10,
-   "id": "67260d6a",
+   "id": "72b076a5",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -25,7 +25,7 @@
   {
    "cell_type": "code",
    "execution_count": 86,
-   "id": "45a193b9",
+   "id": "391c8ebe",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -38,7 +38,7 @@
   {
    "cell_type": "code",
    "execution_count": 85,
-   "id": "4e2c5825",
+   "id": "0f0b166a",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -49,7 +49,7 @@
   {
    "cell_type": "code",
    "execution_count": 78,
-   "id": "1b14521b",
+   "id": "b690f559",
    "metadata": {},
    "outputs": [
     {
@@ -71,7 +71,7 @@
   {
    "cell_type": "code",
    "execution_count": 109,
-   "id": "d0d6fcd7",
+   "id": "5b4cac66",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -87,7 +87,7 @@
   {
    "cell_type": "code",
    "execution_count": 110,
-   "id": "e39172ab",
+   "id": "55928782",
    "metadata": {},
    "outputs": [
     {
@@ -108,7 +108,7 @@
   {
    "cell_type": "code",
    "execution_count": 111,
-   "id": "ef5746b3",
+   "id": "296fc1d0",
    "metadata": {},
    "outputs": [
     {
@@ -136,7 +136,7 @@
   {
    "cell_type": "code",
    "execution_count": 112,
-   "id": "a4f08bd4",
+   "id": "b921ef42",
    "metadata": {},
    "outputs": [
     {
@@ -156,36 +156,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 113,
-   "id": "2b58063c",
+   "execution_count": 144,
+   "id": "83671781",
    "metadata": {},
-   "outputs": [
-    {
-     "ename": "RuntimeError",
-     "evalue": "mat1 and mat2 shapes cannot be multiplied (2x2560 and 7040x10)",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mRuntimeError\u001b[0m                              Traceback (most recent call last)",
-      "Cell \u001b[0;32mIn[113], line 2\u001b[0m\n\u001b[1;32m      1\u001b[0m cnn \u001b[38;5;241m=\u001b[39m CNNetwork()\n\u001b[0;32m----> 2\u001b[0m \u001b[43msummary\u001b[49m\u001b[43m(\u001b[49m\u001b[43mcnn\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m64\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m44\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m\n",
-      "File \u001b[0;32m~/anaconda3/envs/void/lib/python3.9/site-packages/torchsummary/torchsummary.py:72\u001b[0m, in \u001b[0;36msummary\u001b[0;34m(model, input_size, batch_size, device)\u001b[0m\n\u001b[1;32m     68\u001b[0m model\u001b[38;5;241m.\u001b[39mapply(register_hook)\n\u001b[1;32m     70\u001b[0m \u001b[38;5;66;03m# make a forward pass\u001b[39;00m\n\u001b[1;32m     71\u001b[0m \u001b[38;5;66;03m# print(x.shape)\u001b[39;00m\n\u001b[0;32m---> 72\u001b[0m \u001b[43mmodel\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mx\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m     74\u001b[0m \u001b[38;5;66;03m# remove these hooks\u001b[39;00m\n\u001b[1;32m     75\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m h \u001b[38;5;129;01min\u001b[39;00m hooks:\n",
-      "File \u001b[0;32m~/anaconda3/envs/void/lib/python3.9/site-packages/torch/nn/modules/module.py:1501\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1496\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m   1497\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m   1498\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[1;32m   1499\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m   1500\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1501\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1502\u001b[0m \u001b[38;5;66;03m# Do not call functions when jit is used\u001b[39;00m\n\u001b[1;32m   1503\u001b[0m full_backward_hooks, non_full_backward_hooks \u001b[38;5;241m=\u001b[39m [], []\n",
-      "File \u001b[0;32m~/ml-sandbox/VoID/notebooks/../cnn.py:64\u001b[0m, in \u001b[0;36mCNNetwork.forward\u001b[0;34m(self, input_data)\u001b[0m\n\u001b[1;32m     62\u001b[0m x \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mconv4(x)\n\u001b[1;32m     63\u001b[0m x \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mflatten(x)\n\u001b[0;32m---> 64\u001b[0m logits \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mlinear\u001b[49m\u001b[43m(\u001b[49m\u001b[43mx\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m     65\u001b[0m predictions \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msoftmax(logits)\n\u001b[1;32m     66\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m predictions\n",
-      "File \u001b[0;32m~/anaconda3/envs/void/lib/python3.9/site-packages/torch/nn/modules/module.py:1538\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1535\u001b[0m     bw_hook \u001b[38;5;241m=\u001b[39m hooks\u001b[38;5;241m.\u001b[39mBackwardHook(\u001b[38;5;28mself\u001b[39m, full_backward_hooks, backward_pre_hooks)\n\u001b[1;32m   1536\u001b[0m     args \u001b[38;5;241m=\u001b[39m bw_hook\u001b[38;5;241m.\u001b[39msetup_input_hook(args)\n\u001b[0;32m-> 1538\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1539\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks:\n\u001b[1;32m   1540\u001b[0m     \u001b[38;5;28;01mfor\u001b[39;00m hook_id, hook \u001b[38;5;129;01min\u001b[39;00m (\n\u001b[1;32m   1541\u001b[0m         \u001b[38;5;241m*\u001b[39m_global_forward_hooks\u001b[38;5;241m.\u001b[39mitems(),\n\u001b[1;32m   1542\u001b[0m         \u001b[38;5;241m*\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks\u001b[38;5;241m.\u001b[39mitems(),\n\u001b[1;32m   1543\u001b[0m     ):\n",
-      "File \u001b[0;32m~/anaconda3/envs/void/lib/python3.9/site-packages/torch/nn/modules/linear.py:114\u001b[0m, in \u001b[0;36mLinear.forward\u001b[0;34m(self, input)\u001b[0m\n\u001b[1;32m    113\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mforward\u001b[39m(\u001b[38;5;28mself\u001b[39m, \u001b[38;5;28minput\u001b[39m: Tensor) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Tensor:\n\u001b[0;32m--> 114\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mF\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mlinear\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mweight\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mbias\u001b[49m\u001b[43m)\u001b[49m\n",
-      "\u001b[0;31mRuntimeError\u001b[0m: mat1 and mat2 shapes cannot be multiplied (2x2560 and 7040x10)"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "cnn = CNNetwork()\n",
-    "summary(cnn, (1, 64, 44))"
+    "# summary(cnn, (1, 64, 44))"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 114,
-   "id": "70264920",
+   "id": "5a12b59f",
    "metadata": {},
    "outputs": [
     {
@@ -206,7 +189,7 @@
   {
    "cell_type": "code",
    "execution_count": 115,
-   "id": "9383e1bb",
+   "id": "4845de38",
    "metadata": {},
    "outputs": [
     {
@@ -227,7 +210,7 @@
   {
    "cell_type": "code",
    "execution_count": 116,
-   "id": "6d0cb06a",
+   "id": "51c03aaf",
    "metadata": {},
    "outputs": [
     {
@@ -255,7 +238,7 @@
   {
    "cell_type": "code",
    "execution_count": 117,
-   "id": "e07e35f7",
+   "id": "ba6b88ee",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -266,7 +249,7 @@
   {
    "cell_type": "code",
    "execution_count": 107,
-   "id": "ef2eddad",
+   "id": "a6046ccf",
    "metadata": {},
    "outputs": [
     {
@@ -284,10 +267,176 @@
     "now.strftime(\"%Y%m%d_%H%M%S\")"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 145,
+   "id": "d7789a04",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<All keys matched successfully>"
+      ]
+     },
+     "execution_count": 145,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "cnn.load_state_dict(torch.load(\"../models/void_20230512_225714.pth\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 151,
+   "id": "a6030b42",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "x, y = dataset[10]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 152,
+   "id": "78352b6b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "labels = dataset._labels"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 153,
+   "id": "b8cc2162",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "input = x.unsqueeze_(0) "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 154,
+   "id": "845ecea4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def predict(model, input, target, class_mapping):\n",
+    "    model.eval()\n",
+    "    with torch.no_grad():\n",
+    "        predictions = model(input)\n",
+    "        print(predictions)\n",
+    "        predicted_index = predictions[0].argmax(0)\n",
+    "        predicted = class_mapping[predicted_index]\n",
+    "        expected = class_mapping[target]\n",
+    "    return predicted, expected"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 155,
+   "id": "eb8d1e55",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "tensor([[1.0000e+00, 1.3728e-20, 2.8026e-44]])\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "('aman', 'aman')"
+      ]
+     },
+     "execution_count": 155,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "predict(cnn, input, y, labels)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 156,
+   "id": "5d58683e",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "tensor([[[[0.0259, 0.1384, 0.0784,  ..., 0.0000, 0.0000, 0.0000],\n",
+       "          [0.0334, 0.1320, 0.0701,  ..., 0.0000, 0.0000, 0.0000],\n",
+       "          [0.0481, 0.0324, 0.0545,  ..., 0.0000, 0.0000, 0.0000],\n",
+       "          ...,\n",
+       "          [0.2665, 0.3647, 0.3147,  ..., 0.0000, 0.0000, 0.0000],\n",
+       "          [0.2710, 0.3796, 0.2160,  ..., 0.0000, 0.0000, 0.0000],\n",
+       "          [0.1950, 0.2607, 0.1905,  ..., 0.0000, 0.0000, 0.0000]]]])"
+      ]
+     },
+     "execution_count": 156,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "input"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 157,
+   "id": "b0af5b69",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "torch.Size([1, 1, 64, 157])"
+      ]
+     },
+     "execution_count": 157,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "input.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 158,
+   "id": "28c0768a",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "torch.Size([1, 1, 64, 157])"
+      ]
+     },
+     "execution_count": 158,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "x.shape"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "c665d0cf",
+   "id": "c5817d01",
    "metadata": {},
    "outputs": [],
    "source": []