Skip to content

B
book

PaddlePaddle / book

通知 16
Star 4
Fork 0
B
book

前往新版Gitcode，体验更适合开发者的 AI 搜索 >>

未验证 提交 1ede63d1 编写于 作者: C Chen Long 提交者： GitHub
浏览文件
操作

Fix style (#891) 

* fix_some_wrongs

* fix_logs
上级 d0363589
隐藏空白更改
内联 并排
Showing with 45 addition and 101 deletion
paddle2.0_docs/n_gram_model/n_gram_model.ipynb
浏览文件 @ 1ede63d1
......@@ -21,7 +21,7 @@
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": 23,
"metadata": {},
"outputs": [
{
......@@ -30,7 +30,7 @@
"'0.0.0'"
]
},
"execution_count": 1,
"execution_count": 23,
"metadata": {},
"output_type": "execute_result"
}
......@@ -51,22 +51,23 @@
},
{
"cell_type": "code",
"execution_count": 4,
"execution_count": 24,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"--2020-09-08 19:07:26-- https://ocw.mit.edu/ans7870/6/6.006/s08/lecturenotes/files/t8.shakespeare.txt\n",
"正在连接 172.19.57.45:3128... 已连接。\n",
"已发出 Proxy 请求，正在等待回应... 200 OK\n",
"--2020-09-09 14:58:26-- https://ocw.mit.edu/ans7870/6/6.006/s08/lecturenotes/files/t8.shakespeare.txt\n",
"正在解析主机 ocw.mit.edu (ocw.mit.edu)... 151.101.110.133\n",
"正在连接 ocw.mit.edu (ocw.mit.edu)|151.101.110.133|:443... 已连接。\n",
"已发出 HTTP 请求，正在等待回应... 200 OK\n",
"长度：5458199 (5.2M) [text/plain]\n",
"正在保存至: “t8.shakespeare.txt”\n",
"\n",
"t8.shakespeare.txt 100%[===================>] 5.21M 862KB/s 用时 7.1s \n",
"t8.shakespeare.txt 100%[===================>] 5.21M 94.1KB/s 用时 70s \n",
"\n",
"2020-09-08 19:07:34 (755 KB/s) - 已保存 “t8.shakespeare.txt” [5458199/5458199])\n",
"2020-09-09 14:59:38 (75.7 KB/s) - 已保存 “t8.shakespeare.txt” [5458199/5458199])\n",
"\n"
]
}
......@@ -77,7 +78,7 @@
},
{
"cell_type": "code",
"execution_count": 5,
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
......@@ -87,7 +88,7 @@
},
{
"cell_type": "code",
"execution_count": 6,
"execution_count": 5,
"metadata": {},
"outputs": [
{
......@@ -117,7 +118,7 @@
},
{
"cell_type": "code",
"execution_count": 7,
"execution_count": 6,
"metadata": {},
"outputs": [
{
......@@ -136,7 +137,7 @@
},
{
"cell_type": "code",
"execution_count": 8,
"execution_count": 7,
"metadata": {},
"outputs": [
{
......@@ -165,7 +166,7 @@
},
{
"cell_type": "code",
"execution_count": 9,
"execution_count": 8,
"metadata": {},
"outputs": [
{
......@@ -196,7 +197,7 @@
},
{
"cell_type": "code",
"execution_count": 11,
"execution_count": 12,
"metadata": {},
"outputs": [],
"source": [
......@@ -218,7 +219,7 @@
" def __len__(self):\n",
" return len(self.tuple_data)\n",
"train_dataset = TrainDataset(trigram)\n",
"train_loader = paddle.io.DataLoader(train_dataset,places=paddle.fluid.cpu_places(), return_list=True,\n",
"train_loader = paddle.io.DataLoader(train_dataset,places=paddle.CPUPlace(), return_list=True,\n",
" shuffle=True, batch_size=batch_size, drop_last=True)"
]
},
......@@ -232,7 +233,7 @@
},
{
"cell_type": "code",
"execution_count": 14,
"execution_count": 13,
"metadata": {},
"outputs": [],
"source": [
......@@ -264,90 +265,33 @@
},
{
"cell_type": "code",
"execution_count": 16,
"execution_count": 19,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"epoch: 0, batch_id: 0, loss is: [10.252116]\n",
"epoch: 0, batch_id: 100, loss is: [7.078615]\n",
"epoch: 0, batch_id: 200, loss is: [7.0399227]\n",
"epoch: 0, batch_id: 300, loss is: [6.981158]\n",
"epoch: 0, batch_id: 400, loss is: [7.3663793]\n",
"epoch: 0, batch_id: 500, loss is: [6.535556]\n",
"epoch: 0, batch_id: 600, loss is: [6.872655]\n",
"epoch: 0, batch_id: 700, loss is: [6.6887097]\n",
"epoch: 0, batch_id: 800, loss is: [7.1285286]\n",
"epoch: 0, batch_id: 900, loss is: [6.8373947]\n",
"epoch: 0, batch_id: 1000, loss is: [6.35812]\n",
"epoch: 0, batch_id: 1100, loss is: [6.46247]\n",
"epoch: 0, batch_id: 1200, loss is: [6.6280813]\n",
"epoch: 0, batch_id: 1300, loss is: [6.8213453]\n",
"epoch: 0, batch_id: 1400, loss is: [6.546687]\n",
"epoch: 0, batch_id: 1500, loss is: [6.5811205]\n",
"epoch: 0, batch_id: 1600, loss is: [6.8401494]\n",
"epoch: 0, batch_id: 1700, loss is: [6.552598]\n",
"epoch: 0, batch_id: 1800, loss is: [6.9257517]\n",
"epoch: 0, batch_id: 1900, loss is: [6.449529]\n",
"epoch: 0, batch_id: 2000, loss is: [6.781369]\n",
"epoch: 0, batch_id: 2100, loss is: [6.56577]\n",
"epoch: 0, batch_id: 2200, loss is: [7.2461166]\n",
"epoch: 0, batch_id: 2300, loss is: [6.9522705]\n",
"epoch: 0, batch_id: 2400, loss is: [6.9158196]\n",
"epoch: 0, batch_id: 2500, loss is: [6.70108]\n",
"epoch: 0, batch_id: 2600, loss is: [6.6069937]\n",
"epoch: 0, batch_id: 2700, loss is: [6.3994207]\n",
"epoch: 0, batch_id: 2800, loss is: [6.838238]\n",
"epoch: 0, batch_id: 2900, loss is: [6.9941645]\n",
"epoch: 0, batch_id: 3000, loss is: [6.467593]\n",
"epoch: 0, batch_id: 3100, loss is: [6.910493]\n",
"epoch: 0, batch_id: 3200, loss is: [6.582421]\n",
"epoch: 0, batch_id: 3300, loss is: [6.5058546]\n",
"epoch: 0, batch_id: 3400, loss is: [6.704367]\n",
"epoch: 0, batch_id: 3500, loss is: [6.464218]\n",
"epoch: 1, batch_id: 0, loss is: [6.7665234]\n",
"epoch: 1, batch_id: 100, loss is: [6.588025]\n",
"epoch: 1, batch_id: 200, loss is: [6.4301405]\n",
"epoch: 1, batch_id: 300, loss is: [7.1541805]\n",
"epoch: 1, batch_id: 400, loss is: [6.553849]\n",
"epoch: 1, batch_id: 500, loss is: [6.21858]\n",
"epoch: 1, batch_id: 600, loss is: [6.330143]\n",
"epoch: 1, batch_id: 700, loss is: [6.1063113]\n",
"epoch: 1, batch_id: 800, loss is: [6.71904]\n",
"epoch: 1, batch_id: 900, loss is: [6.7976933]\n",
"epoch: 1, batch_id: 1000, loss is: [6.4078493]\n",
"epoch: 1, batch_id: 1100, loss is: [6.5992503]\n",
"epoch: 1, batch_id: 1200, loss is: [6.2867823]\n",
"epoch: 1, batch_id: 1300, loss is: [6.1241736]\n",
"epoch: 1, batch_id: 1400, loss is: [6.903452]\n",
"epoch: 1, batch_id: 1500, loss is: [6.8167877]\n",
"epoch: 1, batch_id: 1600, loss is: [6.785468]\n",
"epoch: 1, batch_id: 1700, loss is: [6.72624]\n",
"epoch: 1, batch_id: 1800, loss is: [6.668326]\n",
"epoch: 1, batch_id: 1900, loss is: [6.592691]\n",
"epoch: 1, batch_id: 2000, loss is: [6.542628]\n",
"epoch: 1, batch_id: 2100, loss is: [6.616316]\n",
"epoch: 1, batch_id: 2200, loss is: [6.786495]\n",
"epoch: 1, batch_id: 2300, loss is: [6.4466743]\n",
"epoch: 1, batch_id: 2400, loss is: [6.931132]\n",
"epoch: 1, batch_id: 2500, loss is: [6.3207083]\n",
"epoch: 1, batch_id: 2600, loss is: [6.697523]\n",
"epoch: 1, batch_id: 2700, loss is: [6.8533525]\n",
"epoch: 1, batch_id: 2800, loss is: [6.375583]\n",
"epoch: 1, batch_id: 2900, loss is: [6.7229414]\n",
"epoch: 1, batch_id: 3000, loss is: [6.7564845]\n",
"epoch: 1, batch_id: 3100, loss is: [6.9129057]\n",
"epoch: 1, batch_id: 3200, loss is: [6.732751]\n",
"epoch: 1, batch_id: 3300, loss is: [6.6692004]\n",
"epoch: 1, batch_id: 3400, loss is: [6.4342775]\n",
"epoch: 1, batch_id: 3500, loss is: [6.594665]\n"
"epoch: 0, batch_id: 0, loss is: [10.252193]\n",
"epoch: 0, batch_id: 500, loss is: [6.894636]\n",
"epoch: 0, batch_id: 1000, loss is: [6.849346]\n",
"epoch: 0, batch_id: 1500, loss is: [6.931605]\n",
"epoch: 0, batch_id: 2000, loss is: [6.6860313]\n",
"epoch: 0, batch_id: 2500, loss is: [6.2472367]\n",
"epoch: 0, batch_id: 3000, loss is: [6.8818874]\n",
"epoch: 0, batch_id: 3500, loss is: [6.941615]\n",
"epoch: 1, batch_id: 0, loss is: [6.3628616]\n",
"epoch: 1, batch_id: 500, loss is: [6.2065206]\n",
"epoch: 1, batch_id: 1000, loss is: [6.5334334]\n",
"epoch: 1, batch_id: 1500, loss is: [6.5788]\n",
"epoch: 1, batch_id: 2000, loss is: [6.352103]\n",
"epoch: 1, batch_id: 2500, loss is: [6.6272373]\n",
"epoch: 1, batch_id: 3000, loss is: [6.801074]\n",
"epoch: 1, batch_id: 3500, loss is: [6.2274427]\n"
]
}
],
"source": [
"import time\n",
"vocab_size = len(vocab)\n",
"epochs = 2\n",
"losses = []\n",
......@@ -359,11 +303,11 @@
" x_data = data[0]\n",
" y_data = data[1]\n",
" predicts = model(x_data)\n",
" y_data = paddle.nn.functional.one_hot(y_data, len(vocab))\n",
" loss = paddle.nn.functional.softmax_with_cross_entropy(predicts, y_data,soft_label=True)\n",
" y_data = paddle.reshape(y_data, ([-1, 1]))\n",
" loss = paddle.nn.functional.softmax_with_cross_entropy(predicts, y_data)\n",
" avg_loss = paddle.mean(loss)\n",
" avg_loss.backward()\n",
" if batch_id % 100 == 0:\n",
" if batch_id % 500 == 0:\n",
" losses.append(avg_loss.numpy())\n",
" print(\"epoch: {}, batch_id: {}, loss is: {}\".format(epoch, batch_id, avg_loss.numpy())) \n",
" optim.minimize(avg_loss)\n",
......@@ -382,22 +326,22 @@
},
{
"cell_type": "code",
"execution_count": 17,
"execution_count": 20,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[<matplotlib.lines.Line2D at 0x14eba4550>]"
"[<matplotlib.lines.Line2D at 0x14e27b3c8>]"
]
},
"execution_count": 17,
"execution_count": 20,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAXAAAAD4CAYAAAD1jb0+AAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4yLjEsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+j8jraAAAgAElEQVR4nO3dd3ic1Zn38e+ZplHvXbIlWW5yBQt3E5sOIZAQQgkBklCywGYhm002ySbvvpt9N4VsQrK7kEACIZsQQk0oCdVgwN1y70WWLKtZvXfNef+YohlpRnVkzYPuz3VxYY3asTz6zXnuc5/zKK01QgghjMc01QMQQggxPhLgQghhUBLgQghhUBLgQghhUBLgQghhUJbz+c2SkpJ0Tk7O+fyWQghheLt3767TWicPfvy8BnhOTg5FRUXn81sKIYThKaXO+HtcSihCCGFQEuBCCGFQEuBCCGFQEuBCCGFQEuBCCGFQEuBCCGFQEuBCCGFQhgjwP+8t5w/b/bZBCiHEtGWIAH9tfxV/2lU21cMQQoiQYogAD7OY6O51TPUwhBAipBgiwG0WEz39EuBCCOHNGAFuNtHTJwEuhBDejBHgFglwIYQYzBABHmYx0y0BLoQQPgwR4DIDF0KIoYwT4P0OtNZTPRQhhAgZhgjwMItzmNKJIoQQA0YMcKXUU0qpGqXUIa/HEpRS7yilTrr+Hz+Zg3QHuNTBhRBiwGhm4E8DVw167FvARq31bGCj6+1JY3PPwCXAhRDCY8QA11p/CDQMevh64HeuP/8O+HSQx+XDZpYAF0KIwcZbA0/VWle5/lwNpAb6QKXUvUqpIqVUUW1t7bi+mczAhRBiqAkvYmpna0jA9hCt9RNa60KtdWFycvK4vkeYxQxIDVwIIbyNN8DPKaXSAVz/rwnekIaSGbgQQgw13gB/FbjT9ec7gVeCMxz/PAHe3z+Z30YIIQxlNG2EzwLbgLlKqXKl1F3Aj4DLlVIngctcb08a9yKmlFCEEGKAZaQP0FrfGuBdlwZ5LAGFWSXAhRBiMEPsxJQ2QiGEGMoQAR4mi5hCCDGEIQJculCEEGIoQwS49IELIcRQhgjwgRm4tBEKIYSbsQJcjpMVQggPYwS4dKEIIcQQhghwq1mhlNTAhRDCmyECXCmFzSz3xRRCCG+GCHBw1sFlBi6EEAMME+BhrhsbCyGEcDJQgJvp7pUAF0IIN8MEuE1m4EII4cM4AW42yUYeIYTwYpwAt0gXihBCeDNMgIdJF4oQQvgwTIDLDFwIIXwZK8BlEVMIITyME+CyE1MIIXwYJsDDrGapgQshhBfDBLjMwIUQwpdxAly6UIQQwodhAjzMIht5hBDCm6ECXGbgQggxwDAB7m4j1FpP9VCEECIkGCfAzSa0hj6HBLgQQoCRAtwi98UUQghvhgnwMFeASx1cCCGcDBPgNosZkBm4EEK4GSjApYQihBDejBfg/dILLoQQYKAAd9fAu+S+mEIIARgowAdm4BLgQggBBgrwMLPUwIUQwpthAlwWMYUQwpdhAjzM1UYofeBCCOFkmACXGbgQQvgyXoBLG6EQQgBGDHCZgQshBDDBAFdKPaiUOqSUOqyUeihYg/JHzkIRQghf4w5wpdRC4B5gObAEuFYplR+sgQ0mM3AhhPA1kRn4fGCH1rpDa90HfADcEJxhDWUzywxcCCG8TSTADwHrlFKJSqkI4Boge/AHKaXuVUoVKaWKamtrx/3NbLKRRwghfIw7wLXWR4EfA28DbwL7gCEtIlrrJ7TWhVrrwuTk5PEP1KSwmeW+mEII4TahRUyt9ZNa62Va64uBRuBEcIbln81ikhm4EEK4WCbyyUqpFK11jVJqBs7698rgDMs/542NpQ9cCCFgggEOvKSUSgR6gQe01k1BGFNANrPMwIUQwm1CAa61XhesgYxGmFVq4EII4WaYnZggM3AhhPBmrACXRUwhhPAwVICHWUxyRx4hhHAxVIDbLCa65Z6YQggBGC7AzXTLDFwIIQCjBbgsYgohhIehAjzMaqKnTzbyCCEEGC3A5SwUIYTwMFSASxuhEEIMMF6AyyKmEEIABgvwMJmBCyGEh6EC3GaRGrgQQrgZK8DNZvodmn6HnuqhCCHElDNWgMuNjYUQwsNQAR4mAS6EEB6GCnD3DLxbNvMIIYRRA1xm4EIIYagA95RQpBdcCCEMGuAyAxdCCGMFuJRQhBBigLEC3GwGZAYuhBBgtACXEooQQngYKsAHFjGljVAIIQwV4J4auNwXUwghjBng0kYohBBGC3CzdKEIIYSboQI8zCqLmEII4WasAHe1EcoMXAghDBbg0kYohBADJMCFEMKgDBXgZpPCYlLSBy6EEBgswMF1X0zpAxdCCGMGuPSBCyGEEQPcbJIauBBCYMAAD7NKgAshBBgwwG1mk/SBCyEERgxwi1kCXAghMGSAyyKmEELABANcKfU1pdRhpdQhpdSzSil7sAYWSJjFRE+f9IELIcS4A1wplQn8A1CotV4ImIFbgjWwQMIsUgMXQgiYeAnFAoQrpSxABFA58SENT9oIhRDCadwBrrWuAP4TKAOqgGat9dvBGlggNosEuBBCwMRKKPHA9UAukAFEKqW+4Ofj7lVKFSmlimpra8c/UpcwWcQUQghgYiWUy4ASrXWt1roXeBlYPfiDtNZPaK0LtdaFycnJE/h2TnIWihBCOE0kwMuAlUqpCKWUAi4FjgZnWIFJG6EQQjhNpAa+A3gR2AMcdH2tJ4I0roBsZrPUwIUQAmcXybhprf8V+NcgjWVU5CwUIYRwMt5OTLOzhOJw6KkeihBCTCnjBbj7tmpSBxdCTHOGC/AwCXAhhACMHOBSBxdCTHOGC3B3CUXOQxFCTHeGDXCZgQshpjvjBbjZDEiACyGE4QJcauBCCOFkuAAfqIHLTR2EENObYQNcZuBCiOnOsAHeLX3gQohpznABLjVwIYRwMmyASx+4EGK6M1yASxuhEEI4GS/ApYQihBCAAQN8oAYubYRCiOnNcAEuZ6EIIYSTYQNcSihCiOnOcAFuMSmUkvPAhRDCcAGulCLMIvfFFEIIwwU4OO+LKTVwIcR0Z8wAt5glwIUQ054hA1xKKEIIYeQAl0VMIcQ0Z8gAt1lMdPeObSPPy3vKue8PuydpREIIcf5ZpnoA42Ebxwz8xd3lbC2up6fP4eklF0IIIzNkko21Bt7b72Df2SYAzrV0TdawhBDivDJkgNvGGOBHq1ro6HGWXKolwIUQHxPGDPAx9oHvKm30/Lm6WQJcCPHxYMwAH+MMvKi0gYRIGyABPhYOh6axvWeqhyGECMCQAR5mMY96EVNrTdGZRi6enUSEzUyVBPio/fVgFSt/uJHKps6pHooQwg9DBvhYZuBlDR3UtnZzUW4CaTF2WcQcgyNVLXT3OXjnyLmpHooQwg/DBnj3KG/o4K5/X5STQFqsnapmmU2OVllDBwDvHpUAFyIUGTPAx7CIWVTaQIzdQn5yFGmxdqmBj8FZV4BvP11PS1fvFI9GCDGYIQM8zDr6EkrRmUYKcxIwmRRpMXZqWrvpd+hJHuHHQ1lDB/PSount13xwvHaqhxOStp6q43t/OTTVwxDTlDED3Ozcian18EHc0N7DqZo2CnPiAUiPtdPn0NS3dY/r+9a0dPHU5hIc0+AFoKWrl6aOXq5bmkFCpE3KKAG8dqCK328/Q3OHXKGI88+QAW6zmNAaevuHD9LdZwbq3wBpseEA4+5E+ePOMr7/+hH2unZ1fpy5yye5iZFcMi+F94/V0CsHiA1R3uj8OZ2ua5vikYjpyLABDiPfVq3oTAM2s4lFmbEApMXYgfEH+IHyZoBp0ZXhDvDshAguL0ilpauPXSUNUzyq0FPharE8Xds+xSMR05EhAzwqzArAl367k78drKIvQJAXlTayKCsWu9UMQFqsM8DH00qotfYK8OrxDNtQ3B0oMxIjWDc7CZvFxDtSRvGhtaai0RngJXUS4OL8G3eAK6XmKqX2ef3XopR6KJiDC+SGCzP57ifnU93Sxf3P7OHih9/nsU2naO/u83xMV28/B8qbPPVvgMRIG1azGtcMvLqli7q2bvJToiiubed07cf7krmsoYO4CCsxdisRNgtr85N458i5EdcdppPatm5PN5QEuJgK4w5wrfVxrfVSrfVSYBnQAfw5aCMbht1q5u51eWz6pw08cfsycpIiefjN41z58w/56KSzW+JAeTO9/ZqLZiZ4Ps9kUqTG2KkeRy/4/rPO2fdDl80GPv5llLKGTrLjIzxvX16QSnljJ8fPtU7hqEJLuWv2HWYxUfwxf0EXoSlYJZRLgWKt9Zkgfb1RMZsUVyxI44/3rOSFv1uFzWzi9id38s0X9/PesRoAls2M9/mctBj7uE4kPFjRhMWkuGx+KgXpMR/7AD/b0MGMhIEAv3ReCgDvnoe/t9bGOIPFHeDLcxMorW+fFt1JIrQEK8BvAZ719w6l1L1KqSKlVFFt7eT1El+Uk8DfHlzH331iFi/tqeBXHxSTnxJFvOsQK7fxbuY5UN7MnNRo7FYzlxeksruskbpxtiOGun6Hs7ab7RXgKTF2lmTHnZcXric3l7DiBxupbQ3tn6+7/n3x7GS6eh1yVLE47yYc4EopG3Ad8IK/92utn9BaF2qtC5OTkyf67YZlt5r51tXz+Mv9ayicGc8NF2YO+Zj0WDtVzV1jquVqrTlY0cziLGc3y+UFqWgN7x2tCdrYQ8m5li56+h0+M3CAy+ensL+8eVLPk6lp7eLn756kp9/BkaqWSfs+wVDe2EF8hJUFmTGAdKKI8y8YM/CrgT1a65CpKSzKiuXF+1Zz//r8Ie9LjbHT3eeguXP0Gy/ONnTS1NHL4qw4ABZkxJAZF87bH9MyiqcDZVCAX7EgDYAbHtvKo++foqY1+EH+n28dp8t1v9MT1aFdby9v7CQrPoK8pCgASqQXfNL0OzRtXk0KwikYAX4rAconoSh9HJt5DlQ4N+64Z+BKKS6bn8LmU7V09ozt5srnyyv7Krj3f4vG9bmBAnxOajRP3lnIzMQIfvLWcVb/8D0eeGYPp2qCE7QHy5t5YXc5X1qTQ3J02LALpu3dfZ6gnyrljR1kxYeTGhNGhM3MaelEmTRPby3l4offD9gyPFl6+x2ePRGhaEIBrpSKBC4HXg7OcCafuxd8LHXwg+XN2Mwm5qRGex67vCCNrl6Hp+sl1Ly4u5y3j5wb1yz5bEMHJgXpcfYh77t0fip/vGclG7/+Cb64OocPT9by93/cO+H2Qq01//baYRIibHz10tnMSY3i5DABfsdTO/nmiwcm9D0nQmtNRVMnWfHhKKXITYo0XAnlSGULn//1dkN00OwsqaehvcezcHy+/PNLB7jkp5s4Ux+a/7YTCnCtdbvWOlFr3RysAU22dHeA+6nj7ilr9Humxf7yJuZnxPjczX5FXgLRdktIdqP09Ts8xwgcrRr77LisoYOMuHCs5sBPj1nJUXz32gK+c818jlW3UnSmMeDHjsbrB6ooOtPIN66cS4zdypzUaE6ca/Pb2dHZ08/eskbem8Lt/fXtPXT1OsiMc17R5SVHGa4XfGtxHVuL67n58e0cD/FylXs95Hz+jPeWNfLyngp6+zX/896p8/Z9x8KQOzEnIjk6DKWGllCaO3u56Vfb+M5fDvo87nBoDlW0sNi1Hd/NajZxybwU3jtWE3KnGx6uHLiJ8+HKsb+2Dm4hHM71SzOItlv4323j7yDt7Onnh387SkF6DJ8rzAZgbmo0nb39fmdcR6qacWho6+5jb9nUnEvjHleWq1c+NymS8saOUZ9THwqqmrsIs5gwm+CWJ7ZxqCI052EtXb2cbXAdWTCGAC+ubWNX6fiOf9Ba8/3Xj5AcHcbNhdm8vLciJGfh0y7ArWYTyVFhQzbzbCuup8+h+dvBKp+abkl9O23dfSzKih38pbi8IJX69h72lE1s9jlW7d193PX0roDhvNN1ZklsuJUjlWPv5Chr6Bx1gEfYLHxuWTZvHqoa96Lmk5tPU9ncxb9+qgCzSQEwJ81Zrjrhp4xy0HWkgVJMWQnLfYhVVoJrBp4UiUNDWX3o1ksHq2xytoo+/5VVRNgs3Prr7ef9uTwax7yuIktHGeA9fQ7uenoX9/1hz7jKe6/sq2RvWRPfvHIuX79iDhaT4tH3Q28WPu0CHJxllOoW3x7jLafqCLeasVvMPPp+sefxA+XOGd4SVweKt3X5zrbI8b7Kg/OJdvPj2/jL3opRf86bh6rZeKyGZ3aU+X3/jpIGchIjWJmXMOYA7+jpo66t26cHfCS3r5pJb7/mTzvPjul7ub195BzLcxJYkZfoeWx2irOzw99C5oGKZpKjw7ggO44PT9aN63tOlHsGPlBCiQTGNkOcapXNXaTH2pmZGMnzf7eKhEgbt/9mB49tOhVSC3dHXBOVjFj7qEsoT28tobS+g7q27jHvJ+jo6eNHbxxjcVYsn70wi5QYO59fMYOX9lSE3Av0tAxwf9vpt5yqY2VeAl9YOYNX9lV4XukPlDcTbjUzy/UL6i02wkpWfPi4Zrlur+yrYEdJA09vLR3157y6vxJwbucfXCN2ODRFZxpYnptAQXosJfXtPmfEjMR9qTraGTg4ywcXz0nmjzvKxlyT7u7r52hVCxfM9H2BjLZbyYwLDzgDX5wZy8VzkjlQ3kRTx/nftVnR2ElsuJVou/NgtZwk5/NjMmq03X39/PvrR3hul/8X7PGqbOr0vABlxoXz/FdWsTAzloffPM66h9/nhse28PSWkvOyK7akrj3gc+doVSsJkTaW5yaM6udb29rNf2885fm7HR7jfoJfbSqmuqWL/3NtASbXFeF9n5iFxaT4n/dPjulrTbZpGeDuzTxuFU2dnK5rZ01+EvdcnIfVbOKxTc7LpYPlzSzIiMESYEGvID1m3BtOHA7N4x+eBmDf2SbP0aTDaWjvYfOpOvKSIqlt7WZfuW8N+GRNG00dvVyUk0BBRgxawzE/C1T9Ds0Vj3zAk5tLfB4v8zpGdizuWDmT6pauMS/qHq9upbdfszhz6BXOnNQoTpzz7ZBo7+7jVG0bi7JiWTc7Ga1hy6n6MX3PQHr7HaOuA7tbCN1i7FaSosKCfshZU0cPtz+5kyc3l3ieK8HQ3ddPbWu3p60WnBOb576yio++uYFvXDmXjp5+/u9rR7jkp5t4ZV/FpB1kdriymUt/uingOsqRqhYK0mPIS46ioqlzxPbRn759nM7efh677ULn549hglXe2MHjH57muiUZFOYMnKOUEmPn1uWhNwuflgGeFhtOa1efZ2a6xXUZvm52MinRzn+ol/c4Fy0OVTZ7NvD4U5ARQ0ldOx09Y99ksPFYDadq2jwHZL15aORjav92sIp+h+YHNyzCYlK8fdg3MHeWOMNsRW4iCzKcOwSP+KmVH6xo5sS5Nh7/oNhn5hOoB3wkG+alkBkXzv9uKx3T57mP6F3sZ41hTmo0xTVtPr2/hytb0Nr58UuyYom2W/jwRHDq4M9sP8O1/73Zs4YwHOcmnnCfx/KSI4M6Az/b0MFnf7mVfWVNrM1P4nRt+7jvJjXYuWbn18nw0yqanRDBAxvyefOhi3n9q2uZmRjJg3/axz3/u5uaSdiF+5O3juPQ8IGff8e+fgfHz7UyPz3ac5VzZpgAPVTRzHNFZ7lzdQ5LsuOYkRAxqgDv6u3ntf2V3PeHPSgF37p63pCPuW/9LMwhVgufpgEeBgy0Em4+VUdSVBhzUp111698Ig+TUnzjhQN09Tr8hotbQXrgWe5IfvVBMVnx4fz9hnzmpUXz5qGqET/n1f2V5KdEsSI3gVWzEnl70NnkO0oaSIuxk50QTnqsnbgIq98rhM2uxb+a1m6fF4GzDR1EhVmIj7CO6e9iNim+sHIm2083+C17BHKgvIl4VylqsDmp0fT0Oyj1+oV1r0kszIzFYjaxZlYSH52sDcrs0H3e+SPvnBj247TWnl2Y3vKSghfgB8qb+MxjW6lr6+H3dy3nHy51vsjvnmC7ppv7ai8jbujP3dvCzFheum81/3LNfD46WctlP/uAF3eXB202vrOkgU3Ha0mItLGzpH5IF8/punZ6+hwUZMSQ5ylT+b/K0Vrz/deOEB9h8/y8RrpCPlzZzHf+fJDl//EuX312L/Vt3fzohsV+fy6pMXY+v3wGL+4pZ/eZ0Li5yfQM8BjnP051cxcOh2bLqTrW5ieilLPelR4bzucKs9jpWpz014HiVuCZ5Y6tjLKrtIHdZxq5Z10eFrOJaxalU3SmcdhzRqqaO9lV2sCnFmeglOKKglRO17Zzqsb5hNZas6vUWf9WSqGUcj6B/Yzto5N1zEuLJis+nN9vL/U8frahg+yECM/PYixuvigbm8XE78fQUnig3HmF4+/7zfXTiXKwopn0WDsp0c6Z48Vzkqls7qJ4FJtoDlc2B6yXt3b1suN0A+mxdradrmf76cBlmYb2Hjp7+z01VrfcpEjq2nrGdEyDP23dfdz26x3YrSZeum8VK/ISWZwVi81sClqAVzWPLsDB+eJ8z8V5vPHgOuamRfNPL+znjqd2TnihU2vNw28eIyU6jH+7bgFdvQ72nPEtCR51he/89BjPDDzQQvFfD1axs7SBf7piLrHhzgnIgowYSl2dZIPVtnZzw2NbeXlPOZfOT+WZu1ew+Z8v4dMXDD1Dye3+DbNIi7Fz0+Pb+cW7J8/7ztDBpmWAuzfzVDV3cay6lfr2HtbkJ/l8zH3rnYsW0WEWchOHLmC6ZcaFE2O3jLkO/qtNxSRE2rjJ1fd8zaI0tIa3Dgcuo7y+vwqt4bqlGQBcVpAK4JmFlzV0cK6lm4tyB2p3BekxHKtu9XmitXf3saeskfVzU7hthe+suayhgxkJI/9S+5MQaeO6JRk8X3R2VGWIzp5+Tta0BbzCyU+JQqlBAV7e7LlFHsC62c5/t5HaCc+1dPGZR7fy/deP+H3/Ryfr6HNoHr5xMSnRYcPOwt2z16ElFPeZKBObhZ8810prdx//+qkF5Kc4X8TsVjMLM2MmvGHKrdL1d3D/LoxGXnIUz927iu9fv4A9Zxq54pEPeXJzybj3Qbx/vIaiM438w6WzWT83GbNJseWUb1fRkcoWbGYTs5KjiAqzkBwdRomfF2utNT956zjz02O4+aJsz+PudaDj1UN/P7edrqe7z8Gz96zkkZuXsiY/ybNoGUhKtJ03HlrHpxan88i7J7j5ie1TWhOflgHufWs19xNm7WzfAM+Kj+D+DfncdFH2sP+oSikKMvzPcgM5Xt3KxmM13Lkqh3Cb83Zv+SnR5KdE8beDgcsor+6vZFFmLLmumUh6bDhLsmI9JZAdrtBc4RXgCzJj6O5z+MxadpTU09uvWTc7yWfWrLV2BfjY6t/evnX1PLLiw/ny07vYP8LNn49UNdPv0D6B7M1uNTMzIcIT4C1dvZyua/cJ/OyECHKTIvlohHbCp7eW0tPv4I2D1X5nYxuP1hAXYWVVXiL3rZ/FjpIGthb7/5qDN/G45Y5wiT9apa4NI3mDOp8KcxI4WN4clDNgKpu7SIy0eW43OFomk+KOVTm884+fYNWsRP799SPc8MutY56NOxyah988zszECG6+KJtou5UlWbFsGfQzP1LVwuzUKM+u4NykSM/Px9vZhk7O1Hfw+eXZnr0EMHCFfNjP7+fWU3XE2C3DrnH5E2O38vNbLuAXtyzlxLlWrvmvj4K2DjNW0zLA7VYzcRFWqpo72XyqjlnJkT6r8W7/ePkcvndtwYhfryA9lmPVLaOeiTz+YTHhVjN3rJrp8/g1C9PYWdLg95zxkrp2DlY0c92SDJ/Hr1iQxr6zTVQ3d7GrpIH4CCv5rpmge2zgW+L56GQdYRYTy2bGkxBp49rF6by8p5zTde109znG3IHiLSkqjGfuXklCpI07ntrpuQT2x72AuSQ78C/QnNRozzZvd4fIokG/cOtmJ7GteGj91K2tu49ntp8hPyWKzt7+IS+S/Q7NpuM1rJ+TjMVs4tblM0iNCePn75z0W+t1b+LJHDQDn5EQgdmkJnwmSkltOyaFzx2RwHlzkp4xdMoMp7Kp0+9ZN6OVERfOk3cW8l+3XkBpXTvXP7plTPshXjtQybHqVv7x8jmecF6bn8T+s020dA2UoI66OlDcAq0zuMud3lef4LyBS3yE/w1tW4vrWZmX6BP4Y3H90kzeeHAdSVE2fvLW8XF9jYmalgEOzn/YsoZOdpY0sHZQ+WSsFmTE0NXrGNWlc0VTJ6/uq+SW5dlDbjZx9aJ0HJohnSUAr7l6v69dku7z+BWuMso7R8+xs7SBwpwEnyuGvORIbBaTz67Nj07WsSIv0TP7umNVDu09/fzXRmeP60QCHJxXOM/cvYIIm5nbn9zhqdEPdqC8mZToMFJjAgfJ3LRoSuudW9TdOzAHz9jXzU6ms7c/YH34+V1naenq4+EbF5OXFMmLu8t93r+/vIn69h4ume/8WdqtZu5fn8/O0ga2Fg+thZc3dhJjt3jqrG42i4ns+PAJb+YpqXeuQ3ifvQMDd5cKRhmlqqmLDD+TlrFQSnHdkgz+8sAa4sKt3PbrHbw06GfrT2+/g5+9c4L56TF8avHAhGR1fhIODdtdP/Oa1i7q2nqY7xXggdYZdpU0EBtuZU5KtM/jnivkQROJsw0dlDV0sHpWIhORFR/BF1fncLCieUL7QcZr2gZ4eqydbcV1dPb2D6l/j5VnIXMUdfBH3jmBSSnuWZc35H3z0qLJTYrkjUHdKFprXt1fyfKchCFXCvkpUeQmRfLM9jOcqe/wKZ+A8+iAeWnRnrFVNXdyqqaNdV5/5yVZsSzKjOWVfc4XiYmUUNyyEyL4w90rAPjCb3b43Q13oLxpxMvX2anR9Ds0p2vbOVDRTFZ8OAmDXvhW5iVgMSm/ZZS+fgdPbi7hopx4LpwRz2eXZbGzpMHnXIv3jtZgNik+MXvghiM3X5RNWoydR945MWQWXt7YSWa8/59RblKk3xrtWJTUtZHjZ90lKSqM3KRIikqHBrh7AXu03SGVTZ2jWsAcjdykSP58/xoKc+L5+gv7efjNYwFvL9fV28/Xn9/PmfoOvnHlHJ/JxgUz4gi3mj1lTXcgun+/YGDD1OAt9btKG5V9NekAABQfSURBVCicGe+33OlvHWiba5F69QR/98E5E7eZTbyw2/9O5H6HnrTDwqZtgKfF2unt15hNipUTfBWelRyFzWwa8RX4WHULL+0p587VM/3+8iiluHphGluL6z2737TWfHCillM1bXxqaYbfz7liQaqnjXH5oAAH5xPY2T+t2XxyaM1fKcXtrnKOUgzprhivWclR/O7LyznX2sXvBu00bfVTz/ZnbupAJ8rB8ma/Hx9tt3LhjHjeP1YzJDjeOFRNRVOn5wXzhgszUQpe2jNwdMHGYzUUzown1qt10m4188CGWRSdaRyyXb/CTw+4W26S81TC8d4fU2tNSW27p54+2LKZ8ewpaxwS1K/ur+Rzv9rGW36u3gZr6eqltbvPbw/4eMVGWPndl5dz6/IZPLapmFue2O5p+XSrbu7ipse38er+Sr5x5Vw2zE3xeX+Yxczy3AS2uGbg7knH/DTfEgrgUwevbe3mdF37kPKJ24KMWHr6HD6dSltdrcPuIxsmIj7SxuUFqfxlb4XfMt5Lu8u56hcfsncSzpmZvgHuaiVckhVLjH1sPc+D2SwmZqdGjTgD//Ebx4gOs/DAhqF3CnK7ZlE6/Q7N80VneXJzCVf/4iO++NtdJEba+OSidL+fc0WB8045kTazT73QrSAjhqaOXqqauzw97/PSfC81r1uSQVyElbQY+5gXtoazICOWy+an8sedZT6Lb4cqBjbkDCc3KRKLSbGzpIGyhg4W+dmxCc7OnGPVrdz/zB7PTTa01jzx4WlykyK5zFUeSY8NZ21+Ei/vKcfhcJ7pfbSqhUvnpwz5mjddlE12Qjg/+OtRz+zN2QPeETDA85Ij6ezt59w4D/aqbeumvac/YIAXzoynob3Hp0yjteaXm5zn97x3bOQAr2pyjs3fus9EWM0mfvCZhfz4s4sorm3juv/ZwkN/2ktFUyd7yxq57n82U1zTxq/vKOSBDfl+W0fX5idxqqaN6uYujla1khkX7vPCOiMxAqV8b19X5Kp/+5u8gPcVsrMEp7Vma3E9q2cljqtd1p/PFWbR2NHLxkG3WWzv7uM/3z7O0uw4lg6z1jNe0zbA3e1TE61/uwXqt3bbVlzP+8dreWBDPnERtoAftyAjhuyEcH74xjH+/fUjhFnN/MdnFvL+N9YPKR24XZAdR0p0GIU5CX63/Lt3ZB6qaGbzyTrWzU4a8sS1W81895MF3LU2dzR/3TH50pocGtp7eNVVooGBDTkjlVBsFhN5yZGeNYBAgX/bihl879oC3jpSzc1PbKOmpYsdJQ0crGjm7nW5PpfWNy7Loryxkx0lDbx3zPkLd8m81CFfM8xi5ttXz+f4uVaeK3JeHjd19NLe0z+kA8XN3Tky3ktmd/klYIDnOOvgu73KKJuO13KsupX4CCubjo+8qalyDD3gY6WU4uaLZrDpG+u5f/0s3jhUzYb/3MTNT2zHbjXz5wfWcHnB0J+12+p859XwllN1HKls9ql/g/PfJDMu3Ge9aWdpA3ariYUZ/p8beUnOdSD372dxbTs1rd0Trn97Wzc7mbQYO88X+ZZRHv/wNDWt3Xz3kwVBe7HwZgn6VzSI/FRnj7F74WqiCjJieGF3OTWtXZ5NJm5aa370xlEyYu3cuTpn2K+jlOK7nyxgb1kTn7kg07OZZTgmk+L3d60gMsz/zHluWgxKwct7Kqhv7/H0Tg9247KsEb/XeKzKS2RuajS/3VrK5wqzUEoFrGf7M9t1cwcg4C+pUoq71uYyMyGCf/jTXj796BZSY+0kRNr47IW+f68rCtKIDrPw4u5yGtq7mZkY4fewMoCrF6axPCeBn719gk8tyRhyCuFgS7PjsJlNbCuuZ/3cobP6kbhLA4ECPC8pirgIK0VnGrjJ1e/8y03FZMTa+eqls/n2ywc5UtXCggA/JxjoAQ9mCWWwaLuVb141j9tWzuRnb5+grbuXH92weMjC/WDz02JIiLSx8dg5Sura+eTioWXDwa2Eu0obuCA7fsiir5tl0DrQNler4upZwZm8gXOz043Lsnhs0ymqmjtJjw2nurmLJz4s5trF6Z4F6GCbtjPwC2fEs+M7lwbtssZduvA3C//rwSr2lzfzj1fMHVV54soFaXzr6nmjCm+3uWnRAWeFUWEWchIjecu14SdYVx2jpZTiS2tyOFrV4ulVD1TP9sddB89JjPC5nPbnsoJUnv/KKhwa9pY1cceqmUN+5uE2M9cuSedvB6vYWlzPJfNSAs6OlFJ879oCGjp6ePS9U1Q0uc4BD1BCibBZuHBmHJtPje+Y29N17djMpoCzY5NJsWxGvKcTpai0gZ2lDdy9Ls9TJtp0fPie5MqmTswmNWSiMRky48L56U1LePz2whHDG5x/v9WzEnnr8DkcGgrSh/4O5LkWirXWtHb1cqSyJWD92819hay1ZsupejLjwske54a1QG5cloVDOydK4DrjxQH/fNXQc1WCZdoGOBDUJ/D8AJ0oPX0OfvLWcealRfOZYbboTjb3mS1zU6NJGaZtb7J8+oJM4iOs/NZ1PGlZQ8eoN1C470U6uP87kIWZsfzlgTU8eOlsvhygJHTjsiw6e/vp7nNwqZ/yibdFrnOhn9pS4gnmwT3a3tbmJ3G4smVcB0+V1rUzMzFi2N7kZTnxnK5tp6G9h199UEx8hJVblmeTHB3GosxY3j9WE/BzwVkDT4uxj7v/ebKtyU/y7Klw72PwlpMUSWt3H3VtPew+04hDw/KcEQI8I4bGjl4qmjrZdjq49W/vca3ITeD5orMcLG/m5b3lfGltzoTbcoczrQM8mGLsVrIThp4N/tSWEs7Ud/DPV8+b0l8Y90JOoPLJZLNbzdy6fAbvHDnHG65TFwffpi6Q+a5Z2JJRztjB2WX0tcvnBFygvnBGPLlJkUTazAEXv7x948q5WM0m/rC9jOgwCzHhgauPa13tiFv89JCPpKSu3dMqF0jhTOd4n91ZxrtHa/ji6lwibM7xbJibHPDerm4VTZ2TWj6ZKPcVYlSYxe+VzsCO13Z2lTZgNikumDH8i7v7Cvml3RU0d/ZOuHU4kJsKszlT38Hf/WE38RG2YRsWgkECPIgGn3y28eg5Hn7zGFcuSGX9nORhPnPyXeAqFW2YN/a6bLDcvmomSil+9MZRABaMMsBnJkbymzsK+fyKGUEbi1KKH3xmET++cXHA2qm31Bg796+fBTh3YA43e1uUGUuM3eI5pni0HA5NaX2Hp1UukMVZsVjNikfeOUGEzcydqwd29K6fl4JDw4fDnA1T1dwV9A6UYMpOiGBmYgQF6TF++7rzkpytf6V17ewqaWRhRgyRYcMv581Ld64DuQ9uWxXEBUxvVy9KIyrMQkVTJ1+7bPaEO9xGIgEeRAXpsZ6zwQ9VNPPVZ/eyICOWR25eOikr0GOxalYir3917aTNPEYjPTacqxam0dLVR15S5JCdjMO5rCDVM8sMllWzErnWzyJZIHevyyM7IZzZqcOvTZhNitWzkth8qm5Mx65WNnfS0+cYcQbuPNgqlj6H5vPLZ/h0NS3JiiM+wsr7x/2XURwOTVVz8DbxTJbHbruQH9yw0O/7MuLsWM2KY9Wt7Ctv4qIRyicwsA5U19bDrOTIYXf/TkSEzcJtK2awOCuWW5cHb8IRyLTtQpkM7pPP3j9Wy7+9dpi4cCtP3lkY9OAZD6UUC0c5451MX16Tw18PVA17RG+oslvNvPrAWqyjmLGvnZ3Em4erKalr95xSOBJ3a1ygDhRvq/ISOVzZwl3rfGv8ZpPi4jnJfHC8FodDD5nB1rV309uvQ7qEAgzbRWMxm5iREMHrByrp6XOMuIDpVpDuvPlKMLtP/Pn2NfMn9et7kxl4ELnrzF97bh8dPf089aWLpmTBMJRdOCOeBy+dzR2rcqZ6KOMSH2kjaoTLdRio4w4+HnU4pWMI8L+/JJ+3HrrYbylkw9wU6tt7OOTnTkyVrk08Ez0HZarlJkVR4zqeYTQzcBj4/VyTPznlk6kgAR5EGbF2YsOt9GvNY7ddyLy0obsipzulFF+7fM6k9cWGipmJEWTFh494zK2303XtRNjMpESHjfixETZLwKC/eE4ySjmvBAercp8DHuIz8JHkJjk7O/JToka1lwCc7bmXzEuZ0jJisEmAB5FSim9dPY9HP38BF0/xoqWYWkopzzG3g+/acqSyhW1+OlRK69rJSYyc8HpJQqSNJVlxfuvg7ptRBOu8m6mS61rIHE0HkVt+ShRPffEioid5YfF8kgAPsluXz+Cqhf7PLBHTy5r8JFq7+zjgdX736do2bn5iG3f/bteQG0uU1LWTG2BH6FhtmJvC/vImGtp9byFX1dxFuNU8pgXkUOTeOTv49M3pRgJciEmyZlYSSuE5AbK1q5d7f7+bfoemvaefV/YNnIjY2+/gbGPniC2Eo7V+bjJaM+ROMZWuHvCp7oqaqOW5CTx224UBD3ibLiTAhZgk8ZE2FmbEsvlkHQ6H5mvP7aekrp3f3FnIvLRo/rijzNNmeLahg36H9nsO+HgsyowlLcbO77ef8WllDOY54FNJKcU1i9L9Ht42nUzvv70Qk2xNfhJ7yhr54RtHeffoOb77yfmsnpXEbStmcLiyxXNbOU8LYZBKKCaT4sHLZrP7TCNvHhq4UXZl88TvxCNChwS4EJNo3ewk+hyaX39Uwo3Lsvii6zTK6y/IJNxq5o87ygCvAA/SDBzgc8uymJMaxY/fPEZPn4Puvn5qW7sN34EiBkiACzGJls2MJ9JmZklWLP/v0ws9tecYu5XrlmTw6v5KWrp6KalrJy7COqoT+0bLYjbx7avnU1rfwTM7znCu2dk3/XEooQinqd8iKMTHmPsmBmmxQ+90dOuKGTxXdJZX9lZQWt8etPq3t/Vzk1mTn8gvNp70tA5KCeXjQ2bgQkyyOanRfg81WpIVS0F6DM/sKKOktj1oHSjelFJ855r5NHf28h9/cx4iFurb6MXoSYALMUWUUnx+xQyOVbdS2dw1qi3047EgI5bPXJDJmXrnzShC+SRCMTYS4EJMoeuXZhBhc5ZWRjqFcCL+6Yq5hFlMJETaCLcF76bVYmpJgAsxhaLtVq5f6jzSdrJm4OBcuPzetQXcujx70r6HOP9kEVOIKfbAhnxi7FbmjeEeqOPxhZUzR/4gYSgS4EJMsaz4iPN6hrT4+JhQCUUpFaeUelEpdUwpdVQptSpYAxNCCDG8ic7AfwG8qbW+USllAybv9stCCCF8jDvAlVKxwMXAFwG01j1Az3CfI4QQIngmUkLJBWqB3yql9iqlfqOUGrKMrpS6VylVpJQqqq0NfKdsIYQQYzORALcAFwK/1FpfALQD3xr8QVrrJ7TWhVrrwuRkuUuNEEIEy0QCvBwo11rvcL39Is5AF0IIcR6MO8C11tXAWaXUXNdDlwJHgjIqIYQQI5poF8pXgWdcHSingS9NfEhCCCFGQ3nfbmnSv5lStcCZcX56ElAXxOFMJhnr5JCxBp9RxgnTe6wztdZDFhHPa4BPhFKqSGtdONXjGA0Z6+SQsQafUcYJMlZ/5DArIYQwKAlwIYQwKCMF+BNTPYAxkLFODhlr8BllnCBjHcIwNXAhhBC+jDQDF0II4UUCXAghDMoQAa6UukopdVwpdUopNeS8lamklHpKKVWjlDrk9ViCUuodpdRJ1//jp3KMrjFlK6XeV0odUUodVko9GMJjtSuldiql9rvG+m+ux3OVUjtcz4PnXBvIQoJSyuw61O1119shOValVKlS6qBSap9Sqsj1WMg9B8D//QZCcaxKqbmun6f7vxal1EPnY6whH+BKKTPwKHA1UADcqpQqmNpR+XgauGrQY98CNmqtZwMb8XPI1xToA76utS4AVgIPuH6OoTjWbuASrfUSYClwlVJqJfBj4BGtdT7QCNw1hWMc7EHgqNfboTzWDVrrpV59yqH4HICB+w3MA5bg/PmG3Fi11sddP8+lwDKgA/gz52OsWuuQ/g9YBbzl9fa3gW9P9bgGjTEHOOT19nEg3fXndOD4VI/Rz5hfAS4P9bHivEnIHmAFzp1tFn/PiykeY5brF/QS4HVAhfBYS4GkQY+F3HMAiAVKcDVahPJYB43vCmDL+RpryM/AgUzgrNfb5a7HQlmq1rrK9edqIHUqBzOYUioHuADYQYiO1VWS2AfUAO8AxUCT1rrP9SGh9Dz4OfBNwOF6O5HQHasG3lZK7VZK3et6LBSfA4HuNxCKY/V2C/Cs68+TPlYjBLihaefLb8j0aiqlooCXgIe01i3e7wulsWqt+7XzkjQLWA7Mm+Ih+aWUuhao0VrvnuqxjNJarfWFOEuSDyilLvZ+Zwg9B0a830AIjRUA1zrHdcALg983WWM1QoBXANleb2e5Hgtl55RS6QCu/9dM8XgAUEpZcYb3M1rrl10Ph+RY3bTWTcD7OMsQcUop9wmaofI8WANcp5QqBf6Es4zyC0JzrGitK1z/r8FZp11OaD4HAt1vIBTH6nY1sEdrfc719qSP1QgBvguY7VrVt+G8RHl1isc0kleBO11/vhNnvXlKKaUU8CRwVGv9M693heJYk5VSca4/h+Os1R/FGeQ3uj4sJMaqtf621jpLa52D87n5ntb6NkJwrEqpSKVUtPvPOOu1hwjB54AOfL+BkBurl1sZKJ/A+RjrVBf9R7kwcA1wAmcd9F+mejyDxvYsUAX04pw13IWzBroROAm8CySEwDjX4ryEOwDsc/13TYiOdTGw1zXWQ8D/cT2eB+wETuG8TA2b6rEOGvd64PVQHatrTPtd/x12/y6F4nPANa6lQJHrefAXID6ExxoJ1AOxXo9N+lhlK70QQhiUEUooQggh/JAAF0IIg5IAF0IIg5IAF0IIg5IAF0IIg5IAF0IIg5IAF0IIg/r/3ypFt5iISw0AAAAASUVORK5CYII=\n",
"image/png": "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\n",
"text/plain": [
"<Figure size 432x288 with 1 Axes>"
]
......@@ -427,16 +371,16 @@
},
{
"cell_type": "code",
"execution_count": 19,
"execution_count": 22,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"the input words is: complete, works\n",
"the predict words is: of\n",
"the true words is: of\n"
"the input words is: of, william\n",
"the predict words is: shakespeare\n",
"the true words is: shakespeare\n"
]
}
],
......
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或