上传了文档文件和若干 TODO

docs/source/user/task1.rst

@@ -0,0 +1,3 @@
+=====================
+用 fastNLP 分类
+=====================

tutorials/fastnlp_10min_tutorial.ipynb

@@ -41,7 +41,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [
     {
@@ -63,7 +63,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [
     {
@@ -97,7 +97,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [
     {
@@ -107,7 +107,7 @@
        "'label': 0 type=str}"
       ]
      },
-     "execution_count": 8,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -128,7 +128,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [
     {
@@ -148,7 +148,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [
     {
@@ -168,7 +168,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [
     {
@@ -191,7 +191,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
@@ -221,7 +221,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [
     {
@@ -249,7 +249,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -263,7 +263,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [
     {
@@ -295,17 +295,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "{'raw_sentence': a welcome relief from baseball movies that try too hard to be mythic , this one is a sweet and modest and ultimately winning story . type=str,\n",
-      "'label': 3 type=int,\n",
-      "'words': [4, 1, 1, 18, 1, 1, 13, 1, 1, 1, 8, 26, 1, 5, 35, 1, 11, 4, 1, 10, 1, 10, 1, 1, 1, 2] type=list,\n",
-      "'seq_len': 26 type=int}\n"
+      "{'raw_sentence': the performances are an absolute joy . type=str,\n",
+      "'label': 4 type=int,\n",
+      "'words': [3, 1, 1, 26, 1, 1, 2] type=list,\n",
+      "'seq_len': 7 type=int}\n"
      ]
     }
    ],
@@ -327,9 +327,21 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 12,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "batch_x has:  {'words': tensor([[ 15,  72,  15,  73,  74,   7,   3,  75,   6,   3,  16,  16,\n",
+      "          76,   2],\n",
+      "        [ 15,  72,  15,  73,  74,   7,   3,  75,   6,   3,  16,  16,\n",
+      "          76,   2]])}\n",
+      "batch_y has:  {'label': tensor([ 1,  1])}\n"
+     ]
+    }
+   ],
    "source": [
     "# 如果你们需要做强化学习或者GAN之类的项目，你们也可以使用这些数据预处理的工具\n",
     "from fastNLP.core.batch import Batch\n",
@@ -352,7 +364,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 15,
    "metadata": {},
    "outputs": [
     {
@@ -360,7 +372,7 @@
       "text/plain": [
        "CNNText(\n",
        "  (embed): Embedding(\n",
-       "    (embed): Embedding(59, 50, padding_idx=0)\n",
+       "    77, 50\n",
        "    (dropout): Dropout(p=0.0)\n",
        "  )\n",
        "  (conv_pool): ConvMaxpool(\n",
@@ -377,14 +389,14 @@
        ")"
       ]
      },
-     "execution_count": 17,
+     "execution_count": 15,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
     "from fastNLP.models import CNNText\n",
-    "model = CNNText(embed_num=len(vocab), embed_dim=50, num_classes=5, padding=2, dropout=0.1)\n",
+    "model = CNNText((len(vocab), 50), num_classes=5, padding=2, dropout=0.1)\n",
     "model"
    ]
   },
@@ -448,7 +460,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 16,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -485,7 +497,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 17,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -508,7 +520,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 18,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -517,7 +529,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 19,
    "metadata": {},
    "outputs": [
     {
@@ -525,48 +537,25 @@
      "output_type": "stream",
      "text": [
       "input fields after batch(if batch size is 2):\n",
-      "\tword_seq: (1)type:torch.Tensor (2)dtype:torch.int64, (3)shape:torch.Size([2, 26]) \n",
+      "\tword_seq: (1)type:torch.Tensor (2)dtype:torch.int64, (3)shape:torch.Size([2, 11]) \n",
       "target fields after batch(if batch size is 2):\n",
       "\tlabel_seq: (1)type:torch.Tensor (2)dtype:torch.int64, (3)shape:torch.Size([2]) \n",
-      "\n",
-      "training epochs started 2019-01-12 17-07-51\n"
+      "\n"
      ]
     },
     {
-     "data": {
-      "text/plain": [
-       "HBox(children=(IntProgress(value=0, layout=Layout(flex='2'), max=10), HTML(value='')), layout=Layout(display='…"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Evaluation at Epoch 1/5. Step:2/10. AccuracyMetric: acc=0.425926\n",
-      "Evaluation at Epoch 2/5. Step:4/10. AccuracyMetric: acc=0.425926\n",
-      "Evaluation at Epoch 3/5. Step:6/10. AccuracyMetric: acc=0.611111\n",
-      "Evaluation at Epoch 4/5. Step:8/10. AccuracyMetric: acc=0.648148\n",
-      "Evaluation at Epoch 5/5. Step:10/10. AccuracyMetric: acc=0.703704\n",
-      "\n",
-      "In Epoch:5/Step:10, got best dev performance:AccuracyMetric: acc=0.703704\n",
-      "Reloaded the best model.\n"
+     "ename": "NameError",
+     "evalue": "\nProblems occurred when calling CNNText.forward(self, words, seq_len=None)\n\tmissing param: ['words']\n\tunused field: ['word_seq']\n\tSuggestion: You need to provide ['words'] in DataSet and set it as input. ",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
+      "\u001b[0;32m<ipython-input-19-ff7d68caf88a>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      7\u001b[0m                           \u001b[0msave_path\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      8\u001b[0m                           \u001b[0mbatch_size\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m32\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 9\u001b[0;31m                           n_epochs=5)\n\u001b[0m\u001b[1;32m     10\u001b[0m \u001b[0moverfit_trainer\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtrain\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m/Users/fdujyn/anaconda3/lib/python3.6/site-packages/fastNLP/core/trainer.py\u001b[0m in \u001b[0;36m__init__\u001b[0;34m(self, train_data, model, optimizer, loss, batch_size, sampler, update_every, n_epochs, print_every, dev_data, metrics, metric_key, validate_every, save_path, prefetch, use_tqdm, device, callbacks, check_code_level)\u001b[0m\n\u001b[1;32m    447\u001b[0m             _check_code(dataset=train_data, model=model, losser=losser, metrics=metrics, dev_data=dev_data,\n\u001b[1;32m    448\u001b[0m                         \u001b[0mmetric_key\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mmetric_key\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcheck_level\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mcheck_code_level\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 449\u001b[0;31m                         batch_size=min(batch_size, DEFAULT_CHECK_BATCH_SIZE))\n\u001b[0m\u001b[1;32m    450\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    451\u001b[0m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtrain_data\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtrain_data\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m/Users/fdujyn/anaconda3/lib/python3.6/site-packages/fastNLP/core/trainer.py\u001b[0m in \u001b[0;36m_check_code\u001b[0;34m(dataset, model, losser, metrics, batch_size, dev_data, metric_key, check_level)\u001b[0m\n\u001b[1;32m    808\u001b[0m             \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0minfo_str\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    809\u001b[0m             _check_forward_error(forward_func=model.forward, dataset=dataset,\n\u001b[0;32m--> 810\u001b[0;31m                                  batch_x=batch_x, check_level=check_level)\n\u001b[0m\u001b[1;32m    811\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    812\u001b[0m         \u001b[0mrefined_batch_x\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0m_build_args\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmodel\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mforward\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mbatch_x\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m/Users/fdujyn/anaconda3/lib/python3.6/site-packages/fastNLP/core/utils.py\u001b[0m in \u001b[0;36m_check_forward_error\u001b[0;34m(forward_func, batch_x, dataset, check_level)\u001b[0m\n\u001b[1;32m    594\u001b[0m             \u001b[0msugg_str\u001b[0m \u001b[0;34m+=\u001b[0m \u001b[0msuggestions\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    595\u001b[0m         \u001b[0merr_str\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m'\\n'\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0;34m'\\n'\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mjoin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0merrs\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0;34m'\\n\\tSuggestion: '\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0msugg_str\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 596\u001b[0;31m         \u001b[0;32mraise\u001b[0m \u001b[0mNameError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0merr_str\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    597\u001b[0m     \u001b[0;32mif\u001b[0m \u001b[0m_unused\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    598\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mcheck_level\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0mWARNING_CHECK_LEVEL\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;31mNameError\u001b[0m: \nProblems occurred when calling CNNText.forward(self, words, seq_len=None)\n\tmissing param: ['words']\n\tunused field: ['word_seq']\n\tSuggestion: You need to provide ['words'] in DataSet and set it as input. "
      ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "{'best_eval': {'AccuracyMetric': {'acc': 0.703704}},\n",
-       " 'best_epoch': 5,\n",
-       " 'best_step': 10,\n",
-       " 'seconds': 0.62}"
-      ]
-     },
-     "execution_count": 21,
-     "metadata": {},
-     "output_type": "execute_result"
     }
    ],
    "source": [

tutorials/fastnlp_test_tutorial.ipynb

@@ -89,7 +89,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.4"
+   "version": "3.6.7"
   }
  },
  "nbformat": 4,