Created
April 16, 2018 13:44
-
-
Save uduse/84a07e3c33d3deb7be64d31e4d6d64ad to your computer and use it in GitHub Desktop.
Train seq2seq model in Keras without using one-hot encoded data
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"cells": [ | |
{ | |
"metadata": { | |
"ExecuteTime": { | |
"end_time": "2018-04-16T13:40:33.812957Z", | |
"start_time": "2018-04-16T13:40:32.813032Z" | |
}, | |
"trusted": true | |
}, | |
"cell_type": "code", | |
"source": "import numpy as np\nimport keras\nimport keras.backend as K\nfrom keras.layers import *\nfrom keras.models import *\nimport random\n\nmax_len = 30\nvocab_size = 3000\nX = np.random.randn(500, max_len)\nY = np.random.randn(500, max_len)\n\ninput_ = Input(X.shape[1:])\nhidden = Embedding(vocab_size, 2)(input_)\noutput = Dense(vocab_size, activation='softmax')(hidden)\nm = Model(input_, output)\n\ndef loss(y_true, y_pred):\n y_true = K.one_hot(y_true, vocab_size)\n return keras.losses.categorical_crossentropy(y_true, y_pred)\ny_tensor = K.placeholder((None, max_len), dtype='int32')\nm.compile(loss=loss, optimizer='adam', target_tensors=[y_tensor])\n\nm.fit(X, Y, batch_size=128, epochs=10, validation_split=0.1)", | |
"execution_count": 4, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": "Train on 450 samples, validate on 50 samples\nEpoch 1/10\n450/450 [==============================] - 0s 412us/step - loss: 6.7245 - val_loss: 6.6977\nEpoch 2/10\n450/450 [==============================] - 0s 139us/step - loss: 6.7180 - val_loss: 6.6909\nEpoch 3/10\n450/450 [==============================] - 0s 139us/step - loss: 6.7111 - val_loss: 6.6839\nEpoch 4/10\n450/450 [==============================] - 0s 141us/step - loss: 6.7041 - val_loss: 6.6768\nEpoch 5/10\n450/450 [==============================] - 0s 139us/step - loss: 6.6969 - val_loss: 6.6696\nEpoch 6/10\n450/450 [==============================] - 0s 136us/step - loss: 6.6897 - val_loss: 6.6623\nEpoch 7/10\n450/450 [==============================] - 0s 136us/step - loss: 6.6823 - val_loss: 6.6549\nEpoch 8/10\n450/450 [==============================] - 0s 134us/step - loss: 6.6749 - val_loss: 6.6473\nEpoch 9/10\n450/450 [==============================] - 0s 133us/step - loss: 6.6673 - val_loss: 6.6396\nEpoch 10/10\n450/450 [==============================] - 0s 137us/step - loss: 6.6595 - val_loss: 6.6318\n" | |
}, | |
{ | |
"data": { | |
"text/plain": "<keras.callbacks.History at 0x7fd4a6a4fb70>" | |
}, | |
"execution_count": 4, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
] | |
} | |
], | |
"metadata": { | |
"hide_input": false, | |
"kernelspec": { | |
"name": "mermaid", | |
"display_name": "mermaid", | |
"language": "python" | |
}, | |
"language_info": { | |
"name": "python", | |
"version": "3.6.3", | |
"mimetype": "text/x-python", | |
"codemirror_mode": { | |
"name": "ipython", | |
"version": 3 | |
}, | |
"pygments_lexer": "ipython3", | |
"nbconvert_exporter": "python", | |
"file_extension": ".py" | |
}, | |
"toc": { | |
"nav_menu": {}, | |
"number_sections": true, | |
"sideBar": true, | |
"skip_h1_title": false, | |
"toc_cell": false, | |
"toc_position": {}, | |
"toc_section_display": "block", | |
"toc_window_display": false | |
}, | |
"varInspector": { | |
"window_display": false, | |
"cols": { | |
"lenName": 16, | |
"lenType": 16, | |
"lenVar": 40 | |
}, | |
"kernels_config": { | |
"python": { | |
"library": "var_list.py", | |
"delete_cmd_prefix": "del ", | |
"delete_cmd_postfix": "", | |
"varRefreshCmd": "print(var_dic_list())" | |
}, | |
"r": { | |
"library": "var_list.r", | |
"delete_cmd_prefix": "rm(", | |
"delete_cmd_postfix": ") ", | |
"varRefreshCmd": "cat(var_dic_list()) " | |
} | |
}, | |
"types_to_exclude": [ | |
"module", | |
"function", | |
"builtin_function_or_method", | |
"instance", | |
"_Feature" | |
] | |
}, | |
"gist": { | |
"id": "", | |
"data": { | |
"description": "Train seq2seq model in Keras without using one-hot encoded data", | |
"public": true | |
} | |
} | |
}, | |
"nbformat": 4, | |
"nbformat_minor": 2 | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment