DSL Encoding - Revision history

Ed at 17:47, 21 September 2020

2020-09-21T17:47:35Z

2020-09-21T17:34:30Z

2020-09-20T16:29:10Z

2019-05-30T15:40:29Z

2019-05-30T15:37:30Z

2019-05-30T15:28:29Z

2019-05-19T21:36:45Z

2019-05-19T21:36:22Z

2019-05-10T21:41:05Z

2019-05-10T21:40:13Z

@@ Line 1: / Line 1: @@
 {{Project
-|Has project output=
+|Has project output=Tool
 |Has sponsor=Kauffman Incubator Project
 |Has title=DSL Encoding

@@ Line 1: / Line 1: @@
 {{Project
 |Has sponsor=Kauffman Incubator Project
 |Has title=DSL Encoding

@@ Line 1: / Line 1: @@
 {{Project
 |Has title=DSL Encoding
 |Has owner=Hiep Nguyen

← Older revision		Revision as of 15:40, 30 May 2019
Line 163:		Line 163:
	A sample training code lives in		A sample training code lives in
	E:\projects\embedding\Web_extractor_model\train_sample.py		E:\projects\embedding\Web_extractor_model\train_sample.py
		+
		+	In the '''utils.py''' file, there are a few hyperparameters to remember.
		+
		+	max_len: the length of each training point
		+
		+	step: the number of steps we want to move to generate the next training point
		+
		+	num_units: LSTM units, a safe choice is 128
		+
		+	len_unique_chars: total number of unique tokens in all training data

@@ Line 158: / Line 158: @@
      prediction = tf.add(tf.matmul(states.h, W), b,name='prediction')
      return prediction
 A sample training code lives in
   E:\projects\embedding\Web_extractor_model\train_sample.py

← Older revision		Revision as of 15:28, 30 May 2019
Line 160:		Line 160:

	A sample training code lives in		A sample training code lives in
−	E:\projects\embedding\train_sample.py	+	E:\projects\embedding\Web_extractor_model\train_sample.py

← Older revision		Revision as of 21:36, 19 May 2019
Line 160:		Line 160:

	A sample training code lives in		A sample training code lives in
−	E:\projects\embedding	+	E:\projects\embedding\train_sample.py

← Older revision		Revision as of 21:36, 19 May 2019
Line 158:		Line 158:
	prediction = tf.add(tf.matmul(states.h, W), b,name='prediction')		prediction = tf.add(tf.matmul(states.h, W), b,name='prediction')
	return prediction		return prediction
		+
		+	A sample training code lives in
		+	E:\projects\embedding

@@ Line 141: / Line 141: @@
      '''
      if tf.test.is_gpu_available():
-         lstm = tf.contrib.cudnn_rnn.CudnnCompatibleLSTMCell(num_units)
+         lstm = tf.contrib.cudnn_rnn.CudnnCompatibleLSTMCell(num_units) #num_units is the number of hidden units in the LSTM cell.
      else:
          lstm = tf.nn.rnn_cell.LSTMCell(num_units,forget_bias=1.0)