[GitHub] nswamy closed pull request #12950: Update dec example

[GitBox <gi...@apache.org>]

nswamy closed pull request #12950: Update dec example
URL: https://github.com/apache/incubator-mxnet/pull/12950
 
 
   

This is a PR merged from a forked repository.
As GitHub hides the original diff on merge, it is displayed below for
the sake of provenance:

As this is a foreign pull request (from a fork), the diff is supplied
below (as it won't show otherwise due to GitHub magic):

diff --git a/example/deep-embedded-clustering/README.md b/example/deep-embedded-clustering/README.md
index 90803d2ed12..3972f90bda4 100644
--- a/example/deep-embedded-clustering/README.md
+++ b/example/deep-embedded-clustering/README.md
@@ -1,9 +1,18 @@
 # DEC Implementation
 This is based on the paper `Unsupervised deep embedding for clustering analysis` by  Junyuan Xie, Ross Girshick, and Ali Farhadi
 
+Abstract:
+
+Clustering is central to many data-driven application domains and has been studied extensively in terms of distance functions and grouping algorithms. Relatively little work has focused on learning representations for clustering. In this paper, we propose Deep Embedded Clustering (DEC), a method that simultaneously learns feature representations and cluster assignments using deep neural networks. DEC learns a mapping from the data space to a lower-dimensional feature space in which it iteratively optimizes a clustering objective. Our experimental evaluations on image and text corpora show significant improvement over state-of-the-art methods.
+
+
 ## Prerequisite
   - Install Scikit-learn: `python -m pip install --user sklearn`
   - Install SciPy: `python -m pip install --user scipy`
 
+## Data
+
+The script is using MNIST dataset.
+
 ## Usage
-run `python dec.py`
\ No newline at end of file
+run `python dec.py`
diff --git a/example/deep-embedded-clustering/data.py b/example/deep-embedded-clustering/data.py
index 9fd472e6a8b..3649990dbbb 100644
--- a/example/deep-embedded-clustering/data.py
+++ b/example/deep-embedded-clustering/data.py
@@ -19,20 +19,21 @@
 from __future__ import print_function
 
 import os
+
+import mxnet as mx
 import numpy as np
-from sklearn.datasets import fetch_mldata
 
 
 def get_mnist():
     """ Gets MNIST dataset """
 
     np.random.seed(1234) # set seed for deterministic ordering
-    data_path = os.path.dirname(os.path.abspath(os.path.expanduser(__file__)))
-    data_path = os.path.join(data_path, '../../data')
-    mnist = fetch_mldata('MNIST original', data_home=data_path)
-    p = np.random.permutation(mnist.data.shape[0])
-    X = mnist.data[p].astype(np.float32)*0.02
-    Y = mnist.target[p]
+    mnist_data = mx.test_utils.get_mnist()
+    X = np.concatenate([mnist_data['train_data'], mnist_data['test_data']])
+    Y = np.concatenate([mnist_data['train_label'], mnist_data['test_label']])
+    p = np.random.permutation(X.shape[0])
+    X = X[p].reshape((X.shape[0], -1)).astype(np.float32)*5
+    Y = Y[p]
     return X, Y
 
 
diff --git a/example/deep-embedded-clustering/dec.py b/example/deep-embedded-clustering/dec.py
index 44e582d9f94..d7594703cfc 100644
--- a/example/deep-embedded-clustering/dec.py
+++ b/example/deep-embedded-clustering/dec.py
@@ -19,9 +19,6 @@
 from __future__ import print_function
 import sys
 import os
-# code to automatically download dataset
-curr_path = os.path.dirname(os.path.abspath(os.path.expanduser(__file__)))
-sys.path = [os.path.join(curr_path, "../autoencoder")] + sys.path
 import mxnet as mx
 import numpy as np
 import data
@@ -33,14 +30,14 @@
 import logging
 
 def cluster_acc(Y_pred, Y):
-  from sklearn.utils.linear_assignment_ import linear_assignment
-  assert Y_pred.size == Y.size
-  D = max(Y_pred.max(), Y.max())+1
-  w = np.zeros((D,D), dtype=np.int64)
-  for i in range(Y_pred.size):
-    w[Y_pred[i], int(Y[i])] += 1
-  ind = linear_assignment(w.max() - w)
-  return sum([w[i,j] for i,j in ind])*1.0/Y_pred.size, w
+    from sklearn.utils.linear_assignment_ import linear_assignment
+    assert Y_pred.size == Y.size
+    D = max(Y_pred.max(), Y.max())+1
+    w = np.zeros((D,D), dtype=np.int64)
+    for i in range(Y_pred.size):
+        w[Y_pred[i], int(Y[i])] += 1
+    ind = linear_assignment(w.max() - w)
+    return sum([w[i,j] for i,j in ind])*1.0/Y_pred.size, w
 
 class DECModel(model.MXModel):
     class DECLoss(mx.operator.NumpyOp):
@@ -87,9 +84,9 @@ def setup(self, X, num_centers, alpha, save_to='dec_model'):
         ae_model = AutoEncoderModel(self.xpu, [X.shape[1],500,500,2000,10], pt_dropout=0.2)
         if not os.path.exists(save_to+'_pt.arg'):
             ae_model.layerwise_pretrain(X_train, 256, 50000, 'sgd', l_rate=0.1, decay=0.0,
-                                        lr_scheduler=mx.misc.FactorScheduler(20000,0.1))
+                                        lr_scheduler=mx.lr_scheduler.FactorScheduler(20000,0.1))
             ae_model.finetune(X_train, 256, 100000, 'sgd', l_rate=0.1, decay=0.0,
-                              lr_scheduler=mx.misc.FactorScheduler(20000,0.1))
+                              lr_scheduler=mx.lr_scheduler.FactorScheduler(20000,0.1))
             ae_model.save(save_to+'_pt.arg')
             logging.log(logging.INFO, "Autoencoder Training error: %f"%ae_model.eval(X_train))
             logging.log(logging.INFO, "Autoencoder Validation error: %f"%ae_model.eval(X_val))
@@ -160,6 +157,8 @@ def refresh(i):
 
 def mnist_exp(xpu):
     X, Y = data.get_mnist()
+    if not os.path.isdir('data'):
+        os.makedirs('data')
     dec_model = DECModel(xpu, X, 10, 1.0, 'data/mnist')
     acc = []
     for i in [10*(2**j) for j in range(9)]:


 

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


With regards,
Apache Git Services