Added code

Notebooks/RESNET152/indiandanceprediction-usingmonk.py

+#!/usr/bin/env python
+# coding: utf-8
+
+# In[1]:
+
+
+pip install tornado --upgrade --use-feature=2020-resolver
+
+
+# In[2]:
+
+
+get_ipython().system('git clone https://github.com/Tessellate-Imaging/monk_v1.git')
+get_ipython().system('cd monk_v1/installation/Misc && pip install -r requirements_kaggle.txt --use-feature=2020-resolver')
+
+
+# In[3]:
+
+
+pip install bokeh
+
+
+# In[4]:
+
+
+pip install monk --upgrade
+
+
+# In[5]:
+
+
+pip install -U monk-kaggle
+
+
+# In[6]:
+
+
+import numpy as np # linear algebra
+import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
+import matplotlib.pyplot as plt
+from PIL import Image, ImageDraw
+import os
+import sys
+
+
+# In[7]:
+
+
+sys.path.append("/kaggle/working/monk_v1/monk/");
+from gluon_prototype import prototype
+
+
+# In[8]:
+
+
+gtf = prototype(verbose=1);
+gtf.Prototype("Dance_Form", "Indian_Classical_Dance_Form_Prediction");
+
+
+# In[10]:
+
+
+import csv
+
+
+# In[11]:
+
+
+#to read the entries from train.csv
+data = []
+with open('../input/dform-gold/dataset1/train.csv', 'r',) as file:
+    reader = csv.reader(file, delimiter = ',')
+    i = 0
+    for row in reader:
+        if i==0:
+            i = i + 1
+            continue
+        data.append(row);
+print(data)
+
+
+# In[12]:
+
+
+#used for cross validation, k : #iterations, div : #images in a division
+k = 4
+div = len(data) / k
+
+
+# In[15]:
+
+
+#to shuffle data and get a set which classifies all 8 classes
+print("division:",div)
+
+#shuffling data
+
+import pandas as pd
+
+flag = False
+
+while (not flag):
+    
+    flag = True
+    
+    pdata = pd.DataFrame(data)
+
+    pdata = pdata.sample(frac = 1) 
+    
+    data = pdata.values.tolist()
+
+
+    for i in range(k):
+
+        train = (data[0:(i * int(div))]) 
+        test = data[ i * int(div) : (i + 1) * int(div) ]
+        for x in data[(i+1) * int(div) : ]:
+            train.append(x)
+        if(len(pd.DataFrame(train).groupby(1).count()[0]) < 8 or len(pd.DataFrame(test).groupby(1).count()[0]) < 8):
+            flag = False
+            break
+
+
+print(data)
+
+
+# In[18]:
+
+
+#performed cross validation and created confusion matrix for cross validation
+'''
+    Model : resnet152_v1
+    #epochs:20
+    optimizer:adam
+    batch_size:7
+    learning_rate:0.005
+    data shuffle : true
+        
+'''
+'''
+    Result: 
+    Epochs for every iteration:
+    test accuracy, train accuracy, test loss, train loss
+    Summary of the model
+    Best accuracy after every iteration
+    Final average accuracy taken from the #iterations
+    
+'''
+accuracy = 0;
+for i in range(k):
+    
+    train = (data[0:(i * int(div))]) 
+    test = data[ i * int(div) : (i + 1) * int(div) ]
+    for x in data[(i+1) * int(div) : ]:
+        train.append(x)
+    print(len(pd.DataFrame(train).groupby(1).count()[0]))
+    print(pd.DataFrame(train).groupby(1).count())
+    print(len(pd.DataFrame(test).groupby(1).count()[0]))
+    print(pd.DataFrame(test).groupby(1).count())
+    a = pd.DataFrame(train, columns = ['Image', 'target']);
+    a.to_csv("train_slot.csv", index=False);
+    a = pd.DataFrame(test, columns = ['Image', 'target']);
+    a.to_csv("test_slot.csv", index=False);
+
+    gtf = prototype(verbose=1);
+    gtf.Prototype("Dance_Form", "resnet152_V1");
+
+
+
+    gtf.Default(dataset_path=["../input/dform-gold/dataset1/train", "../input/dform-gold/dataset1/train"], path_to_csv=["train_slot.csv","test_slot.csv"], model_name="resnet152_v1", freeze_base_network=True, num_epochs=20);
+    gtf.update_shuffle_data(True);
+    gtf.optimizer_adam(0.001);
+    gtf.update_batch_size(7);
+    gtf.update_learning_rate(0.005);
+
+    gtf.Reload()
+
+    gtf.Train();
+    
+    combined = [];
+    predictions_dict = {};
+    j = 0
+    
+    with open('test_slot.csv', 'r',) as file:
+        reader = csv.reader(file, delimiter = ',')
+        for row in reader:
+            if(j == 0):
+                j = j + 1
+                continue
+            img_name = "../input/dform-gold/dataset1/train/" + row[0];
+            predictions = gtf.Infer(img_name=img_name);
+            id_ = row[0]
+            label = predictions["predicted_class"];    
+            combined.append([id_, label]);
+            predictions_dict[id_] = label;
+
+    print(predictions_dict)
+    print("predictions\n\n\n\n\n")
+    print(combined)
+    gtf.Summary()
+    gtf.EDA(show_img=True, save_img=True);
+    # print(gtf.EDA(show_img=True, save_img=True))
+    import csv
+    import numpy as np
+    confusion_mat = {
+
+                     'bharatanatyam':{'bharatanatyam':0,'kathak':0,'kathakali':0,'kuchipudi':0,'manipuri':0,'mohiniyattam':0,'odissi':0,'sattriya':0}, 
+                     'kathak':{'bharatanatyam':0,'kathak':0,'kathakali':0,'kuchipudi':0,'manipuri':0,'mohiniyattam':0,'odissi':0,'sattriya':0},
+                     'kathakali':{'bharatanatyam':0,'kathak':0,'kathakali':0,'kuchipudi':0,'manipuri':0,'mohiniyattam':0,'odissi':0,'sattriya':0},
+                     'kuchipudi':{'bharatanatyam':0,'kathak':0,'kathakali':0,'kuchipudi':0,'manipuri':0,'mohiniyattam':0,'odissi':0,'sattriya':0},
+                     'manipuri':{'bharatanatyam':0,'kathak':0,'kathakali':0,'kuchipudi':0,'manipuri':0,'mohiniyattam':0,'odissi':0,'sattriya':0},
+                     'mohiniyattam':{'bharatanatyam':0,'kathak':0,'kathakali':0,'kuchipudi':0,'manipuri':0,'mohiniyattam':0,'odissi':0,'sattriya':0},
+                     'odissi':{'bharatanatyam':0,'kathak':0,'kathakali':0,'kuchipudi':0,'manipuri':0,'mohiniyattam':0,'odissi':0,'sattriya':0},
+                     'sattriya':{'bharatanatyam':0,'kathak':0,'kathakali':0,'kuchipudi':0,'manipuri':0,'mohiniyattam':0,'odissi':0,'sattriya':0}
+
+                    }
+    correct = 0
+    with open('test_slot.csv', 'r',) as file:
+        reader = csv.reader(file, delimiter = ',')
+        j = 0
+        for gold_label in reader:
+            if j == 0:
+                j = j + 1
+                continue
+            confusion_mat[gold_label[1]][predictions_dict[gold_label[0]]] = confusion_mat[gold_label[1]][predictions_dict[gold_label[0]]] + 1
+            if(gold_label[1] == predictions_dict[gold_label[0]]):
+                correct = correct + 1
+            
+    accuracy_of_iter = correct / div
+    print("correct",correct,"#images",div)
+    print("accuracy for", i, "th iteration:", accuracy_of_iter)
+    accuracy = accuracy + accuracy_of_iter
+    print(confusion_mat)
+
+print("Overall accuracy:", accuracy / k)
+
+
+# In[19]:
+
+
+'''
+checking the model on test by comparing the gold labels of the test data and the prediction of model
+Creating confusion Matrix(real classes vs predicted ones)
+Calculating Final test accuracy
+'''
+confusion_mat = {
+
+                     'bharatanatyam':{'bharatanatyam':0,'kathak':0,'kathakali':0,'kuchipudi':0,'manipuri':0,'mohiniyattam':0,'odissi':0,'sattriya':0}, 
+                     'kathak':{'bharatanatyam':0,'kathak':0,'kathakali':0,'kuchipudi':0,'manipuri':0,'mohiniyattam':0,'odissi':0,'sattriya':0},
+                     'kathakali':{'bharatanatyam':0,'kathak':0,'kathakali':0,'kuchipudi':0,'manipuri':0,'mohiniyattam':0,'odissi':0,'sattriya':0},
+                     'kuchipudi':{'bharatanatyam':0,'kathak':0,'kathakali':0,'kuchipudi':0,'manipuri':0,'mohiniyattam':0,'odissi':0,'sattriya':0},
+                     'manipuri':{'bharatanatyam':0,'kathak':0,'kathakali':0,'kuchipudi':0,'manipuri':0,'mohiniyattam':0,'odissi':0,'sattriya':0},
+                     'mohiniyattam':{'bharatanatyam':0,'kathak':0,'kathakali':0,'kuchipudi':0,'manipuri':0,'mohiniyattam':0,'odissi':0,'sattriya':0},
+                     'odissi':{'bharatanatyam':0,'kathak':0,'kathakali':0,'kuchipudi':0,'manipuri':0,'mohiniyattam':0,'odissi':0,'sattriya':0},
+                     'sattriya':{'bharatanatyam':0,'kathak':0,'kathakali':0,'kuchipudi':0,'manipuri':0,'mohiniyattam':0,'odissi':0,'sattriya':0}
+
+                    }
+j = 0
+combined = []
+correct = 0
+with open('../input/dform-gold/dataset1/gold_labels.csv', 'r',) as file:
+    reader = csv.reader(file, delimiter = ',')
+    for gold_label in reader:
+        if(j == 0):
+            j = j + 1
+            continue
+        img_name = "../input/dform-gold/dataset1/test/" + gold_label[0];
+        predictions = gtf.Infer(img_name=img_name);
+        id_ = gold_label[0]
+        label = predictions["predicted_class"];    
+        combined.append([id_, label]);
+        confusion_mat[gold_label[1]][label] = confusion_mat[gold_label[1]][label] + 1
+        if(gold_label[1] == label):
+            correct = correct + 1
+#         predictions_dict[id_] = label;
+print("#correct labels ", correct, 'out of',len(combined))
+print("test accuracy :", correct / len(combined))
+conf_mat = pd.DataFrame(confusion_mat)
+print(conf_mat)
+
+
+# In[ ]:
+
+
+
+