new tests

.idea/workspace.xml

@@ -20,10 +20,20 @@
   </component>
   <component name="ChangeListManager">
     <list default="true" id="828778c9-9d97-422f-a727-18ddbd059b85" name="Default Changelist" comment="detecting digits">
+      <change afterPath="$PROJECT_DIR$/coder/517.png" afterDir="false" />
+      <change afterPath="$PROJECT_DIR$/coder/test1.png" afterDir="false" />
+      <change afterPath="$PROJECT_DIR$/coder/test2.png" afterDir="false" />
       <change beforePath="$PROJECT_DIR$/.idea/workspace.xml" beforeDir="false" afterPath="$PROJECT_DIR$/.idea/workspace.xml" afterDir="false" />
-      <change beforePath="$PROJECT_DIR$/coder/coder.py" beforeDir="false" afterPath="$PROJECT_DIR$/coder/coder.py" afterDir="false" />
       <change beforePath="$PROJECT_DIR$/coder/digits_recognizer.py" beforeDir="false" afterPath="$PROJECT_DIR$/coder/digits_recognizer.py" afterDir="false" />
+      <change beforePath="$PROJECT_DIR$/coder/ll.png" beforeDir="false" />
       <change beforePath="$PROJECT_DIR$/coder/rocognizer.py" beforeDir="false" afterPath="$PROJECT_DIR$/coder/rocognizer.py" afterDir="false" />
+      <change beforePath="$PROJECT_DIR$/coder/test.jpg" beforeDir="false" />
+      <change beforePath="$PROJECT_DIR$/coder/test1.jpg" beforeDir="false" />
+      <change beforePath="$PROJECT_DIR$/coder/test3.png" beforeDir="false" afterPath="$PROJECT_DIR$/coder/test3.png" afterDir="false" />
+      <change beforePath="$PROJECT_DIR$/coder/test5.png" beforeDir="false" />
+      <change beforePath="$PROJECT_DIR$/coder/test9.png" beforeDir="false" />
+      <change beforePath="$PROJECT_DIR$/coder/testno.png" beforeDir="false" />
+      <change beforePath="$PROJECT_DIR$/coder/train_nn.py" beforeDir="false" />
     </list>
     <option name="SHOW_DIALOG" value="false" />
     <option name="HIGHLIGHT_CONFLICTS" value="true" />
@@ -72,7 +82,7 @@
     <property name="RunOnceActivity.ShowReadmeOnStart" value="true" />
     <property name="SHARE_PROJECT_CONFIGURATION_FILES" value="true" />
     <property name="WebServerToolWindowFactoryState" value="false" />
-    <property name="last_opened_file_path" value="$PROJECT_DIR$/coder" />
+    <property name="last_opened_file_path" value="$USER_HOME$/Downloads/digitRecognition" />
     <property name="restartRequiresConfirmation" value="false" />
     <property name="settings.editor.selected.configurable" value="com.jetbrains.python.configuration.PyActiveSdkModuleConfigurable" />
   </component>
@@ -82,7 +92,7 @@
       <recent name="C:\Users\Pawel Lukaszewicz\PycharmProjects\AL-2020\coder\dataset" />
     </key>
   </component>
-  <component name="RunManager" selected="Python.digits_recognizer">
+  <component name="RunManager" selected="Python.rocognizer">
     <configuration default="true" type="PythonConfigurationType" factoryName="Python">
       <module name="wozek" />
       <option name="INTERPRETER_OPTIONS" value="" />
@@ -131,6 +141,9 @@
       <module name="wozek" />
       <option name="INTERPRETER_OPTIONS" value="" />
       <option name="PARENT_ENVS" value="true" />
+      <envs>
+        <env name="PYTHONUNBUFFERED" value="1" />
+      </envs>
       <option name="SDK_HOME" value="" />
       <option name="WORKING_DIRECTORY" value="$PROJECT_DIR$/coder" />
       <option name="IS_MODULE_SDK" value="true" />
@@ -218,8 +231,8 @@
     </list>
     <recent_temporary>
       <list>
-        <item itemvalue="Python.digits_recognizer" />
         <item itemvalue="Python.rocognizer" />
+        <item itemvalue="Python.digits_recognizer" />
         <item itemvalue="Python.coder" />
         <item itemvalue="Python.z8" />
         <item itemvalue="Python.image" />
@@ -265,6 +278,9 @@
       <workItem from="1590575699320" duration="792000" />
       <workItem from="1590766924835" duration="10060000" />
       <workItem from="1590929874289" duration="7728000" />
+      <workItem from="1590938377522" duration="176000" />
+      <workItem from="1590944305590" duration="10043000" />
+      <workItem from="1590961284964" duration="2200000" />
     </task>
     <task id="LOCAL-00001" summary="create Shelf">
       <created>1589815443652</created>
@@ -364,7 +380,14 @@
       <option name="project" value="LOCAL" />
       <updated>1590846768877</updated>
     </task>
-    <option name="localTasksCounter" value="15" />
+    <task id="LOCAL-00015" summary="img is cropped and transformed to torch">
+      <created>1590938465634</created>
+      <option name="number" value="00015" />
+      <option name="presentableId" value="LOCAL-00015" />
+      <option name="project" value="LOCAL" />
+      <updated>1590938465634</updated>
+    </task>
+    <option name="localTasksCounter" value="16" />
     <servers />
   </component>
   <component name="TypeScriptGeneratedFilesManager">
@@ -398,13 +421,18 @@
     <MESSAGE value="going to pytorch on conda eve" />
     <MESSAGE value="add coder.py" />
     <MESSAGE value="detecting digits" />
-    <option name="LAST_COMMIT_MESSAGE" value="detecting digits" />
+    <MESSAGE value="img is cropped and transformed to torch" />
+    <option name="LAST_COMMIT_MESSAGE" value="img is cropped and transformed to torch" />
   </component>
   <component name="WindowStateProjectService">
-    <state x="115" y="162" key="#com.intellij.refactoring.safeDelete.UnsafeUsagesDialog" timestamp="1589923610328">
+    <state x="115" y="162" key="#com.intellij.refactoring.safeDelete.UnsafeUsagesDialog" timestamp="1590956217731">
       <screen x="0" y="0" width="1536" height="824" />
     </state>
-    <state x="115" y="162" key="#com.intellij.refactoring.safeDelete.UnsafeUsagesDialog/0.0.1536.824@0.0.1536.824" timestamp="1589923610328" />
+    <state x="115" y="162" key="#com.intellij.refactoring.safeDelete.UnsafeUsagesDialog/0.0.1536.824@0.0.1536.824" timestamp="1590956217731" />
+    <state x="549" y="167" key="FileChooserDialogImpl" timestamp="1590962272315">
+      <screen x="0" y="0" width="1536" height="824" />
+    </state>
+    <state x="549" y="167" key="FileChooserDialogImpl/0.0.1536.824@0.0.1536.824" timestamp="1590962272315" />
     <state width="1493" height="208" key="GridCell.Tab.0.bottom" timestamp="1589845242796">
       <screen x="0" y="0" width="1536" height="824" />
     </state>
@@ -425,10 +453,10 @@
       <screen x="0" y="0" width="1536" height="824" />
     </state>
     <state x="277" y="57" key="SettingsEditor/0.0.1536.824@0.0.1536.824" timestamp="1590443566792" />
-    <state x="361" y="145" key="Vcs.Push.Dialog.v2" timestamp="1590846777672">
+    <state x="361" y="145" key="Vcs.Push.Dialog.v2" timestamp="1590938471243">
       <screen x="0" y="0" width="1536" height="824" />
     </state>
-    <state x="361" y="145" key="Vcs.Push.Dialog.v2/0.0.1536.824@0.0.1536.824" timestamp="1590846777672" />
+    <state x="361" y="145" key="Vcs.Push.Dialog.v2/0.0.1536.824@0.0.1536.824" timestamp="1590938471243" />
     <state x="54" y="145" width="672" height="678" key="search.everywhere.popup" timestamp="1590930912296">
       <screen x="0" y="0" width="1536" height="824" />
     </state>

coder/digits_recognizer.py

@@ -75,6 +75,9 @@ print("\nTraining Time (in minutes) =", (time() - time0) / 60)
 
 images, labels = next(iter(val_loader))
 img = images[0].view(1, 784)
+print(type(img))
+print(img.size())
+
 with torch.no_grad():
     logps = model(img)
 ps = torch.exp(logps)

coder/rocognizer.py

@@ -1,17 +1,19 @@
-import numpy as np
-import argparse
-import imutils
 import cv2
 import matplotlib.pyplot as plt
 import torch
-from matplotlib import cm
+from PIL.Image import Image
 from torch import nn
-from PIL import Image
-from skimage.feature import hog
 from torchvision.transforms import transforms
 
+def white_bg_square(img):
+    "return a white-background-color image having the img in exact center"
+    size = (max(img.size),)*2
+    layer = Image.new('RGB', size, (255, 255, 255))
+    layer.paste(img, tuple(map(lambda x:(x[0]-x[1])/2, zip(size, img.size))))
+    return layer
+
 code = []
-path = "test1.jpg"
+path = "test5.jpg"
 
 transform = transforms.Compose([transforms.ToTensor(),
                                 transforms.Normalize((0.5,), (0.5,)),
@@ -45,27 +47,19 @@ model.eval()
 
 for rect in rects:
     # Crop image
-    crop_img = img[rect[1]:rect[1] + rect[3], rect[0]:rect[0] + rect[2]]
+    crop_img = img[rect[1]:rect[1] + rect[3] + 10, rect[0]:rect[0] + rect[2] + 10, 0]
-    plt.imshow(crop_img)
-    plt.show()
-
     # Resize the image
-    roi = cv2.resize(crop_img, (28, 28), interpolation=cv2.INTER_AREA)
+    roi = cv2.resize(crop_img, (28, 28), interpolation=cv2.INTER_LINEAR)
+    roi = cv2.dilate(roi, (3, 3))
     plt.imshow(roi)
     plt.show()
-    im = Image.fromarray(roi)
+    im = transform(roi)
-
+    im = im.view(1, 784)
-    im = transform(im)
-    print(im)
-    plt.imshow(im)
-    plt.show()
-
     with torch.no_grad():
-        logps = model(im)
+        logps = model(im.float())
     ps = torch.exp(logps)
-    print(ps[0])
     probab = list(ps.numpy()[0])
     print("Predicted Digit =", probab.index(max(probab)))
 
-cv2.imshow("Resulting Image with Rectangular ROIs", img)
+cv2.imshow("Code", img)
 cv2.waitKey()

coder/train_nn.py

@@ -1,30 +0,0 @@
-import matplotlib.pyplot as plt
-import numpy as np
-from numpy import asarray
-import pygame
-from sklearn import datasets
-from sklearn.neural_network import MLPClassifier
-from sklearn.metrics import accuracy_score
-from PIL import Image
-
-
-# recznie napisane cyfry
-digits = datasets.load_digits()
-
-y = digits.target
-x = digits.images.reshape((len(digits.images), -1))
-
-x_train = x[:1000000]
-y_train = y[:1000000]
-x_test = x[1000:]
-y_test = y[1000:]
-
-mlp = MLPClassifier(hidden_layer_sizes=(15,), activation='logistic', alpha=1e-4,
-                    solver='sgd', tol=1e-4, random_state=1,
-                    learning_rate_init=.1, verbose=True)
-
-mlp.fit(x_train, y_train)
-
-predictions = mlp.predict(x_test)
-print(accuracy_score(y_test, predictions))
-print(x_test[1])