melNET_test_src.py

import os
import tensorflow as tf
import numpy as np
import cv2
import csv

SCALAR_RED = (0.0, 0.0, 255.0)
SCALAR_BLUE = (255.0, 0.0, 0.0)


#######################################################################################################################
def main(test_path, weight_path, save_performance, show_detection, ground_truth, save_dir):

    print("starting program . . .")

    # module-level variables ###########################################################################################
    global RETRAINED_LABELS_TXT_FILE_LOC
    RETRAINED_LABELS_TXT_FILE_LOC = weight_path + "/" + "retrained_labels.txt"
    global RETRAINED_GRAPH_PB_FILE_LOC
    RETRAINED_GRAPH_PB_FILE_LOC = weight_path + "/" + "retrained_graph.pb"

    global TEST_IMAGES_DIR
    TEST_IMAGES_DIR = test_path

    if not checkIfNecessaryPathsAndFilesExist():
        return
    # end if

    # get a list of classifications from the labels file
    classifications = []
    # for each line in the label file . . .
    for currentLine in tf.gfile.GFile(RETRAINED_LABELS_TXT_FILE_LOC):
        # remove the carriage return
        classification = currentLine.rstrip()
        # and append to the list
        classifications.append(classification)
    # end for

    # show the classifications to prove out that we were able to read the label file successfully
    print("classifications = " + str(classifications))

    # load the graph from file
    with tf.gfile.FastGFile(RETRAINED_GRAPH_PB_FILE_LOC, 'rb') as retrainedGraphFile:
        # instantiate a GraphDef object
        graphDef = tf.GraphDef()
        # read in retrained graph into the GraphDef object
        graphDef.ParseFromString(retrainedGraphFile.read())
        # import the graph into the current default Graph, note that we don't need to be concerned with the return value
        _ = tf.import_graph_def(graphDef, name='')
    # end with

    # if the test image directory listed above is not valid, show an error message and bail
    if not os.path.isdir(TEST_IMAGES_DIR):
        print("the test image directory does not seem to be a valid directory, check file / directory paths")
        return
    # end if

    # Creating a csv file
    if save_performance:
        result_path = save_dir + '/result_' + ground_truth + '.csv'
        f = open(result_path, 'w')
        f.write('FIlE NAME,')
        for class_name in classifications:
            f.write(str(class_name).upper())
            f.write(',')
        f.write('Prediction, Truth, Match\n')

    with tf.Session() as sess:
        # for each file in the test images directory . . .
        for fileName in os.listdir(TEST_IMAGES_DIR):
            # if the file does not end in .jpg or .jpeg (case-insensitive), continue with the next iteration of the for loop
            if not (fileName.lower().endswith(".jpg") or fileName.lower().endswith(".jpeg")):
                continue
            # end if

            # show the file name on std out
            print(fileName)

            # get the file name and full path of the current image file
            imageFileWithPath = os.path.join(TEST_IMAGES_DIR, fileName)
            # attempt to open the image with OpenCV
            openCVImage = cv2.imread(imageFileWithPath)

            # if we were not able to successfully open the image, continue with the next iteration of the for loop
            if openCVImage is None:
                print("unable to open " + fileName + " as an OpenCV image")
                continue
            # end if

            # get the final tensor from the graph
            finalTensor = sess.graph.get_tensor_by_name('final_result:0')

            # convert the OpenCV image (numpy array) to a TensorFlow image
            tfImage = np.array(openCVImage)[:, :, 0:3]
            
            # run the network to get the predictions
            predictions = sess.run(finalTensor, {'DecodeJpeg:0': tfImage})

            # sort predictions from most confidence to least confidence
            sortedPredictions = predictions[0].argsort()[-len(predictions[0]):][::-1]

            print("---------------------------------------")

            # keep track of if we're going through the next for loop for the first time so we can show more info about
            # the first prediction, which is the most likely prediction (they were sorted descending above)
            onMostLikelyPrediction = True
            # for each prediction . . .

            # Writing result on csv File
            if save_performance:
                f.write(fileName)
                f.write(',')
                for predVal in predictions[0]:
                    f.write(str(predVal))
                    f.write(',')
                prediction = classifications[sortedPredictions[0]]
                match = 0
                if prediction == ground_truth:
                    match = 1
                f.write(str(prediction)+','+str(ground_truth)+','+str(match)+'\n')

            for prediction in sortedPredictions:
                strClassification = classifications[prediction]

                # if the classification (obtained from the directory name) ends with the letter "s", remove the "s" to change from plural to singular
                #if strClassification.endswith("s"):
                    #strClassification = strClassification[:-1]
                # end if

                # get confidence, then get confidence rounded to 2 places after the decimal
                confidence = predictions[0][prediction]

                # if we're on the first (most likely) prediction, state what the object appears to be and show a % confidence to two decimal places
                if onMostLikelyPrediction:
                    # get the score as a %
                    scoreAsAPercent = confidence * 100.0
                    # show the result to std out
                    print("the object appears to be a " + strClassification + ", " + "{0:.2f}".format(scoreAsAPercent) + "% confidence")
                    # write the result on the image
                    writeResultOnImage(openCVImage, "File Name: " + fileName + "\nPrediction: " + strClassification +
                                       " (" + "{0:.2f}".format(scoreAsAPercent) + "% confidence) \nGround Truth: " +
                                       ground_truth)
                    # finally we can show the OpenCV image
                    if show_detection:
                        cv2.imshow(fileName, openCVImage)
                        # pause
                        cv2.waitKey(0)
                        # after a key is pressed, close the current window to prep for the next time around
                        cv2.destroyAllWindows()
                    # mark that we've show the most likely prediction at this point so the additional information in
                    # this if statement does not show again for this image
                    onMostLikelyPrediction = False
                # end if

                # for any prediction, show the confidence as a ratio to five decimal places
                print(strClassification + " (" + "{0:.5f}".format(confidence) + ")")
            # end for
        # end for
    # end with
    if save_performance:
        f.close()

    return classifications

    # write the graph to file so we can view with TensorBoard
    '''tfFileWriter = tf.summary.FileWriter(os.getcwd())
    tfFileWriter.add_graph(sess.graph)
    tfFileWriter.close()'''

# end main

#######################################################################################################################
def checkIfNecessaryPathsAndFilesExist():
    if not os.path.exists(TEST_IMAGES_DIR):
        print('')
        print('ERROR: TEST_IMAGES_DIR "' + TEST_IMAGES_DIR + '" does not seem to exist')
        print('Did you set up the test images?')
        print('')
        return False
    # end if

    if not os.path.exists(RETRAINED_LABELS_TXT_FILE_LOC):
        print('ERROR: RETRAINED_LABELS_TXT_FILE_LOC "' + RETRAINED_LABELS_TXT_FILE_LOC + '" does not seem to exist')
        return False
    # end if

    if not os.path.exists(RETRAINED_GRAPH_PB_FILE_LOC):
        print('ERROR: RETRAINED_GRAPH_PB_FILE_LOC "' + RETRAINED_GRAPH_PB_FILE_LOC + '" does not seem to exist')
        return False
    # end if

    return True
# end function

#######################################################################################################################
def writeResultOnImage(openCVImage, resultText):
    # ToDo: this function may take some further fine-tuning to show the text well given any possible image size

    imageHeight, imageWidth, sceneNumChannels = openCVImage.shape

    # choose a font
    fontFace = cv2.FONT_HERSHEY_TRIPLEX

    # chose the font size and thickness as a fraction of the image size
    fontScale = 0.5
    fontThickness = 1.0

    # make sure font thickness is an integer, if not, the OpenCV functions that use this may crash
    fontThickness = int(fontThickness)

    upperLeftTextOriginX = int(imageWidth * 0.05)
    upperLeftTextOriginY = int(imageHeight * 0.05)

    textSize, baseline = cv2.getTextSize(resultText, fontFace, fontScale, fontThickness)
    textSizeWidth, textSizeHeight = textSize

    # write the text on the image
    for i, line in enumerate(resultText.split('\n')):
        # calculate the lower left origin of the text area based on the text area center, width, and height
        lowerLeftTextOriginX = upperLeftTextOriginX
        lowerLeftTextOriginY = upperLeftTextOriginY + i * 2 * textSizeHeight
        #cv2.putText(img, line, (50, y), cv2.FONT_HERSHEY_SIMPLEX, 1, 2)
        cv2.putText(openCVImage, line, (lowerLeftTextOriginX, lowerLeftTextOriginY), fontFace, fontScale,
                    SCALAR_BLUE, fontThickness)

# end function


#######################################################################################################################
if __name__ == "__main__":
    main()