Opencv-python: error: OpenCV(4.0.0) /io/opencv/modules/dnn/src/caffe/caffe_io.cpp:1132: error: (-2:Unspecified error) FAILED: fs.is_open(). Can't open "frozen_east_text_detection.pb" in function 'ReadProtoFromBinaryFile'

[javierfs]

Expected behaviour

I have installed opencv-python OpenCV(4.0.0) but seems it cannot find 'frozen_east_text_detection.pb' when running cv2.dnn.readNet

error: OpenCV(4.0.0) /io/opencv/modules/dnn/src/caffe/caffe_io.cpp:1132

Actual behaviour

error                                     Traceback (most recent call last)
<ipython-input-15-9b59c98d5831> in <module>()
      4 
      5 CTextDetector = ClassTextDetector()
----> 6 boxes = CTextDetector.getTextRegions_EAST(inputImg_1, W, H)

~/disk_user/OCR_project/Classes/ClassTextDetector.py in getTextRegions_EAST(self, inMat, outW, outH)
     20     def getTextRegions_EAST(self, inMat, outW, outH):
     21         layerNames = ["feature_fusion/Conv_7/Sigmoid", "feature_fusion/concat_3"]
---> 22         net = cv2.dnn.readNet('frozen_east_text_detection.pb')
     23 
     24         blob = cv2.dnn.blobFromImage(inMat, 1.0, (outW, outH),(123.68, 116.78, 103.94), swapRB=True, crop=False)

error: OpenCV(4.0.0) /io/opencv/modules/dnn/src/caffe/caffe_io.cpp:1132: error: (-2:Unspecified error) FAILED: fs.is_open(). Can't open "frozen_east_text_detection.pb" in function 'ReadProtoFromBinaryFile'

Steps to reproduce

• example code

inputImg_1 = thresh.copy()
W = int(inputImg_1.shape[1]/32) * int(32)
H = int(inputImg_1.shape[0]/32) * int(32)

CTextDetector = ClassTextDetector()
boxes = CTextDetector.getTextRegions_EAST(inputImg_1, W, H)

def getTextRegions_EAST(self, inMat, outW, outH):
        layerNames = ["feature_fusion/Conv_7/Sigmoid", "feature_fusion/concat_3"]
        net = cv2.dnn.readNet('frozen_east_text_detection.pb')

        blob = cv2.dnn.blobFromImage(inMat, 1.0, (outW, outH),(123.68, 116.78, 103.94), swapRB=True, crop=False)
        start = time.time()
        net.setInput(blob)
        (scores, geometry) = net.forward(layerNames)
        end = time.time()
        # show timing information on text prediction
        print("[INFO] text detection took {:.6f} seconds".format(end - start))

        #print(scores.shape)
        #print(scores)
        (numRows, numCols) = scores.shape[2:4]
        rects = []
        confidences = []

        # loop over the number of rows
        for y in range(0, numRows):
            # extract the scores (probabilities), followed by the geometrical
            # data used to derive potential bounding box coordinates that
            # surround text
            scoresData = scores[0, 0, y]
            xData0 = geometry[0, 0, y]
            xData1 = geometry[0, 1, y]
            xData2 = geometry[0, 2, y]
            xData3 = geometry[0, 3, y]
            anglesData = geometry[0, 4, y]

            # loop over the number of columns
            for x in range(0, numCols):
                # if our score does not have sufficient probability, ignore it
                if scoresData[x] < 0.5:
                    continue

                # compute the offset factor as our resulting feature maps will
                # be 4x smaller than the input image
                (offsetX, offsetY) = (x * 4.0, y * 4.0)

                # extract the rotation angle for the prediction and then
                # compute the sin and cosine
                angle = anglesData[x]
                cos = np.cos(angle)
                sin = np.sin(angle)

                # use the geometry volume to derive the width and height of
                # the bounding box
                h = xData0[x] + xData2[x]
                w = xData1[x] + xData3[x]

                # compute both the starting and ending (x, y)-coordinates for
                # the text prediction bounding box
                endX = int(offsetX + (cos * xData1[x]) + (sin * xData2[x]))
                endY = int(offsetY - (sin * xData1[x]) + (cos * xData2[x]))
                startX = int(endX - w)
                startY = int(endY - h)

                # add the bounding box coordinates and probability score to
                # our respective lists
                rects.append((startX, startY, endX, endY))
                confidences.append(scoresData[x])

        # apply non-maxima suppression to suppress weak, overlapping bounding
        # boxes
        boxes = non_max_suppression(np.array(rects), probs=confidences)

        return boxes

• operating system
  Ubuntu 18.04.1 LTS
• architecture (e.g. x86)
• opencv-python version
  4.00

[skvark]

That file is not shipped with opencv-python. Additionally, I think you will have to have that file in your working directory for cv2.dnn.readNet('frozen_east_text_detection.pb') to work properly.