Why is the outputs's box less and badly offset in openvino ?(tiny-yolov3, keras, NCS2)

Why is the outputs's box less and badly offset in openvino ?(tiny-yolov3, keras, NCS2)

Here's what I did

  • Downloaded keras-tiny-yolov3 model
  • Changed leaky_relu to relu and retrained, then I got the h5 file
  • Used h5_to_pb.py to get the pb file 
  • Converted pb file to IR 
    sudo python mo_tf.py --input_model='/home/rookiechen/model/car/yolov3-tiny.pb' --output_dir='/home/rookiechen/yolo_test_openvino/' --input_shape=[1,416,416,3] --scale_values=[255,255,255] --data_type=FP16
  • Infered 

    def main_IE_infer():
        image_dir = './test_image'
    
        images_list = os.listdir(image_dir)
        images_file_list = []
        for i, image_file_i in enumerate(images_list):
            if image_file_i.split('.')[-1] in ['jpg', 'png']:
                images_file_list.append(os.path.join(image_dir, image_file_i))
    
        inputs_size=416
        channel_num=3
        input_shape = [416, 416]
        args = build_argparser().parse_args()
        model_xml = "yolov3-tiny.xml"  # <--- MYRIAD
        model_bin = os.path.splitext(model_xml)[0] + ".bin"
        namewindows = "car detect"
        cv2.namedWindow(namewindows, cv2.WINDOW_NORMAL)
        time.sleep(1)
        plugin = IEPlugin(device=args.device)
        if "CPU" in args.device:
            plugin.add_cpu_extension("lib/libcpu_extension.so")
        net = IENetwork(model=model_xml, weights=model_bin)
        input_blob = next(iter(net.inputs))
        exec_net = plugin.load(network=net)
    
        # for image_file in images_file_list:
        image_file='1.jpg'
        frame = cv2.imread(image_file)
        image = np.array(frame, dtype='float32')
        shape=image.shape
        image_re = cv2.resize(image, (inputs_size, inputs_size))
        image_re = cv2.cvtColor(image_re, cv2.COLOR_BGR2RGB)
        image_re /= 255.
        image_re = image_re.reshape(1, inputs_size, inputs_size, channel_num)#此时通道3,在最后面
        prepimg = image_re.transpose((0, 3, 1, 2))  # NHWC to NCHW,C 代表通道数,神经棒推理时,要求通道说写在前面第2个位置(1,3,416,416)
        outs= exec_net.infer(inputs={input_blob: prepimg})#2
        anchor_mask = [[3, 4, 5], [1, 2, 3]]  # default setting
        boxes, classes, scores = [], [], []
        i = 0
        for out in outs.values():  # out.shape=(1, 18,13, 13),(1, 18,26, 26),batch,num_anchors,height,width
            b, c, s = _process_feats(out, anchors, anchor_mask[i], input_shape)
            b, c, s = _filter_boxes(b, c, s)
            boxes.append(b)
            classes.append(c)
            scores.append(s)
            i += 1
    
        boxes = np.concatenate(boxes)
        classes = np.concatenate(classes)
        scores = np.concatenate(scores)
    
        # Scale boxes back to original image shape.
        width, height = shape[1], shape[0]
        image_dims = [width, height, width, height]
        boxes = boxes * image_dims
        nboxes, nclasses, nscores = [], [], []
        for c in set(classes):
            inds = np.where(classes == c)
            b = boxes[inds]
            c = classes[inds]
            s = scores[inds]
    
            keep = _nms_boxes(b, s)
    
            nboxes.append(b[keep])
            nclasses.append(c[keep])
            nscores.append(s[keep])
    
        if not nclasses and not nscores:
            boxes=None
            classes=None
            scores=None
        else:
            boxes = np.concatenate(nboxes)
            classes = np.concatenate(nclasses)
            scores = np.concatenate(nscores)
    
        if boxes is not None:
            draw(frame, boxes, scores, classes,all_classes)
            # image=cv2.resize(image, (1280, 720))
        cv2.imshow(namewindows,frame)
        cv2.waitKey(0)
        cv2.destroyAllWindows()
        del exec_net
        del plugin

But the results is so bad.You can see in the attachment, the left is not using NCS2

So, what's the problem? Please help me.The following is the xml content

This XML file does not appear to have any style information associated with it. The document tree is shown below.
<net batch="1" name="yolov3-tiny" version="5">
<layers>
<layer id="0" name="input_1" precision="FP16" type="Input">
<output>
<port id="0">
<dim>1</dim>
<dim>3</dim>
<dim>416</dim>
<dim>416</dim>
</port>
</output>
</layer>
<layer id="1" name="conv2d_1/convolution" precision="FP16" type="Convolution">
<data auto_pad="same_upper" dilations="1,1" group="1" kernel="3,3" output="16" pads_begin="1,1" pads_end="1,1" strides="1,1"/>
<input>
<port id="0">
<dim>1</dim>
<dim>3</dim>
<dim>416</dim>
<dim>416</dim>
</port>
</input>
<output>
<port id="3">
<dim>1</dim>
<dim>16</dim>
<dim>416</dim>
<dim>416</dim>
</port>
</output>
<blobs>
<weights offset="0" size="864"/>
<biases offset="864" size="32"/>
</blobs>
</layer>
<layer id="2" name="re_lu_1/Relu" precision="FP16" type="ReLU">
<input>
<port id="0">
<dim>1</dim>
<dim>16</dim>
<dim>416</dim>
<dim>416</dim>
</port>
</input>
<output>
<port id="1">
<dim>1</dim>
<dim>16</dim>
<dim>416</dim>
<dim>416</dim>
</port>
</output>
</layer>
<layer id="3" name="max_pooling2d_1/MaxPool" precision="FP16" type="Pooling">
<data auto_pad="same_upper" exclude-pad="true" kernel="2,2" pads_begin="0,0" pads_end="0,0" pool-method="max" strides="2,2"/>
<input>
<port id="0">
<dim>1</dim>
<dim>16</dim>
<dim>416</dim>
<dim>416</dim>
</port>
</input>
<output>
<port id="1">
<dim>1</dim>
<dim>16</dim>
<dim>208</dim>
<dim>208</dim>
</port>
</output>
</layer>
<layer id="4" name="conv2d_2/convolution" precision="FP16" type="Convolution">
<data auto_pad="same_upper" dilations="1,1" group="1" kernel="3,3" output="32" pads_begin="1,1" pads_end="1,1" strides="1,1"/>
<input>
<port id="0">
<dim>1</dim>
<dim>16</dim>
<dim>208</dim>
<dim>208</dim>
</port>
</input>
<output>
<port id="3">
<dim>1</dim>
<dim>32</dim>
<dim>208</dim>
<dim>208</dim>
</port>
</output>
<blobs>
<weights offset="896" size="9216"/>
<biases offset="10112" size="64"/>
</blobs>
</layer>
<layer id="5" name="re_lu_2/Relu" precision="FP16" type="ReLU">
<input>
<port id="0">
<dim>1</dim>
<dim>32</dim>
<dim>208</dim>
<dim>208</dim>
</port>
</input>
<output>
<port id="1">
<dim>1</dim>
<dim>32</dim>
<dim>208</dim>
<dim>208</dim>
</port>
</output>
</layer>
<layer id="6" name="max_pooling2d_2/MaxPool" precision="FP16" type="Pooling">
<data auto_pad="same_upper" exclude-pad="true" kernel="2,2" pads_begin="0,0" pads_end="0,0" pool-method="max" strides="2,2"/>
<input>
<port id="0">
<dim>1</dim>
<dim>32</dim>
<dim>208</dim>
<dim>208</dim>
</port>
</input>
<output>
<port id="1">
<dim>1</dim>
<dim>32</dim>
<dim>104</dim>
<dim>104</dim>
</port>
</output>
</layer>
<layer id="7" name="conv2d_3/convolution" precision="FP16" type="Convolution">
<data auto_pad="same_upper" dilations="1,1" group="1" kernel="3,3" output="64" pads_begin="1,1" pads_end="1,1" strides="1,1"/>
<input>
<port id="0">
<dim>1</dim>
<dim>32</dim>
<dim>104</dim>
<dim>104</dim>
</port>
</input>
<output>
<port id="3">
<dim>1</dim>
<dim>64</dim>
<dim>104</dim>
<dim>104</dim>
</port>
</output>
<blobs>
<weights offset="10176" size="36864"/>
<biases offset="47040" size="128"/>
</blobs>
</layer>
<layer id="8" name="re_lu_3/Relu" precision="FP16" type="ReLU">
<input>
<port id="0">
<dim>1</dim>
<dim>64</dim>
<dim>104</dim>
<dim>104</dim>
</port>
</input>
<output>
<port id="1">
<dim>1</dim>
<dim>64</dim>
<dim>104</dim>
<dim>104</dim>
</port>
</output>
</layer>
<layer id="9" name="max_pooling2d_3/MaxPool" precision="FP16" type="Pooling">
<data auto_pad="same_upper" exclude-pad="true" kernel="2,2" pads_begin="0,0" pads_end="0,0" pool-method="max" strides="2,2"/>
<input>
<port id="0">
<dim>1</dim>
<dim>64</dim>
<dim>104</dim>
<dim>104</dim>
</port>
</input>
<output>
<port id="1">
<dim>1</dim>
<dim>64</dim>
<dim>52</dim>
<dim>52</dim>
</port>
</output>
</layer>
<layer id="10" name="conv2d_4/convolution" precision="FP16" type="Convolution">
<data auto_pad="same_upper" dilations="1,1" group="1" kernel="3,3" output="128" pads_begin="1,1" pads_end="1,1" strides="1,1"/>
<input>
<port id="0">
<dim>1</dim>
<dim>64</dim>
<dim>52</dim>
<dim>52</dim>
</port>
</input>
<output>
<port id="3">
<dim>1</dim>
<dim>128</dim>
<dim>52</dim>
<dim>52</dim>
</port>
</output>
<blobs>
<weights offset="47168" size="147456"/>
<biases offset="194624" size="256"/>
</blobs>
</layer>
<layer id="11" name="re_lu_4/Relu" precision="FP16" type="ReLU">
<input>
<port id="0">
<dim>1</dim>
<dim>128</dim>
<dim>52</dim>
<dim>52</dim>
</port>
</input>
<output>
<port id="1">
<dim>1</dim>
<dim>128</dim>
<dim>52</dim>
<dim>52</dim>
</port>
</output>
</layer>
<layer id="12" name="max_pooling2d_4/MaxPool" precision="FP16" type="Pooling">
<data auto_pad="same_upper" exclude-pad="true" kernel="2,2" pads_begin="0,0" pads_end="0,0" pool-method="max" strides="2,2"/>
<input>
<port id="0">
<dim>1</dim>
<dim>128</dim>
<dim>52</dim>
<dim>52</dim>
</port>
</input>
<output>
<port id="1">
<dim>1</dim>
<dim>128</dim>
<dim>26</dim>
<dim>26</dim>
</port>
</output>
</layer>
<layer id="13" name="conv2d_5/convolution" precision="FP16" type="Convolution">
<data auto_pad="same_upper" dilations="1,1" group="1" kernel="3,3" output="256" pads_begin="1,1" pads_end="1,1" strides="1,1"/>
<input>
<port id="0">
<dim>1</dim>
<dim>128</dim>
<dim>26</dim>
<dim>26</dim>
</port>
</input>
<output>
<port id="3">
<dim>1</dim>
<dim>256</dim>
<dim>26</dim>
<dim>26</dim>
</port>
</output>
<blobs>
<weights offset="194880" size="589824"/>
<biases offset="784704" size="512"/>
</blobs>
</layer>
<layer id="14" name="re_lu_5/Relu" precision="FP16" type="ReLU">
<input>
<port id="0">
<dim>1</dim>
<dim>256</dim>
<dim>26</dim>
<dim>26</dim>
</port>
</input>
<output>
<port id="1">
<dim>1</dim>
<dim>256</dim>
<dim>26</dim>
<dim>26</dim>
</port>
</output>
</layer>
<layer id="15" name="max_pooling2d_5/MaxPool" precision="FP16" type="Pooling">
<data auto_pad="same_upper" exclude-pad="true" kernel="2,2" pads_begin="0,0" pads_end="0,0" pool-method="max" strides="2,2"/>
<input>
<port id="0">
<dim>1</dim>
<dim>256</dim>
<dim>26</dim>
<dim>26</dim>
</port>
</input>
<output>
<port id="1">
<dim>1</dim>
<dim>256</dim>
<dim>13</dim>
<dim>13</dim>
</port>
</output>
</layer>
<layer id="16" name="conv2d_6/convolution" precision="FP16" type="Convolution">
<data auto_pad="same_upper" dilations="1,1" group="1" kernel="3,3" output="512" pads_begin="1,1" pads_end="1,1" strides="1,1"/>
<input>
<port id="0">
<dim>1</dim>
<dim>256</dim>
<dim>13</dim>
<dim>13</dim>
</port>
</input>
<output>
<port id="3">
<dim>1</dim>
<dim>512</dim>
<dim>13</dim>
<dim>13</dim>
</port>
</output>
<blobs>
<weights offset="785216" size="2359296"/>
<biases offset="3144512" size="1024"/>
</blobs>
</layer>
<layer id="17" name="re_lu_6/Relu" precision="FP16" type="ReLU">
<input>
<port id="0">
<dim>1</dim>
<dim>512</dim>
<dim>13</dim>
<dim>13</dim>
</port>
</input>
<output>
<port id="1">
<dim>1</dim>
<dim>512</dim>
<dim>13</dim>
<dim>13</dim>
</port>
</output>
</layer>
<layer id="18" name="max_pooling2d_6/MaxPool" precision="FP16" type="Pooling">
<data auto_pad="same_upper" exclude-pad="true" kernel="2,2" pads_begin="0,0" pads_end="1,1" pool-method="max" strides="1,1"/>
<input>
<port id="0">
<dim>1</dim>
<dim>512</dim>
<dim>13</dim>
<dim>13</dim>
</port>
</input>
<output>
<port id="1">
<dim>1</dim>
<dim>512</dim>
<dim>13</dim>
<dim>13</dim>
</port>
</output>
</layer>
<layer id="19" name="conv2d_7/convolution" precision="FP16" type="Convolution">
<data auto_pad="same_upper" dilations="1,1" group="1" kernel="3,3" output="1024" pads_begin="1,1" pads_end="1,1" strides="1,1"/>
<input>
<port id="0">
<dim>1</dim>
<dim>512</dim>
<dim>13</dim>
<dim>13</dim>
</port>
</input>
<output>
<port id="3">
<dim>1</dim>
<dim>1024</dim>
<dim>13</dim>
<dim>13</dim>
</port>
</output>
<blobs>
<weights offset="3145536" size="9437184"/>
<biases offset="12582720" size="2048"/>
</blobs>
</layer>
<layer id="20" name="re_lu_7/Relu" precision="FP16" type="ReLU">
<input>
<port id="0">
<dim>1</dim>
<dim>1024</dim>
<dim>13</dim>
<dim>13</dim>
</port>
</input>
<output>
<port id="1">
<dim>1</dim>
<dim>1024</dim>
<dim>13</dim>
<dim>13</dim>
</port>
</output>
</layer>
<layer id="21" name="conv2d_8/convolution" precision="FP16" type="Convolution">
<data auto_pad="same_upper" dilations="1,1" group="1" kernel="1,1" output="256" pads_begin="0,0" pads_end="0,0" strides="1,1"/>
<input>
<port id="0">
<dim>1</dim>
<dim>1024</dim>
<dim>13</dim>
<dim>13</dim>
</port>
</input>
<output>
<port id="3">
<dim>1</dim>
<dim>256</dim>
<dim>13</dim>
<dim>13</dim>
</port>
</output>
<blobs>
<weights offset="12584768" size="524288"/>
<biases offset="13109056" size="512"/>
</blobs>
</layer>
<layer id="22" name="re_lu_8/Relu" precision="FP16" type="ReLU">
<input>
<port id="0">
<dim>1</dim>
<dim>256</dim>
<dim>13</dim>
<dim>13</dim>
</port>
</input>
<output>
<port id="1">
<dim>1</dim>
<dim>256</dim>
<dim>13</dim>
<dim>13</dim>
</port>
</output>
</layer>
<layer id="23" name="conv2d_9/convolution" precision="FP16" type="Convolution">
<data auto_pad="same_upper" dilations="1,1" group="1" kernel="3,3" output="512" pads_begin="1,1" pads_end="1,1" strides="1,1"/>
<input>
<port id="0">
<dim>1</dim>
<dim>256</dim>
<dim>13</dim>
<dim>13</dim>
</port>
</input>
<output>
<port id="3">
<dim>1</dim>
<dim>512</dim>
<dim>13</dim>
<dim>13</dim>
</port>
</output>
<blobs>
<weights offset="13109568" size="2359296"/>
<biases offset="15468864" size="1024"/>
</blobs>
</layer>
<layer id="24" name="re_lu_9/Relu" precision="FP16" type="ReLU">
<input>
<port id="0">
<dim>1</dim>
<dim>512</dim>
<dim>13</dim>
<dim>13</dim>
</port>
</input>
<output>
<port id="1">
<dim>1</dim>
<dim>512</dim>
<dim>13</dim>
<dim>13</dim>
</port>
</output>
</layer>
<layer id="25" name="conv2d_10/convolution" precision="FP16" type="Convolution">
<data auto_pad="same_upper" dilations="1,1" group="1" kernel="1,1" output="18" pads_begin="0,0" pads_end="0,0" strides="1,1"/>
<input>
<port id="0">
<dim>1</dim>
<dim>512</dim>
<dim>13</dim>
<dim>13</dim>
</port>
</input>
<output>
<port id="3">
<dim>1</dim>
<dim>18</dim>
<dim>13</dim>
<dim>13</dim>
</port>
</output>
<blobs>
<weights offset="15469888" size="18432"/>
<biases offset="15488320" size="36"/>
</blobs>
</layer>
<layer id="26" name="conv2d_11/convolution" precision="FP16" type="Convolution">
<data auto_pad="same_upper" dilations="1,1" group="1" kernel="1,1" output="128" pads_begin="0,0" pads_end="0,0" strides="1,1"/>
<input>
<port id="0">
<dim>1</dim>
<dim>256</dim>
<dim>13</dim>
<dim>13</dim>
</port>
</input>
<output>
<port id="3">
<dim>1</dim>
<dim>128</dim>
<dim>13</dim>
<dim>13</dim>
</port>
</output>
<blobs>
<weights offset="15488356" size="65536"/>
<biases offset="15553892" size="256"/>
</blobs>
</layer>
<layer id="27" name="re_lu_10/Relu" precision="FP16" type="ReLU">
<input>
<port id="0">
<dim>1</dim>
<dim>128</dim>
<dim>13</dim>
<dim>13</dim>
</port>
</input>
<output>
<port id="1">
<dim>1</dim>
<dim>128</dim>
<dim>13</dim>
<dim>13</dim>
</port>
</output>
</layer>
<layer id="28" name="up_sampling2d_1/ResizeNearestNeighbor" precision="FP16" type="Resample">
<data antialias="0" factor="2.0" type="caffe.ResampleParameter.NEAREST"/>
<input>
<port id="0">
<dim>1</dim>
<dim>128</dim>
<dim>13</dim>
<dim>13</dim>
</port>
</input>
<output>
<port id="1">
<dim>1</dim>
<dim>128</dim>
<dim>26</dim>
<dim>26</dim>
</port>
</output>
</layer>
<layer id="29" name="concatenate_1/concat" precision="FP16" type="Concat">
<data axis="1"/>
<input>
<port id="0">
<dim>1</dim>
<dim>128</dim>
<dim>26</dim>
<dim>26</dim>
</port>
<port id="1">
<dim>1</dim>
<dim>256</dim>
<dim>26</dim>
<dim>26</dim>
</port>
</input>
<output>
<port id="2">
<dim>1</dim>
<dim>384</dim>
<dim>26</dim>
<dim>26</dim>
</port>
</output>
</layer>
<layer id="30" name="conv2d_12/convolution" precision="FP16" type="Convolution">
<data auto_pad="same_upper" dilations="1,1" group="1" kernel="3,3" output="256" pads_begin="1,1" pads_end="1,1" strides="1,1"/>
<input>
<port id="0">
<dim>1</dim>
<dim>384</dim>
<dim>26</dim>
<dim>26</dim>
</port>
</input>
<output>
<port id="3">
<dim>1</dim>
<dim>256</dim>
<dim>26</dim>
<dim>26</dim>
</port>
</output>
<blobs>
<weights offset="15554148" size="1769472"/>
<biases offset="17323620" size="512"/>
</blobs>
</layer>
<layer id="31" name="re_lu_11/Relu" precision="FP16" type="ReLU">
<input>
<port id="0">
<dim>1</dim>
<dim>256</dim>
<dim>26</dim>
<dim>26</dim>
</port>
</input>
<output>
<port id="1">
<dim>1</dim>
<dim>256</dim>
<dim>26</dim>
<dim>26</dim>
</port>
</output>
</layer>
<layer id="32" name="conv2d_13/convolution" precision="FP16" type="Convolution">
<data auto_pad="same_upper" dilations="1,1" group="1" kernel="1,1" output="18" pads_begin="0,0" pads_end="0,0" strides="1,1"/>
<input>
<port id="0">
<dim>1</dim>
<dim>256</dim>
<dim>26</dim>
<dim>26</dim>
</port>
</input>
<output>
<port id="3">
<dim>1</dim>
<dim>18</dim>
<dim>26</dim>
<dim>26</dim>
</port>
</output>
<blobs>
<weights offset="17324132" size="9216"/>
<biases offset="17333348" size="36"/>
</blobs>
</layer>
</layers>
<edges>
<edge from-layer="0" from-port="0" to-layer="1" to-port="0"/>
<edge from-layer="1" from-port="3" to-layer="2" to-port="0"/>
<edge from-layer="2" from-port="1" to-layer="3" to-port="0"/>
<edge from-layer="3" from-port="1" to-layer="4" to-port="0"/>
<edge from-layer="4" from-port="3" to-layer="5" to-port="0"/>
<edge from-layer="5" from-port="1" to-layer="6" to-port="0"/>
<edge from-layer="6" from-port="1" to-layer="7" to-port="0"/>
<edge from-layer="7" from-port="3" to-layer="8" to-port="0"/>
<edge from-layer="8" from-port="1" to-layer="9" to-port="0"/>
<edge from-layer="9" from-port="1" to-layer="10" to-port="0"/>
<edge from-layer="10" from-port="3" to-layer="11" to-port="0"/>
<edge from-layer="11" from-port="1" to-layer="12" to-port="0"/>
<edge from-layer="12" from-port="1" to-layer="13" to-port="0"/>
<edge from-layer="13" from-port="3" to-layer="14" to-port="0"/>
<edge from-layer="14" from-port="1" to-layer="15" to-port="0"/>
<edge from-layer="15" from-port="1" to-layer="16" to-port="0"/>
<edge from-layer="16" from-port="3" to-layer="17" to-port="0"/>
<edge from-layer="17" from-port="1" to-layer="18" to-port="0"/>
<edge from-layer="18" from-port="1" to-layer="19" to-port="0"/>
<edge from-layer="19" from-port="3" to-layer="20" to-port="0"/>
<edge from-layer="20" from-port="1" to-layer="21" to-port="0"/>
<edge from-layer="21" from-port="3" to-layer="22" to-port="0"/>
<edge from-layer="22" from-port="1" to-layer="23" to-port="0"/>
<edge from-layer="23" from-port="3" to-layer="24" to-port="0"/>
<edge from-layer="24" from-port="1" to-layer="25" to-port="0"/>
<edge from-layer="22" from-port="1" to-layer="26" to-port="0"/>
<edge from-layer="26" from-port="3" to-layer="27" to-port="0"/>
<edge from-layer="27" from-port="1" to-layer="28" to-port="0"/>
<edge from-layer="28" from-port="1" to-layer="29" to-port="0"/>
<edge from-layer="14" from-port="1" to-layer="29" to-port="1"/>
<edge from-layer="29" from-port="2" to-layer="30" to-port="0"/>
<edge from-layer="30" from-port="3" to-layer="31" to-port="0"/>
<edge from-layer="31" from-port="1" to-layer="32" to-port="0"/>
</edges>
<meta_data>
<MO_version value="2019.1.1-83-g28dfbfd"/>
<cli_parameters>
<data_type value="FP16"/>
<disable_fusing value="False"/>
<disable_gfusing value="False"/>
<disable_nhwc_to_nchw value="False"/>
<disable_resnet_optimization value="False"/>
<enable_concat_optimization value="False"/>
<extensions value="DIR"/>
<framework value="tf"/>
<generate_deprecated_IR_V2 value="False"/>
<input_model value="DIR/yolov3-tiny.pb"/>
<input_model_is_text value="False"/>
<input_shape value="[1,416,416,3]"/>
<keep_shape_ops value="False"/>
<log_level value="INFO"/>
<mean_scale_values value="[(None, array([255., 255., 255.]))]"/>
<mean_values value="()"/>
<move_to_preprocess value="False"/>
<output_dir value="DIR"/>
<placeholder_shapes value="[ 1 416 416 3]"/>
<reverse_input_channels value="False"/>
<scale_values value="[255,255,255]"/>
<silent value="False"/>
<version value="False"/>
<unset unset_cli_parameters="batch, finegrain_fusing, freeze_placeholder_with_value, input, input_checkpoint, input_meta_graph, model_name, output, saved_model_dir, saved_model_tags, scale, tensorboard_logdir, tensorflow_custom_layer_libraries, tensorflow_custom_operations_config_update, tensorflow_object_detection_api_pipeline_config, tensorflow_operation_patterns, tensorflow_subgraph_patterns, tensorflow_use_custom_operations_config"/>
</cli_parameters>
</meta_data>
</net>

 

5 posts / 0 new
Last post
For more complete information about compiler optimizations, see our Optimization Notice.

Dear chen, rookie,

Is this a custom-trained  tiny-yolo v3 model  or did you simply use the default  pre-trained model ?

Thanks,

Shubha

custom-trained

Hi chen, rookie,

I don't see any attachments on your original post, could you try adding them again?

 

Also, could you try to add following option to the model optimizer command (mo_tf.py)? 

--reverse_input_channels

 Regards,

Jesus

Dear everyone,

kindly download OpenVino 2019R2 which was just released today. It fixes a lot of issues and introduces some wonderful new features !

Thanks,

Shubha

Leave a Comment

Please sign in to add a comment. Not a member? Join today