Using v4 start in retraining example

I am trying to adapt an example retraining script ( https://github.com/tensorflow/tensorflow/blob/master/tensorflow/examples/image_retraining/retrain.py ) to use the Inception V4 model.

The script already supports retraining Inception V3 (2015), as well as various versions of Mobilenets.

What I have done so far: since the script uses protobuf files (.pb) and not breakpoints (.ckpt), I downloaded inception_v4.pbfrom here: https://deepdetect.com/models/tf/inception_v4.pb , as I understand it , you could also load a breakpoint and use the graph freeze tool to get the same file.

Then I looked at the graph in tenorboard using the python tool import_pb_to_tensorboard.pywhich can be found in the tenorflow github repository. From there (correct me if I'm not mistaken) I found what resized_input_tensor_nameis called InputImagethen bottleneck_tensor_name- InceptionV4/Logits/Logits/MatMulwith bottleneck_tensor_size- 1001.

With this information, I tried to adapt create_model_info(architecture)the retraining script by adding:

    elif architecture == 'inception_v4':
        data_url = 'http://download.tensorflow.org/models/image/imagenet/inception-2015-12-05.tgz' #this won't make any difference
        bottleneck_tensor_name = 'InceptionV4 / Logits / Logits / MatMul'
        bottleneck_tensor_size = 1001
        input_width = 299
        input_height = 299
        input_depth = 3
        resized_input_tensor_name = 'InputImage'
        model_file_name = 'inception_v4.pb'
        input_mean = 128
        input_std = 128

I run the script using the following command:

python retrain.py --architecture = inception_v4 --bottleneck_dir = test2 / bottlenecks --model_dir = inception_v4 --summaries_dir = test2 / summaries / basic --output_graph = test2 / graph_flowers.pb --output_labels = test2 / labels_flowers.txt - image_dir = datasets / flowers / flower_photos --how_many_training_steps 100

and I get the following error:

File โ€œretrain.pyโ€, line 373, in create_bottleneck_file str (e))) RuntimeError: Error processing file datasets /flowers/flower_photos/tulips/4546299243_23cd58eb43.jpg (Cannot interpret feed_dict key as tensor: cannot convert operation to Tensor .)

+8
source share
2

.

:0 bottleneck_tensor_name resized_input_tensor_name.

retrain.py, Google :0 .

, InceptionV4/Logits/Logits/MatMul - , , InceptionV4/Logits/Logits/MatMul:0 - , ., .

+5

script, InputImage :

resized_input_tensor_name = 'InputImage:0'
+1

Source: https://habr.com/ru/post/1687794/


All Articles