lixiangchun / mynotebook Goto Github PK

Hi, and thanks for your code

I just try to run the code to test my inception_v3 checkpoint for learning purpose but when i path it arguments , its give me a warn about "cannot process image file"

`tf.app.flags.DEFINE_integer('num_classes', 2, 'The number of classes.')
tf.app.flags.DEFINE_string('infile','/home/majid/Downloads/images/pathadd.txt', 'Image file, one image per line.')

tf.app.flags.DEFINE_boolean('tfrecord',False, 'Input file is formatted as TFRecord.')

tf.app.flags.DEFINE_string('outfile','/home/majid/Downloads/images/res/image_path.txt', 'Output file for prediction probabilities.')

tf.app.flags.DEFINE_string('model_name', 'inception_v3', 'The name of the architecture to evaluate.')

tf.app.flags.DEFINE_string('preprocessing_name','inception_v3', 'The name of the preprocessing to use. If left as None, then the model_name flag is used.')

tf.app.flags.DEFINE_string('checkpoint_path', '/home/majid/Desktop/FineTune/models/inception_v3/','The directory where the model was written to or an absolute path to a checkpoint file.')

tf.app.flags.DEFINE_integer('eval_image_size', None, 'Eval image size.')

FLAGS = tf.app.flags.FLAGS
`

btw: I put every thing for Finetune in my Desktop/FineTune/ directory & the full path of my *.jpg files in /home/majid/Downloads/images/pathadd.txt

system specs :
Ubuntu 17.10
Tensorflow 1.5
python 3
my email : [email protected]

@lixiangchun i was trying to do the same way as you did. But though i pass a jpeg image the code says image cannot process.