Closed lunasdejavu closed 6 years ago
@lunasdejavu what exactly did you modify ?
`import tensorflow as tf
import glob
a=0
for impath in glob.glob('/home/lunasdejavu/Downloads/image-classification-tensorflow-master/validation/*.jpg'): image_path = impath
image_data = tf.gfile.FastGFile(image_path, 'rb').read()
label_lines = [line.rstrip() for line
in tf.gfile.GFile("logs/trained_labels.txt")]
with tf.gfile.FastGFile("logs/trained_graph.pb", 'rb') as f:
graph_def=tf.GraphDef()
graph_def.ParseFromString(f.read())
_=tf.import_graph_def(graph_def, name='')
with tf.Session() as sess:
# Feed the image_data as input to the graph and get first prediction
softmax_tensor=sess.graph.get_tensor_by_name('final_result:0')
predictions = sess.run(softmax_tensor, \
{'DecodeJpeg/contents:0': image_data})
# Sort to show labels of first prediction in order of confidence
top_k = predictions[0].argsort()[-len(predictions[0]):][::-1]
if predictions[0][0]>predictions[0][1]:
a+=1
print ('GG')
#for node_id in top_k:
#human_string = label_lines[node_id]
#score = predictions[0][node_id]
#print('%s (score = %.5f)' % (human_string, score))`
that is for the classify.py the training dataset is 5677 for A 5768 for B validalition 577 for each
Loading model every time in loop ,if we add takes time .how to implement that load model once and test many time in classify. Py
arun what is the best way to deploy this retrained model as could not find anything worthwile on the net
want to consume the model and utilise as a service
You want to build a service to classify a particular set of images ?
Closing due to inactivity.
I trained with 10509 images 2 classes
then accuracy was good for 81.6% but when I tried to rewrite classify.py I encounter this error ValueError: GraphDef cannot be larger than 2GB.
`#os.environ['TF_CPP_MIN_LOG_LEVEL']='2' a=0
for impath in glob.glob('/home/lunasdejavu/Downloads/image-classification-tensorflow-master/validation/*.jpg'): image_path = impath `
then
if predictions[0][0]>predictions[0][1]: a+=1 print (a/577)
I checked the stackoverflow already https://stackoverflow.com/questions/36349049/overcome-graphdef-cannot-be-larger-than-2gb-in-tensorflow but I still don't know how to modify :( `