why Keras 2D regression network has constant output -

-



i working on kind of 2d regression deep network keras, network has constant output every datasets, test handmade dataset in code feed network constant 2d values , output linear valu of x (2*x/100) out put constant.

import resource import glob import gc rsrc = resource.rlimit_data soft, hard = resource.getrlimit(rsrc) print ('soft limit starts  :', soft)  resource.setrlimit(rsrc, (4 * 1024 * 1024 * 1024, hard))  # limit 4 giga bytes  soft, hard = resource.getrlimit(rsrc) print ('soft limit changed :', soft)  keras.models import sequential import keras.optimizers keras.layers import dense, dropout, activation, flatten, batchnormalization keras.layers import convolution2d, maxpooling2d,averagepooling2d import numpy np import random keras.utils import plot_model  sample_size = 1 batch_size = 50 input_shape = (int(720 / 4), int(1280 / 4), sample_size * 5)  # model model = sequential() model.add(batchnormalization(input_shape=input_shape)) model.add(convolution2d(128, (3, 3), activation='relu', dim_ordering="tf", padding="same",kernel_initializer='random_uniform')) model.add(convolution2d(128, (3, 3), activation='sigmoid', dim_ordering="tf", padding="same",kernel_initializer='random_uniform'))  model.add(averagepooling2d(pool_size=(4, 4), dim_ordering="tf")) model.add(convolution2d(256, (3, 3), activation='sigmoid', dim_ordering="tf", padding="same",kernel_initializer='random_uniform')) model.add(convolution2d(256, (3, 3), activation='sigmoid', dim_ordering="tf", padding="same",kernel_initializer='random_uniform'))  model.add(averagepooling2d(pool_size=(4, 4), dim_ordering="tf"))  model.add(convolution2d(512, (3, 3), activation='sigmoid', dim_ordering="tf", padding="same",kernel_initializer='random_uniform')) model.add(convolution2d(512, (3, 3), activation='sigmoid', dim_ordering="tf", padding="same",kernel_initializer='random_uniform'))  model.add(averagepooling2d(pool_size=(4, 4), dim_ordering="tf"))  model.add(flatten()) model.add(dense(4096, activation='relu',kernel_initializer='random_uniform')) #model.add(dropout(0.5)) model.add(dense(512, activation='sigmoid',kernel_initializer='random_uniform')) model.add(dense(1, activation='sigmoid',kernel_initializer='random_uniform')) model.compile(loss='mean_absolute_error',               optimizer='adam',               metrics=['mae','mse']) model.summary() plot_model(model,to_file='model.png')  def generate_tr(batch_size, is_training=false):     x=np.linspace(0, 10, num=5000).reshape(-1, 1)      counter = 0     print 'start'     while 1:         samples=np.zeros((batch_size, 720/4, 1280/4, 5))         labels=[]     t in range (batch_size):         = int(random.randint(0, 4999))         b in range(sample_size):              samples[t, :,:,b*5:b*5+5] = np.random.rand(720/4,1280/4,5)/10+x[i]           labels.append((2*x[i])/100)          counter += 1         print counter #, labels         yield ((samples), np.asarray(labels))   tt = model.fit_generator(generate_tr(batch_size, true), steps_per_epoch=100, epochs=10,                          use_multiprocessing=false, verbose=2)  score = model.predict_generator(generate_tr(batch_size, true), steps=30)

the output average of of values (here .10)

do know why?





wiki

Comments

Post a Comment

Popular posts from this blog

python - Read npy file directly from S3 StreamingBody -

-
i have many .npy (numpy) , .json files saved in s3, need download , load these files. for json files downloading files , loading dictionary using following code: obj = s3.object(bucket, key) response = obj.get() body = response['body'].read().decode('utf-8') data = json.loads(body) that way avoid writing .json file disk , reading it. now want same .npy files, equivalent? currently downloading file, saving temp file on disk , loading np.load avoid if possible. following https://stackoverflow.com/a/28196540/3509999 : obj = s3.object(bucket, key) io.bytesio(obj.get()["body"].read()) f: # rewind file f.seek(0) arr = np.load(f) wiki
Read more

kotlin - Out-projected type in generic interface prohibits the use of metod with generic parameter -

-
i start using kotlin , defined interface this: interface aadapter<vh : recyclerview.viewholder> { fun oncreateaviewholder(parent: viewgroup): vh fun onbindaviewholder(v: vh, position: int) } and when try use on code: class klasa ( private val adapter: aadapter<*> ) { fun dosth(){ //... val vh = this.adapter.oncreateaviewholder(parent) //on below line error adapter.onbindaviewholder(v, position) //... } } i error out-projected type 'aadapter<*>' prohibits use of 'public abstract fun onbindaviewholder(v: t, position: int): unit i tied add "in" or "out" definition i'm confused. how allow it. replace aadapter<*> aadapter<recyclerview.viewholder> . class klasa ( private val adapter: aadapter<recyclerview.viewholder> ) { // ... because have declared aadapter has type parameter vh type subclass of recyclerview....
Read more

Asterisk AGI Python Script to Dialplan does not work -

-
i'm stuck project have check database of sip extension incoming caller id , dial sip extension. below receive when run script on asterisk cli. -- registered sip '9125' @ 192.168.1.102:50142 > saved useragent "zoiper rv2.8.40" peer 9125 [2017-08-22 13:53:33] notice[5095]: chan_sip.c:24558 handle_response_peerpoke: peer '9125' reachable. (17ms / 2000ms) == using sip rtp tos bits 184 == using sip rtp cos mark 5 -- executing [0112617769@from-trunk:1] answer("sip/obitrunk1-0000000d", "") in new stack > 0x1ca50d0 -- probation passed - setting rtp source address 192.168.1.98:16834 -- executing [0112617769@from-trunk:2] agi("sip/obitrunk1-0000000d", "test.py") in new stack -- launched agi script /var/lib/asterisk/agi-bin/test.py args: ['/var/lib/asterisk/agi-bin/test.py'] env line: agi_request: test.py env line: agi_channel: sip/obitrunk1-0000000d env line: agi_language: en env line: a...
Read more