CNN predict always the same output

I’m new on neural networks and i’m working on prediction for images. I would like to predict 101 data point from an image. I’ve tried the following code, but when I predict I get always the same prediction.
I’ve also tried with more epochs, different layers, different activation functions and got the same problem.
Any idea to solve this issue ?

Here is my code :

import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
from matplotlib import image
import os
import random

Trainingfolder =r '---\Dataset\Dataset1\Trainingset'  
Testfolder = r'---\Dataset\Dataset1\Testset'  

image_files = [os.path.join(Trainingfolder, f) for f in os.listdir(Trainingfolder) if f.endswith('.jpeg')]

for i in range(5):
    imgfile = random.choice(image_files)
    img = image.imread(imgfile)
    outname = imgfile[0:-5] + ".mat"
    outfile =, squeeze_me=True,struct_as_record=False)
    output = outfile['output'].AnkleFlexExt

def create_dataset(datafolder):
    image_files = [os.path.join(datafolder, f) for f in os.listdir(datafolder) if f.endswith('.jpeg')]

    img_data_array = []
    output_data = []

    for imgfile in image_files:
        imag = image.imread(imgfile)
        imag = np.array(imag)
        imag = imag.astype('float64')
        imag /= 255 
        outname = imgfile[0:-5] + ".mat"
        outfile =, squeeze_me=True,struct_as_record=False)
        output = outfile['output'].AnkleFlexExt
    return img_data_array, output_data

img_Trainingdata, output_Trainingdata = create_dataset(Trainingfolder)

model = tf.keras.Sequential()

model.add(tf.keras.layers.Conv2D(64, kernel_size=(3,3), activation='relu', input_shape=(101,9,3))) 
model.add(tf.keras.layers.MaxPool2D(pool_size=(2, 2), padding='same'))
model.add(tf.keras.layers.Conv2D(128, kernel_size=(3,3), activation='relu')) 
model.add(tf.keras.layers.MaxPool2D(pool_size=(2, 2)))
model.add(tf.keras.layers.Dense(3000, activation = 'relu')) 

adam = tf.keras.optimizers.Adam(learning_rate=0.001, beta_1=0.9, beta_2=0.999, amsgrad=False);
model.compile(optimizer=adam, loss='mse', metrics=["mse"])

Layer (type) Output Shape Param #
conv2d_2 (Conv2D) (None, 99, 7, 64) 1792
max_pooling2d (MaxPooling2D) (None, 50, 4, 64) 0
conv2d_3 (Conv2D) (None, 48, 2, 128) 73856
max_pooling2d_1 (MaxPooling2D) (None, 24, 1, 128) 0
flatten_1 (Flatten) (None, 3072) 0
dense_2 (Dense) (None, 3000) 9219000
dense_3 (Dense) (None, 101) 303101

Total params: 9,597,749
Trainable params: 9,597,749
Non-trainable params: 0

history =, np.float64), y=np.array(output_Trainingdata, np.float64), epochs=1)

36/36 [==============================] - 2s 55ms/step - loss: 0.0639 - mse: 0.0639

def load_Testdata(dataname):    

   img_data_array = []
   imag = image.imread(imgfile)
   imag = np.array(imag)
   imag = imag.astype('float64')
   imag /= 255 
   return img_data_array

image_test = [os.path.join(Testfolder, f) for f in os.listdir(Testfolder) if f.endswith('.jpeg')]



for itest in image_test:

    outname = itest[0:-5] + ".mat"
    outfile =, squeeze_me=True,struct_as_record=False)
    output = outfile['output'].AnkleFlexExt
    plt.plot(output, color='blue', label='Measured')

for itest in image_test:
    img_test = load_Testdata(itest)    
    pred = model.predict (x=np.array(img_test, np.float64))
    pred = pred[0]
    plt.plot(pred, color='red', label='Predicted')

plt.title('Ankle Flex-Ext Moment')
plt.xlabel('% cycle')


Hi @Ozan_Simon, According to my understanding in the create dataset function you have mentioned imgfile[0:-5] + “.mat” which will generate a error because imgfile[0:-5] will produce a list and ‘.mat’ is a string you can not concatenate list and string. And in the model model.add(tf.keras.layers.Dense(3000, activation = ‘relu’)) try removing this layer and train your model. Thank You.

Hi @Kiran_Sai_Ramineni,

Thank you for your answer.

imgfile is in the for loop, so imgfile [0:-5] + “.mat looks like : ‘- - - \Trainingset\1.mat’. then the output data are loaded and added to the output_data list which contains the data from each trial.

I tried to remove the layer but I still predict the same output.