这是我在keras中的代码
batch_size = 16
num_classes = 4
epochs = 30
frames = 5 # The number of frames for each sequence
input_shape = [100 , 100, 3]
def build_rgb_model2():
model = Sequential()
model.add(TimeDistributed(Conv2D(32, (3, 3), padding='same'), input_shape=(frames, 120, 180, 3)))
model.add(TimeDistributed(Activation('relu')))
model.add(TimeDistributed(MaxPooling2D(pool_size=(2, 2))))
model.add(TimeDistributed(Conv2D(32, (3, 3))))
model.add(TimeDistributed(Activation('relu')))
model.add(TimeDistributed(MaxPooling2D(pool_size=(2, 2))))
model.add(TimeDistributed(Conv2D(32, (3, 3))))
model.add(TimeDistributed(Activation('relu')))
model.add(TimeDistributed(MaxPooling2D(pool_size=(2, 2))))
model.add(TimeDistributed(Conv2D(32, (3, 3))))
model.add(TimeDistributed(Activation('relu')))
model.add(TimeDistributed(MaxPooling2D(pool_size=(2, 2))))
model.add(TimeDistributed(Dropout(0.25)))
model.add(TimeDistributed(Flatten()))
model.add(TimeDistributed(Dense(512)))
model.add(TimeDistributed(Dense(32, name="first_dense_rgb")))
model.add(LSTM(20, return_sequences=True, name="lstm_layer_rgb"));
model.add(TimeDistributed(Dense(num_classes), name="time_distr_dense_one_rgb"))
model.add(GlobalAveragePooling1D(name="global_avg_rgb"))
return model
def build_rgb_model():
model = Sequential()
model.add(TimeDistributed(Conv2D(64, (3, 3), padding='same', activation='relu' ), input_shape=(frames, 120, 180, 3)))
#model.add(TimeDistributed(Activation('relu')))
# model.add(TimeDistributed(Conv2D(64, (3, 3), activation='relu', padding='same', input_shape=(frames, 120, 180, 3))))
model.add(TimeDistributed(Conv2D(64, (3, 3), activation='relu', padding='same')))
model.add(TimeDistributed(MaxPooling2D((2, 2), strides=(2, 2))))
model.add(TimeDistributed(Conv2D(128, (3, 3), activation='relu', padding='same')))
model.add(TimeDistributed(Conv2D(128, (3, 3), activation='relu', padding='same')))
model.add(TimeDistributed(MaxPooling2D((2, 2), strides=(2, 2))))
model.add(TimeDistributed(Conv2D(256, (3, 3), activation='relu', padding='same')))
model.add(TimeDistributed(Conv2D(256, (3, 3), activation='relu', padding='same')))
model.add(TimeDistributed(Conv2D(256, (3, 3), activation='relu', padding='same')))
model.add(TimeDistributed(MaxPooling2D((2, 2), strides=(2, 2))))
model.add(TimeDistributed(Conv2D(512, (3, 3), activation='relu', padding='same')))
model.add(TimeDistributed(Conv2D(512, (3, 3), activation='relu', padding='same')))
model.add(TimeDistributed(Conv2D(512, (3, 3), activation='relu', padding='same')))
model.add(TimeDistributed(MaxPooling2D((2, 2), strides=(2, 2))))
model.add(TimeDistributed(Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv1')))
model.add(TimeDistributed(Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv2')))
model.add(TimeDistributed(Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv3')))
model.add(TimeDistributed(MaxPooling2D((2, 2), strides=(2, 2))))
model.add(TimeDistributed(Dropout(0.25)))
model.add(TimeDistributed(Flatten()))
model.add(TimeDistributed(Dense(1024)))
model.add(TimeDistributed(Dense(32, name="first_dense_rgb")))
model.add(LSTM(20, return_sequences=True, name="lstm_layer_rgb"));
model.add(TimeDistributed(Dense(num_classes), name="time_distr_dense_one_rgb"))
model.add(GlobalAveragePooling1D(name="global_avg_rgb"))
return model
def build_flow_model():
model = Sequential()
model.add(TimeDistributed(Conv2D(64, (3, 3), padding='same',activation='relu'), input_shape=(frames, 120, 180, 2)))
# model.add(TimeDistributed(Activation('relu')))
#model.add(TimeDistributed(Conv2D(64, (3, 3), activation='relu', padding='same', input_shape=(frames, 120, 180, 2))))
model.add(TimeDistributed(Conv2D(64, (3, 3), activation='relu', padding='same')))
model.add(TimeDistributed(MaxPooling2D((2, 2), strides=(2, 2))))
model.add(TimeDistributed(Conv2D(128, (3, 3), activation='relu', padding='same')))
model.add(TimeDistributed(Conv2D(128, (3, 3), activation='relu', padding='same')))
model.add(TimeDistributed(MaxPooling2D((2, 2), strides=(2, 2))))
model.add(TimeDistributed(Conv2D(256, (3, 3), activation='relu', padding='same')))
model.add(TimeDistributed(Conv2D(256, (3, 3), activation='relu', padding='same')))
model.add(TimeDistributed(Conv2D(256, (3, 3), activation='relu', padding='same')))
model.add(TimeDistributed(MaxPooling2D((2, 2), strides=(2, 2))))
model.add(TimeDistributed(Conv2D(512, (3, 3), activation='relu', padding='same')))
model.add(TimeDistributed(Conv2D(512, (3, 3), activation='relu', padding='same')))
model.add(TimeDistributed(Conv2D(512, (3, 3), activation='relu', padding='same')))
model.add(TimeDistributed(MaxPooling2D((2, 2), strides=(2, 2))))
model.add(TimeDistributed(Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv1')))
model.add(TimeDistributed(Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv2')))
model.add(TimeDistributed(Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv3')))
model.add(TimeDistributed(MaxPooling2D((2, 2), strides=(2, 2))))
model.add(TimeDistributed(Dropout(0.25)))
model.add(TimeDistributed(Flatten()))
model.add(TimeDistributed(Dense(1024)))
model.add(TimeDistributed(Dense(32, name="first_dense_flow")))
model.add(LSTM(20, return_sequences=True, name="lstm_layer_flow"));
model.add(TimeDistributed(Dense(num_classes), name="time_distr_dense_one_flow"))
model.add(GlobalAveragePooling1D(name="global_avg_flow"))
return model
def build_model():
rgb_model = build_rgb_model()
flow_model = build_flow_model()
out=average([rgb_model.output, flow_model.output])
model=Model([rgb_model.input,flow_model.input], out)
#model.add(add([rgb_model, flow_model]))
model.compile(loss='categorical_crossentropy',
optimizer='rmsprop',
metrics=['accuracy'])
plot_model(model, to_file='model/cnn_lstm.png')
return model
def batch_iter(split_file):
split_data = np.genfromtxt(split_file, dtype=None, delimiter=",")
total_seq_num = len(split_data)
ADRi = "/UCF3"
split_data2 = np.genfromtxt("C.txt", dtype=None, delimiter=",")
num_batches_per_epoch = int(((int(split_data2[4])-1)/frames - 1) / batch_size)-300
total_frames=int(split_data2[4])-1
listing = sorted(os.listdir(ADRi))
indices2=[]
def data_generator():
p = 0
while 1:
indices = np.random.permutation(np.arange(total_seq_num))
t=0
for j in range(total_seq_num):
for k in range(int(split_data[j][1]/frames)):
indices2.append (j*1000+k*frames)
t=t+1
indices3 = np.random.permutation(np.arange(indices2.__len__()))
for batch_num in range(num_batches_per_epoch): # for each batch
start_index = batch_num * batch_size
end_index = ((batch_num + 1) * batch_size) -1
RGB = []
FLOW = []
Y = []
for i in range(start_index, end_index): # for each sequence
ii=int(indices3[i]/1000) # seqnumber
image_dir = split_data[indices[ii]][0].decode("UTF-8")
seq_len = int(split_data[indices[ii]][1])
y = int(split_data[indices[ii]][2])
# To reduce the computational time, data augmentation is performed for each frame
jj= min( int(indices3[i]/1000), seq_len-frames-1)
augs_rgb = []
augs_flow = []
for j in range(jj,jj+frames): # for each frame
# Get frames at regular interval. start from frame index 1
frame = j
hf = h5py.File(image_dir+".h5", 'r')
# rgb image
im = hf.get(str(frame))
#rgb_i = load_img("%s/img_%05d.jpg" % (image_dir, frame), target_size=(224, 224))
rgb = im[:, :, :, (3, 5, 7)].transpose(0,3,1,2)
#img_gen = ImageDataGenerator(horizontal_flip=True)
#= img_gen.apply_transform(rgb)
#img = Image.fromarray(rgb)
#rgb_flip_i=img.transpose(Image.FLIP_LEFT_RIGHT) # augmentation
rgb_flip = np.flip(rgb,2)
#t=np.append(rgb, rgb_flip,axis=0)
t=np.concatenate([rgb],axis=0)
augs_rgb.append(t)
# flow image
flow_x=im[:, :, :, 1]
flow_y = im[:, :, :, 2]
flow_x_flip = - np.flip(flow_x,2) # augmentation
flow_y_flip = np.flip(flow_y,2) # augmentation
flow = np.concatenate([flow_x, flow_y], axis=0)
flow_flip = np.concatenate([flow_x_flip, flow_y_flip], axis=0)
#tt=np.concatenate([flow[None,:,:,:], flow_flip[None,:,:,:]], axis=0)
tt = np.concatenate([flow[None, :, :, :]], axis=0)
augs_flow.append(tt)
augs_rgb = np.array(augs_rgb).transpose((1, 0, 3, 4, 2))
augs_flow = np.array(augs_flow).transpose((1, 0, 3, 4, 2))
RGB.extend(augs_rgb)
FLOW.extend(augs_flow)
Y.extend([y])
RGB1 = np.array(RGB)
FLOW1 = np.array(FLOW)
Y1 = np_utils.to_categorical(Y, num_classes)
p=p+1
yield ([RGB1, FLOW1], Y1)
return num_batches_per_epoch, data_generator()
if __name__ == "__main__":
# Build model
model = build_model()
model.summary()
print("Built model")
# Make batches
train_steps, train_batches = batch_iter(train_split_file)
valid_steps, valid_batches = batch_iter(test_split_file)
# Train model
history = model.fit_generator(train_batches, steps_per_epoch=train_steps,
epochs=10, verbose=1, validation_data=valid_batches,
validation_steps=valid_steps)
plot_history(history)
print("Trained model")
当我将train_steps设置为100时，它可以工作。当我在上次运行中设置真实样本（462）时，出现此错误
461/462 [===========================>。]-ETA：2秒-损失：6.6250- acc：0.4111Traceback（最近通话最近）： Two.py“，第332行，在 validate_steps = valid_steps） 文件“ /home/PycharmProjects/test2/local/lib/python2.7/site-packages/keras/legacy/interfaces.py”， 第91行，在包装器中 return func（* args，** kwargs） 文件“ /home/PycharmProjects/test2/local/lib/python2.7/site-packages/keras/engine/training.py”， 在fit_generator中的第1418行 initial_epoch = initial_epoch） 文件“ /home/PycharmProjects/test2/local/lib/python2.7/site-packages/keras/engine/training_generator.py”， 在fit_generator中的第234行 工人= 0） 文件“ /home/PycharmProjects/test2/local/lib/python2.7/site-packages/keras/legacy/interfaces.py”， 第91行，在包装器中 return func（* args，** kwargs） 文件“ /home/PycharmProjects/test2/local/lib/python2.7/site-packages/keras/engine/training.py”， 第1472行，在validate_generator中 详细=详细） 文件“ /home/PycharmProjects/test2/local/lib/python2.7/site-packages/keras/engine/training_generator.py”， 第330行，在evaluate_generator中 generator_output =下一步（output_generator） 文件“ /home/PycharmProjects/test2/local/lib/python2.7/site-packages/keras/utils/data_utils.py”， 709行，进入 six.reraise（* sys.exc_info（）） 文件“ /home/PycharmProjects/test2/local/lib/python2.7/site-packages/keras/utils/data_utils.py”， 685行，进入 输入= self.queue.get（block = True）.get（） 在get中的文件“ /usr/lib/python2.7/multiprocessing/pool.py”，行567 提高自我价值 IndexError：索引2992超出了尺寸为2992的轴0的边界
我没有任何2992个Prometric值！
答案 0 :(得分：0)
python中的数组从0开始，因此，如果有2992个元素，则最后一个是2991。