所以我寫了一個 CNN 模型的代碼。當我用總共大約 200-250 張影像（包括訓練、測驗、驗證）的較小資料集對其進行測驗時，它運行良好。然后我繼續將我的其余資料（總共超過 8000 張照片）移動到我為模型設定的目錄中，在組織檔案夾數小時后，現在它停在應該運行第一個紀元的點。我不知道為什么會這樣。我沒有更改代碼。我需要在周末結束之前提交它，現在我完全一無所知，除錯視窗的代碼和輸出是：
from tensorflow.keras.preprocessing.image import ImageDataGenerator
from keras.layers import Dense, Conv2D, Flatten, MaxPool2D
from tensorflow.keras.preprocessing import image
from tensorflow.keras import layers
from keras.models import Sequential
from tensorflow.keras import Model
import matplotlib.pyplot as plt
import tensorflow.keras.models
from tensorflow import keras
from keras import optimizers
import tensorflow as tf
import numpy as np
import cv2 as cv
import os
img = image.load_img('C:/Users/Asus/Pictures/thesisdata/training/pepsi_500ml_ful/WIN_20210605_02_05_35_Pro.jpg')
plt.imshow(img)
shape = cv.imread('C:/Users/Asus/Pictures/thesisdata/training/pepsi_500ml_ful/WIN_20210605_02_05_35_Pro.jpg').shape
print(shape)
train = ImageDataGenerator(rescale = 1/255,shear_range=0.2, zoom_range=0.2,rotation_range=0.2)
validation = ImageDataGenerator(rescale= 1/255,shear_range=0.2,zoom_range=0.2,validation_split=0.999999999)
train_dataset = train.flow_from_directory('C:/Users/Asus/Pictures/thesisdata/training',target_size=(200,200), batch_size= 10, class_mode= 'categorical', subset='training')
validation_dataset = validation.flow_from_directory('C:/Users/Asus/Pictures/thesisdata/validation',target_size=(200,200), batch_size= 10, class_mode='categorical', subset='validation')
print(train_dataset.class_indices)
model = tf.keras.models.Sequential()
model.add(tf.keras.layers.Conv2D(filters=16,padding='same',strides=2,kernel_size=3,activation='relu',input_shape=(200,200,3)))
model.add(tf.keras.layers.MaxPool2D(pool_size=2,strides=2))
model.add(tf.keras.layers.Flatten())
model.add(tf.keras.layers.Dense(4,activation='softmax'))
opt = keras.optimizers.RMSprop(learning_rate=0.013)
model.compile(loss='categorical_crossentropy',optimizer = opt ,metrics = ['accuracy'])
model_fit = model.fit(train_dataset, steps_per_epoch = 3, epochs = 20, validation_data= validation_dataset)
這是除錯訊息：
C:\Users\Asus\PycharmProjects\helloworld2\venv\Scripts\python.exe C:/Users/Asus/PycharmProjects/helloworld2/venv/hello.py
2021-10-23 18:11:23.847265: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'cudart64_110.dll'; dlerror: cudart64_110.dll not found
2021-10-23 18:11:23.847388: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
(720, 1280, 3)
Found 4964 images belonging to 61 classes.
Found 1553 images belonging to 61 classes.
{'7up_1500ml_emty': 0, '7up_1500ml_ful': 1, '7up_300ml_emty': 2, '7up_300ml_ful': 3, '7up_diet_1500ml_emty': 4, '7up_diet_1500ml_ful': 5, '7up_diet_500ml_emty': 6, '7up_diet_500ml_ful': 7, 'aquafina_500ml_emty': 8, 'aquafina_500ml_ful': 9, 'cocacola_2250ml_emty': 10, 'cocacola_2250ml_ful': 11, 'cocacola_500ml_emty': 12, 'cocacola_500ml_ful': 13, 'fanta_1500ml_emty': 14, 'fanta_1500ml_ful': 15, 'fanta_2250ml_emty': 16, 'fanta_2250ml_ful': 17, 'fanta_500ml_ful': 18, 'gatorade_blue_500ml_ful': 19, 'gatorade_red_500ml_ful': 20, 'gatorade_white_500ml_emty': 21, 'gatorade_white_500ml_ful': 22, 'mirinda_300ml_ful': 23, 'mirinda_500ml_emty': 24, 'mirinda_500ml_ful': 25, 'mtdew_1500ml_emty': 26, 'mtdew_1500ml_ful': 27, 'mtdew_2250ml_emty': 28, 'mtdew_2250ml_ful': 29, 'mtdew_300ml_emty': 30, 'mtdew_300ml_ful': 31, 'mtdew_500ml_emty': 32, 'mtdew_500ml_ful': 33, 'pakola_green_1500ml_emty': 34, 'pakola_green_1500ml_ful': 35, 'pakola_green_500ml_emty': 36, 'pakola_green_500ml_ful': 37, 'pakola_lemon_300ml_ful': 38, 'pakola_lemon_500ml_emty': 39, 'pakola_lemon_500ml_ful': 40, 'pakola_lychee_1500ml_emty': 41, 'pakola_lychee_1500ml_ful': 42, 'pakola_lychee_300ml_emty': 43, 'pakola_lychee_500ml_emty': 44, 'pakola_lychee_500ml_ful': 45, 'pepsi_1500ml_ful': 46, 'pepsi_300ml_ful': 47, 'pepsi_500ml_ful': 48, 'slice_1000ml_emty': 49, 'slice_1000ml_ful': 50, 'slice_355ml_ful': 51, 'sprite_1500ml_emty': 52, 'sprite_1500ml_ful': 53, 'sprite_2250ml_emty': 54, 'sprite_2250ml_ful': 55, 'sprite_500ml_ful': 56, 'sting_red_500ml_ful': 57, 'sting_yellow_500ml_emty': 58, 'sting_yellow_500ml_ful': 59, 'sunlay_300ml_emty': 60}
2021-10-23 18:11:27.764834: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'cudart64_110.dll'; dlerror: cudart64_110.dll not found
2021-10-23 18:11:27.765399: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'cublas64_11.dll'; dlerror: cublas64_11.dll not found
2021-10-23 18:11:27.765975: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'cublasLt64_11.dll'; dlerror: cublasLt64_11.dll not found
2021-10-23 18:11:27.766536: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'cufft64_10.dll'; dlerror: cufft64_10.dll not found
2021-10-23 18:11:27.767063: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'curand64_10.dll'; dlerror: curand64_10.dll not found
2021-10-23 18:11:27.767598: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'cusolver64_11.dll'; dlerror: cusolver64_11.dll not found
2021-10-23 18:11:27.768131: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'cusparse64_11.dll'; dlerror: cusparse64_11.dll not found
2021-10-23 18:11:27.768681: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'cudnn64_8.dll'; dlerror: cudnn64_8.dll not found
2021-10-23 18:11:27.768777: W tensorflow/core/common_runtime/gpu/gpu_device.cc:1835] Cannot dlopen some GPU libraries. Please make sure the missing libraries mentioned above are installed properly if you would like to use GPU. Follow the guide at https://www.tensorflow.org/install/gpu for how to download and setup the required libraries for your platform.
Skipping registering GPU devices...
2021-10-23 18:11:27.769190: I tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX AVX2
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2021-10-23 18:11:27.937756: I tensorflow/compiler/mlir/mlir_graph_optimization_pass.cc:185] None of the MLIR Optimization Passes are enabled (registered 2)
Epoch 1/20
Traceback (most recent call last):
File "C:\Users\Asus\PycharmProjects\helloworld2\venv\hello.py", line 35, in <module>
model_fit = model.fit(train_dataset, steps_per_epoch = 3, epochs = 20, validation_data= validation_dataset)
File "C:\Users\Asus\PycharmProjects\helloworld2\venv\lib\site-packages\keras\engine\training.py", line 1184, in fit
tmp_logs = self.train_function(iterator)
File "C:\Users\Asus\PycharmProjects\helloworld2\venv\lib\site-packages\tensorflow\python\eager\def_function.py", line 885, in __call__
result = self._call(*args, **kwds)
File "C:\Users\Asus\PycharmProjects\helloworld2\venv\lib\site-packages\tensorflow\python\eager\def_function.py", line 950, in _call
return self._stateless_fn(*args, **kwds)
File "C:\Users\Asus\PycharmProjects\helloworld2\venv\lib\site-packages\tensorflow\python\eager\function.py", line 3039, in __call__
return graph_function._call_flat(
File "C:\Users\Asus\PycharmProjects\helloworld2\venv\lib\site-packages\tensorflow\python\eager\function.py", line 1963, in _call_flat
return self._build_call_outputs(self._inference_function.call(
File "C:\Users\Asus\PycharmProjects\helloworld2\venv\lib\site-packages\tensorflow\python\eager\function.py", line 591, in call
outputs = execute.execute(
File "C:\Users\Asus\PycharmProjects\helloworld2\venv\lib\site-packages\tensorflow\python\eager\execute.py", line 59, in quick_execute
tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,
tensorflow.python.framework.errors_impl.InvalidArgumentError: logits and labels must be broadcastable: logits_size=[10,4] labels_size=[10,61]
[[node categorical_crossentropy/softmax_cross_entropy_with_logits (defined at \hello.py:35) ]] [Op:__inference_train_function_626]
Function call stack:
train_function
uj5u.com熱心網友回復：
model.add(tf.keras.layers.Dense(4,activation='softmax'))
由于您的輸出層是 4 而您的班級是：
Found 4964 images belonging to 61 classes.
Found 1553 images belonging to 61 classes.
最有可能的是，您必須更改 4 --> 61
model.add(tf.keras.layers.Dense(4,activation='softmax'))
轉載請註明出處，本文鏈接：https://www.uj5u.com/gongcheng/334341.html