18:11:27.764834: W tensorflow/stream_executor/platform/default/dso_:64] Could not load dynamic library 'cudart64_110.dll' dlerror: cudart64_110.dll not found 18:11:23.847388: I tensorflow/stream_executor/cuda/cudart_:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.įound 4964 images belonging to 61 classes.įound 1553 images belonging to 61 classes. 18:11:23.847265: W tensorflow/stream_executor/platform/default/dso_:64] Could not load dynamic library 'cudart64_110.dll' dlerror: cudart64_110.dll not found Here's the debug message: C:\Users\Asus\PycharmProjects\helloworld2\venv\Scripts\python.exe C:/Users/Asus/PycharmProjects/helloworld2/venv/hello.py Model_fit = model.fit(train_dataset, steps_per_epoch = 3, epochs = 20, validation_data= validation_dataset) pile(loss='categorical_crossentropy',optimizer = opt ,metrics = )
Validation_dataset = validation.flow_from_directory('C:/Users/Asus/Pictures/thesisdata/validation',target_size=(200,200), batch_size= 10, class_mode='categorical', subset='validation')
Train_dataset = train.flow_from_directory('C:/Users/Asus/Pictures/thesisdata/training',target_size=(200,200), batch_size= 10, class_mode= 'categorical', subset='training') Train = ImageDataGenerator(rescale = 1/255,shear_range=0.2, zoom_range=0.2,rotation_range=0.2)
I need to submit it before the end of the weekend and I am completely clueless right now the code and the output from the debug window are : from import ImageDataGeneratorįrom keras.layers import Dense, Conv2D, Flatten, MaxPool2Dįrom import image I then proceeded to move the rest of my data (over 8000 photos total) to the directory I had set up for the model and after hours of organizing the folders, now it stops at the point where it should run the first epoch.
It was running alright when I was testing it with a smaller dataset of about 200-250 images total(training, testing, validation included).