search

experiencor / keras-yolo2

Easy training on custom dataset. Various backends (MobileNet and SqueezeNet) supported. A YOLO demo to detect raccoon run entirely in brower is accessible at https://git.io/vF7vI (not on Windows).
MIT License
1.73k stars 785 forks source link

FileNotFoundError: [WinError 3] The system cannot find the path specified #334

Closed Yufeng4024 closed 6 years ago

Yufeng4024 commented 6 years ago

In running the code of "keras-yolo2/Yolo Step-by-Step.ipynb" in Windows Jupyter environment, I got the following error:

FileNotFoundError: [WinError 3] The system cannot find the path specified: 'C:\Users\Yufeng2/logs/'

Here is the code cell that caused the error:

tbcounter = len([log for log in os.listdir(os.path.expanduser('~/logs/')) if 'coco' in log]) + 1 tensorboard = TensorBoard(logdir=os.path.expanduser('~/logs/') + 'coco' + '_' + str(tb_counter), histogram_freq=0, write_graph=True, write_images=False)

optimizer = Adam(lr=0.5e-4, beta_1=0.9, beta_2=0.999, epsilon=1e-08, decay=0.0)

optimizer = SGD(lr=1e-4, decay=0.0005, momentum=0.9)

optimizer = RMSprop(lr=1e-4, rho=0.9, epsilon=1e-08, decay=0.0)

model.compile(loss=custom_loss, optimizer=optimizer)

model.fit_generator(generator = train_batch, steps_per_epoch = len(train_batch), epochs = 100, verbose = 1, validation_data = valid_batch, validation_steps = len(valid_batch), callbacks = [early_stop, checkpoint, tensorboard], max_queue_size = 3)

Appreciate any advice.

Yufeng4024 commented 6 years ago

Not sure why part of the code is crossed out above. It is not crossed out in the real code.