So to use files from google drive in google colab I used this code:
from google.colab import drive
drive.mount('/content/gdrive')
!ln -s /content/gdrive/My\ Drive/ /mydrive
!ls /mydrive
Drive already mounted at /content/gdrive; to attempt to forcibly remount, call drive.mount("/content/gdrive", force_remount=True).
app 'Colab Notebooks' lixo 'My Drive' pixellib yolov3
Inside of pixellib I have the folder meat
and the file pretraining.h5
.
I installed this too:
!pip3 install pixellib
Until here, ok, but when I run this code:
import pixellib
from pixellib.custom_train import instance_custom_training
train_maskrcnn = instance_custom_training()
train_maskrcnn.modelConfig(network_backbone = "resnet101", num_classes= 2, batch_size = 4)
train_maskrcnn.load_pretrained_model("/mydrive/pixellib/pretraining.h5")
train_maskrcnn.load_dataset("/mydrive/pixellib/meat")
train_maskrcnn.train_model(num_epochs = 20, augmentation=True, path_trained_models = "/mydrive/pixellib/mask_rcnn_models")
the following error message appears:
Using resnet101 as network backbone For Mask R-CNN model
---------------------------------------------------------------------------
IsADirectoryError Traceback (most recent call last)
<ipython-input-44-8a3b66f50c89> in <module>()
7 train_maskrcnn.modelConfig(network_backbone = "resnet101", num_classes= 2, batch_size = 4)
8 train_maskrcnn.load_pretrained_model("/mydrive/pixellib/pretraining.h5")
----> 9 train_maskrcnn.load_dataset("/mydrive/pixellib/meat")
10 train_maskrcnn.train_model(num_epochs = 20, augmentation=True, path_trained_models = "/mydrive/pixellib/mask_rcnn_models")
7 frames
/usr/local/lib/python3.6/dist-packages/PIL/Image.py in open(fp, mode)
2807
2808 if filename:
-> 2809 fp = builtins.open(filename, "rb")
2810 exclusive_fp = True
2811
IsADirectoryError: [Errno 21] Is a directory: '/mydrive/pixellib/meat/train/78-3.jpg'
What kind of error is that? Something is wrong with my code?
If you have a json for every image in this directory (he said this in a comment), it seems likely to me that one of your json files has a .jpg ending. Either download both json and jpg and confirm that they are the correct file type, or you try to plot the image instead to see if it is an image.