Hi Jeremy, when I use
tfms = tfms_from_model(arch, sz, aug_tfms=transforms_side_on, max_zoom=1.1)
data = ImageClassifierData.from_csv(PATH, 'train', f'{PATH}labels.csv', test_name='test', num_workers = 4, val_idxs=val_idxs, suffix = '.jpg', tfms=tfms, bs=bs)
this works fine, but when I try to run
data.test_ds
The error shows
AttributeError: 'ImageClassifierData' object has no attribute 'test'
what is the output of: !ls {PATH}
get-pip.py sample_submission.csv test.zip
labels.csv sample_submission.csv.zip train
labels.csv.zip test train.zip
this is the output
Hi @sermakarevich, @jeremy and everyone!
I have a error when counting accuracy:
so when i run
log_preds,y = learn.TTA()
probs = np.exp(log_preds)
accuracy(log_preds,y), metrics.log_loss(y, probs)
AttributeError Traceback (most recent call last)
<ipython-input-25-ceca03c60965> in <module>()
1 log_preds,y = learn.TTA()
2 probs = np.exp(log_preds)
----> 3 accuracy(log_preds,y), metrics.log_loss(y, probs)
~/fastai/courses/dl1/fastai/metrics.py in accuracy(preds, targs)
4 def accuracy(preds, targs):
5 preds = np.argmax(preds, axis=1)
----> 6 return (preds==targs).mean()
7
8 def accuracy_thresh(thresh):
`AttributeError: 'bool' object has no attribute 'mean'`
it is happens when indicator is 3/4 or 4/4
Do you have some idea how to fix it?
thank you for so fast reply!
Hi! The shape of my probability is [120,]. How can I write it to csv file for kaggle submission?
Edit: There was some error in learn.TTA() function. Got it right and submitted my first file to the competition. Thanks @jeremy for this great course.
Hi all,
I am following along with the lesson.
I am getting this error on a Paperspace GPU Hourly after running the cell
torch.cuda.set_device(1)
RuntimeError: cuda runtime error (10) : invalid device ordinal at torch/csrc/cuda/Module.cpp:88
From what I am reading I have a feeling it is a driver error but I am unsure how to resolve.
Any help greatly appreciated.
Kind regards,
Luke
You shouldnât run that - thatâs only if you have multiple GPUs. Where did you see this?
BTW, you may find this helpful more generally: http://wiki.fast.ai/index.php/How_to_use_the_Provided_Notebooks
@jeremy I saw that on the video for lesson 2 when you were running through dog breed Kaggle challenge.
I have just been pausing the video and typing out whats in the cells.
Having also issue while trying to runt his line in paperspace:
ConvLearner.pretrained(arch, data)
Error message:
No such file or directory: â/home/paperspace/fastai/courses/dl1/fastai/weights/resnext_101_64x4d.pthâ
Iâve download the weight files and itâs save in fastai folder
I guess this error is related to the path but not sure how to solve it
Move it one folder deeper into fastai/fastai 
Pure magic, thx farlion!
@bushaev Did you ever solve this? For me, itâs now working only on inception_4.
hmm, I donât really remember anymore 
I donât think I did, I probably just used models that worked.
I am getting an error on:
test = pd.DataFrame(np.exp(test))
Value error: Must pass 2-D input.
test = learn.TTA(is_test=True)[0] returns object of shape (5, 10357, 120)
Fixed it.
Just learning to browse through these forums.
Iâve been wondering about the get_cv_idxs(n) and creating a validation set. Is it important to generate a validation set with the same distribution as the training set?
In the implementation, it takes n_val +1 indices from a random permutation based on parameter ânâ. Would it be beneficial to take indices based on the distribution of the images? Or does that not really change anything?
Signature: get_cv_idxs(n, cv_idx=0, val_pct=0.2, seed=42)
Source:
def get_cv_idxs(n, cv_idx=0, val_pct=0.2, seed=42):
np.random.seed(seed)
n_val = int(val_pct*n)
idx_start = cv_idx*n_val
idxs = np.random.permutation(n)
return idxs[idx_start:idx_start+n_val]
File: ~/fastai/courses/dl1/fastai/dataset.py
Type: functionYes have you read http://www.fast.ai/2017/11/13/validation-sets/ ?
Also look at k-fold cross validation as an option
So at the moment, this is not covered in the get_cv_idxs() method.