Yes! I’ll give this a try in the morning!
Cheers mrfabulous1 
1 Like
Also, for those curious on RAM usage, I have three resnet models loaded in, memory spiked during download etc at ~114 Mbs, but it’s staying at a steady 57 MB once all set up 
Hi @muellerzr.
Just curious since you seem to have waded deep into fastai v2. Did you explore detectron2 + fastai2 models by any chance?
They look awesome and I’d like to use them in fastai2, however I’m not sure how best to leverage them? The topic popped up several times in the forums but I don’t know if someone is already experimenting with it?
The PointRend model looks real nice for instance
Detectron is extremely difficult to get set up… I tried to but getting the environment good is a nightmare so I gave up honestly.
I feel ya. Had similar issues 
Might give it a second try though…
2 Likes
I’ve seen a few repositories that got maskrcnn working with fastai on github (do a search and explore) but that’s the best I got. If you get it working please let us know!
1 Like
not sure where to ask this, but in running 07_Super_Resolution, on an aws deep learning ubuntu instance , i get an exception running this line
learn_gen = create_gen_learner()
and narrowed it down to module.py line 576
def __getattr__(self, name):
if '_parameters' in self.__dict__:
_parameters = self.__dict__['_parameters']
if name in _parameters:
return _parameters[name]
if '_buffers' in self.__dict__:
_buffers = self.__dict__['_buffers']
if name in _buffers:
return _buffers[name]
if '_modules' in self.__dict__:
modules = self.__dict__['_modules']
if name in modules:
return modules[name]
# this line
raise AttributeError("'{}' object has no attribute '{}'".format(
#error msg
'Conv2d' object has no attribute 'weight'
but don’t know enough to figure out what is going on. it works fine in colab. suggestions?
What is the exact versions of the setup? (IE PyTorch, fastai2, fastcore, etc)
here is what i got from a conda env export > environment.yml https://gist.github.com/foobar8675/f6f352f9ddada60a45da6257b4ba949a
and here are what i think are the relevant libraries
- fastai2==0.0.11
- fastcore==0.1.14
- fastprogress==0.2.2
- torch==1.4.0
- torchvision==0.5.0
oh, is torch 1.4 not supported???
No, that setup looks fine by me. I also can’t recreate it on my machine so I’m not sure 
Thank you for looking. Off topic, but I can’t find a tutorial on how you got your imports into colab, for example https://github.com/muellerzr/Practical-Deep-Learning-for-Coders-2.0/tree/master/Computer%20Vision/imports , such that you can access them from a notebook. if you know of one, can you point me to it?
Hi @muellerzr !
I have run the codes on my dataset for object detection (from ur lecture). However, I am unable to get the results of the model. It gives me the following error –
learn.get_preds()
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
~/anaconda3/lib/python3.6/site-packages/fastai2/torch_core.py in to_concat(xs, dim)
216 # in this case we return a big list
--> 217 try: return retain_type(torch.cat(xs, dim=dim), xs[0])
218 except: return sum([L(retain_type(o_.index_select(dim, tensor(i)).squeeze(dim), xs[0])
TypeError: expected Tensor as element 0 in argument 0, but got int
During handling of the above exception, another exception occurred:
TypeError Traceback (most recent call last)
<ipython-input-54-d0be1d9a8327> in <module>()
----> 1 learn.get_preds()
~/anaconda3/lib/python3.6/site-packages/fastai2/learner.py in get_preds(self, ds_idx, dl, with_input, with_decoded, with_loss, act, inner, **kwargs)
202 self(event.begin_epoch if inner else _before_epoch)
203 self._do_epoch_validate(dl=dl)
--> 204 self(event.after_epoch if inner else _after_epoch)
205 if act is None: act = getattr(self.loss_func, 'activation', noop)
206 res = cb.all_tensors()
~/anaconda3/lib/python3.6/site-packages/fastai2/learner.py in __call__(self, event_name)
106 def ordered_cbs(self, cb_func): return [cb for cb in sort_by_run(self.cbs) if hasattr(cb, cb_func)]
107
--> 108 def __call__(self, event_name): L(event_name).map(self._call_one)
109 def _call_one(self, event_name):
110 assert hasattr(event, event_name)
~/anaconda3/lib/python3.6/site-packages/fastcore/foundation.py in map(self, f, *args, **kwargs)
360 else f.format if isinstance(f,str)
361 else f.__getitem__)
--> 362 return self._new(map(g, self))
363
364 def filter(self, f, negate=False, **kwargs):
~/anaconda3/lib/python3.6/site-packages/fastcore/foundation.py in _new(self, items, *args, **kwargs)
313 @property
314 def _xtra(self): return None
--> 315 def _new(self, items, *args, **kwargs): return type(self)(items, *args, use_list=None, **kwargs)
316 def __getitem__(self, idx): return self._get(idx) if is_indexer(idx) else L(self._get(idx), use_list=None)
317 def copy(self): return self._new(self.items.copy())
~/anaconda3/lib/python3.6/site-packages/fastcore/foundation.py in __call__(cls, x, *args, **kwargs)
39 return x
40
---> 41 res = super().__call__(*((x,) + args), **kwargs)
42 res._newchk = 0
43 return res
~/anaconda3/lib/python3.6/site-packages/fastcore/foundation.py in __init__(self, items, use_list, match, *rest)
304 if items is None: items = []
305 if (use_list is not None) or not _is_array(items):
--> 306 items = list(items) if use_list else _listify(items)
307 if match is not None:
308 if is_coll(match): match = len(match)
~/anaconda3/lib/python3.6/site-packages/fastcore/foundation.py in _listify(o)
240 if isinstance(o, list): return o
241 if isinstance(o, str) or _is_array(o): return [o]
--> 242 if is_iter(o): return list(o)
243 return [o]
244
~/anaconda3/lib/python3.6/site-packages/fastcore/foundation.py in __call__(self, *args, **kwargs)
206 if isinstance(v,_Arg): kwargs[k] = args.pop(v.i)
207 fargs = [args[x.i] if isinstance(x, _Arg) else x for x in self.pargs] + args[self.maxi+1:]
--> 208 return self.fn(*fargs, **kwargs)
209
210 # Cell
~/anaconda3/lib/python3.6/site-packages/fastai2/learner.py in _call_one(self, event_name)
109 def _call_one(self, event_name):
110 assert hasattr(event, event_name)
--> 111 [cb(event_name) for cb in sort_by_run(self.cbs)]
112
113 def _bn_bias_state(self, with_bias): return bn_bias_params(self.model, with_bias).map(self.opt.state)
~/anaconda3/lib/python3.6/site-packages/fastai2/learner.py in <listcomp>(.0)
109 def _call_one(self, event_name):
110 assert hasattr(event, event_name)
--> 111 [cb(event_name) for cb in sort_by_run(self.cbs)]
112
113 def _bn_bias_state(self, with_bias): return bn_bias_params(self.model, with_bias).map(self.opt.state)
~/anaconda3/lib/python3.6/site-packages/fastai2/callback/core.py in __call__(self, event_name)
21 _run = (event_name not in _inner_loop or (self.run_train and getattr(self, 'training', True)) or
22 (self.run_valid and not getattr(self, 'training', False)))
---> 23 if self.run and _run: getattr(self, event_name, noop)()
24 if event_name=='after_fit': self.run=True #Reset self.run to True at each end of fit
25
~/anaconda3/lib/python3.6/site-packages/fastai2/callback/core.py in after_fit(self)
93 "Concatenate all recorded tensors"
94 if self.with_input: self.inputs = detuplify(to_concat(self.inputs, dim=self.concat_dim))
---> 95 if not self.save_preds: self.preds = detuplify(to_concat(self.preds, dim=self.concat_dim))
96 if not self.save_targs: self.targets = detuplify(to_concat(self.targets, dim=self.concat_dim))
97 if self.with_loss: self.losses = to_concat(self.losses)
~/anaconda3/lib/python3.6/site-packages/fastai2/torch_core.py in to_concat(xs, dim)
211 def to_concat(xs, dim=0):
212 "Concat the element in `xs` (recursively if they are tuples/lists of tensors)"
--> 213 if is_listy(xs[0]): return type(xs[0])([to_concat([x[i] for x in xs], dim=dim) for i in range_of(xs[0])])
214 if isinstance(xs[0],dict): return {k: to_concat([x[k] for x in xs], dim=dim) for k in xs.keys()}
215 #We may receives xs that are not concatenatable (inputs of a text classifier for instance),
~/anaconda3/lib/python3.6/site-packages/fastai2/torch_core.py in <listcomp>(.0)
211 def to_concat(xs, dim=0):
212 "Concat the element in `xs` (recursively if they are tuples/lists of tensors)"
--> 213 if is_listy(xs[0]): return type(xs[0])([to_concat([x[i] for x in xs], dim=dim) for i in range_of(xs[0])])
214 if isinstance(xs[0],dict): return {k: to_concat([x[k] for x in xs], dim=dim) for k in xs.keys()}
215 #We may receives xs that are not concatenatable (inputs of a text classifier for instance),
~/anaconda3/lib/python3.6/site-packages/fastai2/torch_core.py in to_concat(xs, dim)
211 def to_concat(xs, dim=0):
212 "Concat the element in `xs` (recursively if they are tuples/lists of tensors)"
--> 213 if is_listy(xs[0]): return type(xs[0])([to_concat([x[i] for x in xs], dim=dim) for i in range_of(xs[0])])
214 if isinstance(xs[0],dict): return {k: to_concat([x[k] for x in xs], dim=dim) for k in xs.keys()}
215 #We may receives xs that are not concatenatable (inputs of a text classifier for instance),
~/anaconda3/lib/python3.6/site-packages/fastai2/torch_core.py in <listcomp>(.0)
211 def to_concat(xs, dim=0):
212 "Concat the element in `xs` (recursively if they are tuples/lists of tensors)"
--> 213 if is_listy(xs[0]): return type(xs[0])([to_concat([x[i] for x in xs], dim=dim) for i in range_of(xs[0])])
214 if isinstance(xs[0],dict): return {k: to_concat([x[k] for x in xs], dim=dim) for k in xs.keys()}
215 #We may receives xs that are not concatenatable (inputs of a text classifier for instance),
~/anaconda3/lib/python3.6/site-packages/fastai2/torch_core.py in to_concat(xs, dim)
211 def to_concat(xs, dim=0):
212 "Concat the element in `xs` (recursively if they are tuples/lists of tensors)"
--> 213 if is_listy(xs[0]): return type(xs[0])([to_concat([x[i] for x in xs], dim=dim) for i in range_of(xs[0])])
214 if isinstance(xs[0],dict): return {k: to_concat([x[k] for x in xs], dim=dim) for k in xs.keys()}
215 #We may receives xs that are not concatenatable (inputs of a text classifier for instance),
~/anaconda3/lib/python3.6/site-packages/fastai2/torch_core.py in <listcomp>(.0)
211 def to_concat(xs, dim=0):
212 "Concat the element in `xs` (recursively if they are tuples/lists of tensors)"
--> 213 if is_listy(xs[0]): return type(xs[0])([to_concat([x[i] for x in xs], dim=dim) for i in range_of(xs[0])])
214 if isinstance(xs[0],dict): return {k: to_concat([x[k] for x in xs], dim=dim) for k in xs.keys()}
215 #We may receives xs that are not concatenatable (inputs of a text classifier for instance),
~/anaconda3/lib/python3.6/site-packages/fastai2/torch_core.py in to_concat(xs, dim)
217 try: return retain_type(torch.cat(xs, dim=dim), xs[0])
218 except: return sum([L(retain_type(o_.index_select(dim, tensor(i)).squeeze(dim), xs[0])
--> 219 for i in range_of(o_)) for o_ in xs], L())
220
221 # Cell
~/anaconda3/lib/python3.6/site-packages/fastai2/torch_core.py in <listcomp>(.0)
217 try: return retain_type(torch.cat(xs, dim=dim), xs[0])
218 except: return sum([L(retain_type(o_.index_select(dim, tensor(i)).squeeze(dim), xs[0])
--> 219 for i in range_of(o_)) for o_ in xs], L())
220
221 # Cell
~/anaconda3/lib/python3.6/site-packages/fastcore/utils.py in range_of(x)
162 def range_of(x):
163 "All indices of collection `x` (i.e. `list(range(len(x)))`)"
--> 164 return list(range(len(x)))
165
166 # Cell
TypeError: object of type 'int' has no len()
Can u tell me what did I do wrong?
You can do a !pip list @foobar8675
oh, sorry, wasn’t clear. i wasn’t referring to pip modules, but just files like you have in your github repo under imports/ such as you
inference.py
metrics.py
model.py
utils.py
Thanks for posting these. watching them in preparation for the coming weeks.
@foobar8675 git cline the repository, then just cd until you’re outside the imports directory (IIRC) and then you can do from imports import * (or go one file lower and directly import)
1 Like
I’ll attempt to look at this later this weekend but that’s not really much information to go off of. Refer to here for a good way to report issues:
https://forums.fast.ai/t/how-to-debug-your-code-and-ask-for-help-with-fastai-v2/64196/3
in 07_Super_Resolution in this func get_dls there is this line
dls.c = 3 # For 3 channel image
which i don’t follow. can you elaborate on why this is?
It’s for cnn_learner (it relies on dls.c). Try using it without it and report back what happens 
(specifically look at the last few layers of the model)
I have been trying to load this dataset in https://www.kaggle.com/msheriey/104-flowers-garden-of-eden which is in the format:
-train
-- rose
--daffodil
(classnames)
-val
(classnames)
Inorder to use a fastaiv2 data loader, is this code correct:
DATASET_DIR = '/kaggle/input/104-flowers-garden-of-eden/jpeg-512x512'
TRAIN_DIR = DATASET_DIR + '/train'
VAL_DIR = DATASET_DIR + '/val'
TEST_DIR = DATASET_DIR + '/test'
flower_path = Path(DATASET_DIR)
items = get_image_files(TRAIN_DIR)
flowers = DataBlock(blocks=(ImageBlock, CategoryBlock),
get_items=get_image_files,
splitter=RandomSplitter(),
get_y=items,
item_tfms=Resize(460),
batch_tfms=aug_transforms(size=224, max_rotate=30, min_scale=0.75))
dls = flowers.dataloaders(TRAIN_DIR, bs=32)
dls.show_batch(max_n=9, figsize=(6,7))