pppw / deep-learning-random-explore Goto Github PK

Hi ,

I found this wonderful github repo containing many models:
https://github.com/osmr/imgclsmob/blob/master/pytorch/README.md

Can we include all here, so that we can integrate them with Fastai ?

Thanks in advance for your help!

https://github.com/PPPW/deep-learning-random-explore/blob/master/backward_propagation_for_all/backward_propagation_for_all.ipynb

Here, b's shape is mentioned as (1, M) where M is the number of samples. Shouldn't the size of b be (N', 1)?

There is a weird StopIteration: error happens only with this model.

Example:

from fastai.vision.learner import model_meta

def identity(x): return x

def pnasnet5large(pretrained=False):    
    pretrained = 'imagenet' if pretrained else None
    model = models.cadene_models.pretrainedmodels.pnasnet5large(pretrained=pretrained, num_classes=1000) 
    model.logits = identity
    return nn.Sequential(model)

model_meta[pnasnet5large] =  { 'cut': None, 
                               'split': lambda m: (list(m[0][0].children())[8], m[1]) }

learn = cnn_learner(data, base_arch=pnasnet5large, pretrained=False)

Error:

---------------------------------------------------------------------------
StopIteration                             Traceback (most recent call last)
<ipython-input-79-2126a555d117> in <module>
----> 1 learn = cnn_learner(data, base_arch=pnasnet5large, pretrained=False)

~/anaconda3/envs/fastai-v1/lib/python3.7/site-packages/fastai/vision/learner.py in cnn_learner(data, base_arch, cut, pretrained, lin_ftrs, ps, custom_head, split_on, bn_final, init, concat_pool, **kwargs)
     95     meta = cnn_config(base_arch)
     96     model = create_cnn_model(base_arch, data.c, cut, pretrained, lin_ftrs, ps=ps, custom_head=custom_head,
---> 97         split_on=split_on, bn_final=bn_final, concat_pool=concat_pool)
     98     learn = Learner(data, model, **kwargs)
     99     learn.split(split_on or meta['split'])

~/anaconda3/envs/fastai-v1/lib/python3.7/site-packages/fastai/vision/learner.py in create_cnn_model(base_arch, nc, cut, pretrained, lin_ftrs, ps, custom_head, split_on, bn_final, concat_pool)
     81         split_on:Optional[SplitFuncOrIdxList]=None, bn_final:bool=False, concat_pool:bool=True):
     82     "Create custom convnet architecture"
---> 83     body = create_body(base_arch, pretrained, cut)
     84     if custom_head is None:
     85         nf = num_features_model(nn.Sequential(*body.children())) * (2 if concat_pool else 1)

~/anaconda3/envs/fastai-v1/lib/python3.7/site-packages/fastai/vision/learner.py in create_body(arch, pretrained, cut)
     57     if cut is None:
     58         ll = list(enumerate(model.children()))
---> 59         cut = next(i for i,o in reversed(ll) if has_pool_type(o))
     60     if   isinstance(cut, int):      return nn.Sequential(*list(model.children())[:cut])
     61     elif isinstance(cut, Callable): return cut(model)

StopIteration: 
 

Pytorch recently included pretrained object detection models such FastRCNN (
torchvision.models.detection.faster_rcnn).
Do you know how to integrate them with fastai?

In cnn_archs notebook you mentioned we need to monkey patch the forward pass(excluding final layers). But it seems like you've also excluded initial transform_input part as well.

if self.transform_input:
            x = x.clone()
            x[:, 0] = x[:, 0] * (0.229 / 0.5) + (0.485 - 0.5) / 0.5
            x[:, 1] = x[:, 1] * (0.224 / 0.5) + (0.456 - 0.5) / 0.5
            x[:, 2] = x[:, 2] * (0.225 / 0.5) + (0.406 - 0.5) / 0.5

Although I tried to add these lines to your notebook and it ran without any issue. But is there any specific reason to skip this part ?

Hi,

I appreciate this github repo.
When we want to cut the last few layers of nasnet,
you recommend to change it into an identity function.
I researched, but I can't do this.
Could you tell me how to do this??

Thanks in advance for your help.

Hi, thanks for creating these examples!

I used the cadene alexnet and dog/cat breed dataset to create a learner. learn.model prints the right model, but learn.summary() prints the wrong model head. Any idea what's going wrong?

pretrained='imagenet'

def alexnet_cadene(*args):
    model = pretrainedmodels.__dict__['alexnet'](pretrained=pretrained)
    sz = pretrainedmodels.pretrained_settings['alexnet']['imagenet']['input_size'][-1]
    data.sz = data.one_batch()[0].size()[-1]
    if data.sz != sz:
        raise ValueError(f'data size should be {sz} but is instead {data.sz}')    
    model.last_linear.out_features = data.c
    all_layers = list(model.children())
    model = nn.Sequential(all_layers[0], nn.Sequential(Flatten(), *all_layers[1:]))    
    return model

arch_summary(lambda _: alexnet_cadene()) # overall
arch_summary(lambda _: next(alexnet_cadene().children())) # body
arch_summary(lambda _: list(alexnet_cadene().children())[1]) # head

learn = create_cnn(data,alexnet_cadene,custom_head=children(alexnet_cadene())[1],metrics=error_rate,
                  split_on= lambda m: (m[0][0][6],m[1],m[1][7]))

get_groups(nn.Sequential(*learn.model[0][0], *learn.model[1]), learn.layer_groups)

print(learn.layer_groups)

print(learn.model) 
print(learn.summary()) # why is the model summary wrong?
# last linear layer says 1000 classes when my dataset has 37

Hi, were you able to get a Learner to work for either torchvision inception_v3 or cadene inceptionv3? I'm able to use Learner directly rather than create_cnn, but learn.summary() fails with AttributeError: 'NoneType' object has no attribute 'shape'

Hi,
When I am trying to use unet_learner of fastai with se_resnext101_32x4d I am getting below error:
`---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
in
1 # Fit one cycle of 6 epochs with max lr of 1e-3
----> 2 learn.fit_one_cycle(6)

/opt/conda/lib/python3.6/site-packages/fastai/train.py in fit_one_cycle(learn, cyc_len, max_lr, moms, div_factor, pct_start, final_div, wd, callbacks, tot_epochs, start_epoch)
20 callbacks.append(OneCycleScheduler(learn, max_lr, moms=moms, div_factor=div_factor, pct_start=pct_start,
21 final_div=final_div, tot_epochs=tot_epochs, start_epoch=start_epoch))
---> 22 learn.fit(cyc_len, max_lr, wd=wd, callbacks=callbacks)
23
24 def lr_find(learn:Learner, start_lr:Floats=1e-7, end_lr:Floats=10, num_it:int=100, stop_div:bool=True, wd:float=None):

/opt/conda/lib/python3.6/site-packages/fastai/basic_train.py in fit(self, epochs, lr, wd, callbacks)
198 callbacks = [cb(self) for cb in self.callback_fns + listify(defaults.extra_callback_fns)] + listify(callbacks)
199 if defaults.extra_callbacks is not None: callbacks += defaults.extra_callbacks
--> 200 fit(epochs, self, metrics=self.metrics, callbacks=self.callbacks+callbacks)
201
202 def create_opt(self, lr:Floats, wd:Floats=0.)->None:

/opt/conda/lib/python3.6/site-packages/fastai/basic_train.py in fit(epochs, learn, callbacks, metrics)
99 for xb,yb in progress_bar(learn.data.train_dl, parent=pbar):
100 xb, yb = cb_handler.on_batch_begin(xb, yb)
--> 101 loss = loss_batch(learn.model, xb, yb, learn.loss_func, learn.opt, cb_handler)
102 if cb_handler.on_batch_end(loss): break
103

/opt/conda/lib/python3.6/site-packages/fastai/basic_train.py in loss_batch(model, xb, yb, loss_func, opt, cb_handler)
24 if not is_listy(xb): xb = [xb]
25 if not is_listy(yb): yb = [yb]
---> 26 out = model(*xb)
27 out = cb_handler.on_loss_begin(out)
28

/opt/conda/lib/python3.6/site-packages/torch/nn/modules/module.py in call(self, *input, **kwargs)
491 result = self._slow_forward(*input, **kwargs)
492 else:
--> 493 result = self.forward(*input, **kwargs)
494 for hook in self._forward_hooks.values():
495 hook_result = hook(self, input, result)

/opt/conda/lib/python3.6/site-packages/fastai/layers.py in forward(self, x)
134 for l in self.layers:
135 res.orig = x
--> 136 nres = l(res)
137 # We have to remove res.orig to avoid hanging refs and therefore memory leaks
138 res.orig = None

/opt/conda/lib/python3.6/site-packages/torch/nn/modules/module.py in call(self, *input, **kwargs)
491 result = self._slow_forward(*input, **kwargs)
492 else:
--> 493 result = self.forward(*input, **kwargs)
494 for hook in self._forward_hooks.values():
495 hook_result = hook(self, input, result)

/opt/conda/lib/python3.6/site-packages/fastai/layers.py in forward(self, x)
148 "Merge a shortcut with the result of the module by adding them or concatenating thme if dense=True."
149 def init(self, dense:bool=False): self.dense=dense
--> 150 def forward(self, x): return torch.cat([x,x.orig], dim=1) if self.dense else (x+x.orig)
151
152 def res_block(nf, dense:bool=False, norm_type:Optional[NormType]=NormType.Batch, bottle:bool=False, **conv_kwargs):

RuntimeError: invalid argument 0: Sizes of tensors must match except in dimension 1. Got 256 and 128 in dimension 2 at /opt/conda/conda-bld/pytorch_1556653099582/work/aten/src/THC/generic/THCTensorMath.cu:71
`
Below is the code I am using:

`SZ = 256
BS=16

MODEL_PATH = "/kaggle/working/"

data = (SegmentationItemList.from_folder(path=path/'train')
.split_by_rand_pct(0.2)
.label_from_func(lambda x : str(x).replace('train', 'masks'), classes=[0, 1])
.add_test((path/'test').ls(), label=None)
.transform(get_transforms(), size=SZ, tfm_y=True)
.databunch(path=Path('.'), bs=BS)
.normalize(imagenet_stats))

def se_resnext101(pretrained=True):
pretrained = 'imagenet' if pretrained else None
model = pretrainedmodels.dict'se_resnext101_32x4d'
model.load_state_dict(torch.load("../input/preptrainedmode-weight/se_resnext101_32x4d-3b2fe3d8.pth"))
return model

learn = unet_learner(data, se_resnext101, pretrained=True,path=MODEL_PATH,
cut=-2, split_on=lambda m: (m[0][4], m[1]),metrics=[dice])

learn.fit_one_cycle(6) # this line is giving above error`

Thanks in advance for your help!

my code in jupyter notebook:

from torchvision.models import *
import pretrainedmodels

from fastai.vision import *
from fastai.vision.models import *
from fastai.vision.learner import model_meta

from utils import *
import sys

def se_resnet50(pretrained=False):
    pretrained = 'imagenet' if pretrained else None
    model = pretrainedmodels.se_resnet50(pretrained=pretrained)
    return model

arch_summary(se_resnet50)

got the error below:

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-72-da671789676a> in <module>
     14     return model
     15 
---> 16 arch_summary(se_resnet50)

NameError: name 'arch_summary' is not defined

Hi,

When I am trying to use nasnetalarge I am getting AssertionError. Below is the code and error details.

Code

def nasnetalarge(pretrained=True): pretrained = 'imagenet' if pretrained else None model = pretrainedmodels.__dict__['nasnetalarge'](pretrained=pretrained) return model
This is causing error:
learn = create_cnn(data, nasnetalarge, pretrained=True,path=MODEL_PATH, cut=-2, split_on=lambda m: (m[0][4], m[1]))

Error:
`AssertionError Traceback (most recent call last)
in ()
1 learn = create_cnn(data, nasnetalarge, pretrained=True,path=MODEL_PATH,
----> 2 cut=-2, split_on=lambda m: (m[0][4], m[1]))

/opt/conda/lib/python3.6/site-packages/fastai/vision/learner.py in create_cnn(data, arch, cut, pretrained, lin_ftrs, ps, custom_head, split_on, bn_final, **kwargs)
53 "Build convnet style learners."
54 meta = cnn_config(arch)
---> 55 body = create_body(arch, pretrained, cut)
56 nf = num_features_model(body) * 2
57 head = custom_head or create_head(nf, data.c, lin_ftrs, ps=ps, bn_final=bn_final)

/opt/conda/lib/python3.6/site-packages/fastai/vision/learner.py in create_body(arch, pretrained, cut, body_fn)
30 def create_body(arch:Callable, pretrained:bool=True, cut:Optional[int]=None, body_fn:Callable[[nn.Module],nn.Module]=None):
31 "Cut off the body of a typically pretrained model at cut or as specified by body_fn."
---> 32 model = arch(pretrained)
33 if not cut and not body_fn: cut = cnn_config(arch)['cut']
34 return (nn.Sequential(*list(model.children())[:cut]) if cut

in nasnetalarge(pretrained)
1 def nasnetalarge(pretrained=True):
2 pretrained = 'imagenet' if pretrained else None
----> 3 model = pretrainedmodels.dict'nasnetalarge'
4 return model

/opt/conda/lib/python3.6/site-packages/pretrainedmodels/models/nasnet.py in nasnetalarge(num_classes, pretrained)
613 settings = pretrained_settings['nasnetalarge'][pretrained]
614 assert num_classes == settings['num_classes'],
--> 615 "num_classes should be {}, but is {}".format(settings['num_classes'], num_classes)
616
617 # both 'imagenet'&'imagenet+background' are loaded from same parameters

AssertionError: num_classes should be 1000, but is 1001`

On separate note,From where I can call Arch_summary?
arch_summary(resnet34)
I am getting error:
`NameError Traceback (most recent call last)
in ()
----> 1 arch_summary(resnet34)

NameError: name 'arch_summary' is not defined`

Hi ,

When I tried using resnext101 in kaggle kernel

learn = create_cnn(data, resnext101_32x4d, pretrained=False,
                  cut=-2, split_on=lambda m: (m[0][6], m[1]))

I got below error:
`---------------------------------------------------------------------------
OSError Traceback (most recent call last)
in ()
1 learn = create_cnn(data, resnext101_32x4d, pretrained=False,
----> 2 cut=-2, split_on=lambda m: (m[0][6], m[1]))

/opt/conda/lib/python3.6/site-packages/fastai/vision/learner.py in create_cnn(data, arch, cut, pretrained, lin_ftrs, ps, custom_head, split_on, bn_final, **kwargs)
57 head = custom_head or create_head(nf, data.c, lin_ftrs, ps=ps, bn_final=bn_final)
58 model = nn.Sequential(body, head)
---> 59 learn = Learner(data, model, **kwargs)
60 learn.split(ifnone(split_on,meta['split']))
61 if pretrained: learn.freeze()

in init(self, data, model, opt_func, loss_func, metrics, true_wd, bn_wd, wd, train_bn, path, model_dir, callback_fns, callbacks, layer_groups)

/opt/conda/lib/python3.6/site-packages/fastai/basic_train.py in post_init(self)
144 "Setup path,metrics, callbacks and ensure model directory exists."
145 self.path = Path(ifnone(self.path, self.data.path))
--> 146 (self.path/self.model_dir).mkdir(parents=True, exist_ok=True)
147 self.model = self.model.to(self.data.device)
148 self.loss_func = ifnone(self.loss_func, self.data.loss_func)

/opt/conda/lib/python3.6/pathlib.py in mkdir(self, mode, parents, exist_ok)
1244 self._raise_closed()
1245 try:
-> 1246 self._accessor.mkdir(self, mode)
1247 except FileNotFoundError:
1248 if not parents or self.parent == self:

/opt/conda/lib/python3.6/pathlib.py in wrapped(pathobj, *args)
385 @functools.wraps(strfunc)
386 def wrapped(pathobj, *args):
--> 387 return strfunc(str(pathobj), *args)
388 return staticmethod(wrapped)
389

OSError: [Errno 30] Read-only file system: '../input/models'`

What is way around of this?

Hi ,
As per table present in below link:
https://github.com/rwightman/pytorch-image-models/blob/master/results/results-all.csv

ig_resnext101 models like : ig_resnext101_32x16d , ig_resnext101_32x32d and ig_resnext101_32x48d give great results.

Can we include these here ?

Thanks in advance!

Hi,
Can we implement new EfficientNet in this package?
Details: [https://ai.googleblog.com/2019/05/efficientnet-improving-accuracy-and.html]

I tried implementing it with Fastai, but getting error.
Below is the code:
`!pip install efficientnet_pytorch
from efficientnet_pytorch import EfficientNet

def efficientnet(model_name='efficientnet-b0',**kwargs):
return EfficientNet.from_pretrained(model_name).to(device)

getting error here

learn = cnn_learner(data_large, efficientnet, metrics=accuracy, model_dir=MODEL_PATH)`

Error:
`---------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
in ()
----> 1 learn = cnn_learner(data_large, efficientnet, metrics=accuracy, model_dir=MODEL_PATH)

/opt/conda/lib/python3.6/site-packages/fastai/vision/learner.py in cnn_learner(data, base_arch, cut, pretrained, lin_ftrs, ps, custom_head, split_on, bn_final, init, concat_pool, **kwargs)
95 meta = cnn_config(base_arch)
96 model = create_cnn_model(base_arch, data.c, cut, pretrained, lin_ftrs, ps=ps, custom_head=custom_head,
---> 97 split_on=split_on, bn_final=bn_final, concat_pool=concat_pool)
98 learn = Learner(data, model, **kwargs)
99 learn.split(split_on or meta['split'])

/opt/conda/lib/python3.6/site-packages/fastai/vision/learner.py in create_cnn_model(base_arch, nc, cut, pretrained, lin_ftrs, ps, custom_head, split_on, bn_final, concat_pool)
81 split_on:Optional[SplitFuncOrIdxList]=None, bn_final:bool=False, concat_pool:bool=True):
82 "Create custom convnet architecture"
---> 83 body = create_body(base_arch, pretrained, cut)
84 if custom_head is None:
85 nf = num_features_model(nn.Sequential(*body.children())) * (2 if concat_pool else 1)

/opt/conda/lib/python3.6/site-packages/fastai/vision/learner.py in create_body(arch, pretrained, cut)
53 def create_body(arch:Callable, pretrained:bool=True, cut:Optional[Union[int, Callable]]=None):
54 "Cut off the body of a typically pretrained model at cut (int) or cut the model as specified by cut(model) (function)."
---> 55 model = arch(pretrained)
56 cut = ifnone(cut, cnn_config(arch)['cut'])
57 if cut is None:

in efficientnet(model_name, **kwargs)
1 def efficientnet(model_name='efficientnet-b0',**kwargs):
----> 2 return EfficientNet.from_pretrained(model_name).to(device)

/opt/conda/lib/python3.6/site-packages/efficientnet_pytorch/model.py in from_pretrained(cls, model_name)
185 @classmethod
186 def from_pretrained(cls, model_name):
--> 187 model = EfficientNet.from_name(model_name)
188 load_pretrained_weights(model, model_name)
189 return model

/opt/conda/lib/python3.6/site-packages/efficientnet_pytorch/model.py in from_name(cls, model_name, override_params)
179 @classmethod
180 def from_name(cls, model_name, override_params=None):
--> 181 cls._check_model_name_is_valid(model_name)
182 blocks_args, global_params = get_model_params(model_name, override_params)
183 return EfficientNet(blocks_args, global_params)

/opt/conda/lib/python3.6/site-packages/efficientnet_pytorch/model.py in check_model_name_is_valid(cls, model_name, also_need_pretrained_weights)
201 num_models = 4 if also_need_pretrained_weights else 8
202 valid_models = ['efficientnet_b'+str(i) for i in range(num_models)]
--> 203 if model_name.replace('-','') not in valid_models:
204 raise ValueError('model_name should be one of: ' + ', '.join(valid_models))

AttributeError: 'bool' object has no attribute 'replace'`