OS ERROR in Deep Learning 2018 part 1 chap 1

Can Someone please help me in solving the error posted below. I’m using my Desktop with Ubuntu 18.04 and Cuda 9.0. All the dependencies and CUDA are running properly. I have tried giving my data folder all read and write capabilities(chmod -R 777 home/data/) but it is not working.

OSError Traceback (most recent call last)
in ()
1 arch=resnet34
2 data = ImageClassifierData.from_paths(PATH, tfms=tfms_from_model(arch, sz))
----> 3 learn = ConvLearner.pretrained(arch, data, precompute=True)
4 #learn.fit(0.01, 2)

~/fastai/courses/dl1/fastai/conv_learner.py in pretrained(cls, f, data, ps, xtra_fc, xtra_cut, custom_head, precompute, pretrained, **kwargs)
112 models = ConvnetBuilder(f, data.c, data.is_multi, data.is_reg,
113 ps=ps, xtra_fc=xtra_fc, xtra_cut=xtra_cut, custom_head=custom_head, pretrained=pretrained)
–> 114 return cls(data, models, precompute, **kwargs)
116 @classmethod

~/fastai/courses/dl1/fastai/conv_learner.py in init(self, data, models, precompute, **kwargs)
98 if hasattr(data, ‘is_multi’) and not data.is_reg and self.metrics is None:
99 self.metrics = [accuracy_thresh(0.5)] if self.data.is_multi else [accuracy]
–> 100 if precompute: self.save_fc1()
101 self.freeze()
102 self.precompute = precompute

~/fastai/courses/dl1/fastai/conv_learner.py in save_fc1(self)
177 m=self.models.top_model
178 if len(self.activations[0])!=len(self.data.trn_ds):
–> 179 predict_to_bcolz(m, self.data.fix_dl, act)
180 if len(self.activations[1])!=len(self.data.val_ds):
181 predict_to_bcolz(m, self.data.val_dl, val_act)

~/fastai/courses/dl1/fastai/model.py in predict_to_bcolz(m, gen, arr, workers)
18 y = to_np(m(VV(x)).data)
19 with lock:
—> 20 arr.append(y)
21 arr.flush()

bcolz/carray_ext.pyx in bcolz.carray_ext.carray.append()

bcolz/carray_ext.pyx in bcolz.carray_ext.chunks.append()

bcolz/carray_ext.pyx in bcolz.carray_ext.chunks._save()

OSError: [Errno 30] Read-only file system: '/home/nipun_dl/data/dogscats/tmp/x_act_resnet34_0_224.bc/data/__0.blp

Looks like you can’t write to dogscats… have you tried with precompute=False?