Correction test MobileNet Brutus

higher/compare_res.py

@@ -82,7 +82,7 @@ if __name__ == "__main__":
     nb_run=3
     accs = []
     times = []
-    files = ["res/brutus-tests/log/Aug_mod(Data_augV5(Uniform-14TFx2-MagFxSh)-LeNet)-150epochs(dataug:0)-0in_it-%s.json"%str(run) for run in range(nb_run)]
+    files = ["res/brutus-tests/log/Aug_mod(Data_augV5(Uniform-14TFx3-Mag)-LeNet)-150epochs(dataug:0)-1in_it-%s.json"%str(run) for run in range(nb_run)]
     
     for idx, file in enumerate(files):
         #legend+=str(idx)+'-'+file+'\n'

higher/datasets.py

@@ -50,7 +50,6 @@ class AugmentedDataset(VisionDataset):
         for idx, img in enumerate(self.sup_data):
             self.sup_data[idx]= Image.fromarray(img) #to PIL Image
 
-        self.unsup_ratio=5 #Batch size unsup = train batch size * unsup_ratio
         self.unsup_data=[]
         self.unsup_targets=[]
 
@@ -157,6 +156,120 @@ class AugmentedDataset(VisionDataset):
     def __str__(self):
         return "CIFAR10(Sup:{}-Unsup:{}-{}TF)".format(self.dataset_info['sup'], self.dataset_info['unsup'], len(self._TF))
 
+class AugmentedDatasetV2(VisionDataset):
+    def __init__(self, root, train=True, transform=None, target_transform=None, download=False, subset=None):
+
+        super(AugmentedDatasetV2, self).__init__(root, transform=transform, target_transform=target_transform)
+
+        supervised_dataset = torchvision.datasets.CIFAR10(root, train=train, download=download, transform=transform)
+
+        self.sup_data = supervised_dataset.data if not subset else supervised_dataset.data[subset[0]:subset[1]]
+        self.sup_targets = supervised_dataset.targets if not subset else supervised_dataset.targets[subset[0]:subset[1]]
+        assert len(self.sup_data)==len(self.sup_targets)
+
+        for idx, img in enumerate(self.sup_data):
+            self.sup_data[idx]= Image.fromarray(img) #to PIL Image
+
+        self.unsup_data=[]
+        self.unsup_targets=[]
+        self.origin_idx=[]
+
+        self.dataset_info= {
+            'name': 'CIFAR10',
+            'sup': len(self.sup_data),
+            'unsup': len(self.unsup_data),
+            'length': len(self.sup_data)+len(self.unsup_data),
+        }
+
+
+        self._TF = [
+            ## Geometric TF ##
+            'Rotate',
+            'TranslateX',
+            'TranslateY',
+            'ShearX',
+            'ShearY',
+
+            'Cutout',
+
+            ## Color TF ##
+            'Contrast',
+            'Color',
+            'Brightness',
+            'Sharpness',
+            #'Posterize',
+            #'Solarize',
+
+            'Invert',
+            'AutoContrast',
+            'Equalize',
+        ]
+        self._op_list =[]
+        self.prob=0.5
+        for tf in self._TF:
+            for mag in range(1, 10):
+                self._op_list+=[(tf, self.prob, mag)]
+        self._nb_op = len(self._op_list)
+
+    def __getitem__(self, index):
+        """
+        Args:
+            index (int): Index
+
+        Returns:
+            tuple: (image, target) where target is index of the target class.
+        """
+        aug_img, origin_img, target = self.unsup_data[index], self.sup_data[self.origin_idx[index]], self.unsup_targets[index]
+
+        # doing this so that it is consistent with all other datasets
+        # to return a PIL Image
+        #img = Image.fromarray(img)
+
+        if self.transform is not None:
+            aug_img = self.transform(aug_img)
+            origin_img = self.transform(origin_img)
+
+        if self.target_transform is not None:
+            target = self.target_transform(target)
+
+        return aug_img, origin_img, target
+
+    def augement_data(self, aug_copy=1):
+
+        policies = []
+        for op_1 in self._op_list:
+            for op_2 in self._op_list:
+                policies += [[op_1, op_2]]
+
+        for idx, image in enumerate(self.sup_data):
+            if idx%(self.dataset_info['sup']/5)==0: print("Augmenting data... ", idx,"/", self.dataset_info['sup'])
+            #if idx==10000:break
+
+            for _ in range(aug_copy):
+                chosen_policy = policies[np.random.choice(len(policies))]
+                aug_image = augmentation_transforms.apply_policy(chosen_policy, image, use_mean_std=False) #Cast en float image
+                #aug_image = augmentation_transforms.cutout_numpy(aug_image)
+
+                self.unsup_data+=[(aug_image*255.).astype(self.sup_data.dtype)]#Cast float image to uint8
+                self.unsup_targets+=[self.sup_targets[idx]]
+                self.origin_idx+=[idx]
+
+        #self.unsup_data=(np.array(self.unsup_data)*255.).astype(self.sup_data.dtype) #Cast float image to uint8
+        self.unsup_data=np.array(self.unsup_data)
+        
+        assert len(self.unsup_data)==len(self.unsup_targets)
+       
+        self.dataset_info['unsup']=len(self.unsup_data)
+        self.dataset_info['length']=self.dataset_info['sup']+self.dataset_info['unsup']
+
+
+    def __len__(self):
+        return self.dataset_info['unsup']#self.dataset_info['length']
+
+    def __str__(self):
+        return "CIFAR10(Sup:{}-Unsup:{}-{}TF)".format(self.dataset_info['sup'], self.dataset_info['unsup'], len(self._TF))
+
+
 ### Classic Dataset ###
 data_train = torchvision.datasets.CIFAR10("./data", train=True, download=download_data, transform=transform)
 #data_val = torchvision.datasets.CIFAR10("./data", train=True, download=download_data, transform=transform)

higher/test_brutus.py

@@ -35,7 +35,7 @@ if __name__ == "__main__":
 
 
     n_inner_iter = 1
-    epochs = 150
+    epochs = 200
     dataug_epoch_start=0
 
     #model = LeNet(3,10)
@@ -44,22 +44,6 @@ if __name__ == "__main__":
 
     tf_dict = {k: TF.TF_dict[k] for k in tf_names}
 
-    t0 = time.process_time()
-
-    aug_model = Augmented_model(Data_augV5(TF_dict=tf_dict, N_TF=3, mix_dist=0.0, fixed_prob=True, fixed_mag=True, shared_mag=True), model).to(device)
-    
-    print("{} on {} for {} epochs - {} inner_it".format(str(aug_model), device_name, epochs, n_inner_iter))
-    log= run_dist_dataugV2(model=aug_model, epochs=epochs, inner_it=n_inner_iter, dataug_epoch_start=dataug_epoch_start, print_freq=10, KLdiv=True, loss_patience=None)
-
-    exec_time=time.process_time() - t0
-    ####
-    times = [x["time"] for x in log]
-    out = {"Accuracy": max([x["acc"] for x in log]), "Time": (np.mean(times),np.std(times), exec_time), "Device": device_name, "Param_names": aug_model.TF_names(), "Log": log}
-    filename = "{}-{} epochs (dataug:{})- {} in_it".format(str(aug_model),epochs,dataug_epoch_start,n_inner_iter)
-    with open("res/log/%s.json" % filename, "w+") as f:
-        json.dump(out, f, indent=True)
-        print('Log :\"',f.name, '\" saved !')
-
     ####
     t0 = time.process_time()
 
@@ -77,6 +61,23 @@ if __name__ == "__main__":
         json.dump(out, f, indent=True)
         print('Log :\"',f.name, '\" saved !')
 
+
+    ####
+    t0 = time.process_time()
+
+    aug_model = Augmented_model(Data_augV5(TF_dict=tf_dict, N_TF=3, mix_dist=0.0, fixed_prob=False, fixed_mag=False, shared_mag=False), model).to(device)
+    
+    print("{} on {} for {} epochs - {} inner_it".format(str(aug_model), device_name, epochs, n_inner_iter))
+    log= run_dist_dataugV2(model=aug_model, epochs=epochs, inner_it=n_inner_iter, dataug_epoch_start=dataug_epoch_start, print_freq=10, KLdiv=True, loss_patience=None)
+
+    exec_time=time.process_time() - t0
+    ####
+    times = [x["time"] for x in log]
+    out = {"Accuracy": max([x["acc"] for x in log]), "Time": (np.mean(times),np.std(times), exec_time), "Device": device_name, "Param_names": aug_model.TF_names(), "Log": log}
+    filename = "{}-{} epochs (dataug:{})- {} in_it".format(str(aug_model),epochs,dataug_epoch_start,n_inner_iter)
+    with open("res/log/%s.json" % filename, "w+") as f:
+        json.dump(out, f, indent=True)
+        print('Log :\"',f.name, '\" saved !')
     '''
     res_folder="res/brutus-tests/"
     epochs= 150

higher/train_utils.py

@@ -629,7 +629,7 @@ def run_dist_dataug(model, epochs=1, inner_it=1, dataug_epoch_start=0):
     print("Copy ", countcopy)
     return log
 
-def run_dist_dataugV2(model, epochs=1, inner_it=0, dataug_epoch_start=0, print_freq=1, KLdiv=False, loss_patience=None):
+def run_dist_dataugV2(model, epochs=1, inner_it=0, dataug_epoch_start=0, print_freq=1, KLdiv=False, loss_patience=None, save_sample=False):
     device = next(model.parameters()).device
     log = []
     countcopy=0
@@ -796,8 +796,12 @@ def run_dist_dataugV2(model, epochs=1, inner_it=0, dataug_epoch_start=0, print_f
             model.augment(mode=True)
             if inner_it != 0: high_grad_track = True
 
-    viz_sample_data(imgs=xs, labels=ys, fig_name='samples/data_sample_epoch{}_noTF'.format(epoch))
+    try:
-    viz_sample_data(imgs=model['data_aug'](xs), labels=ys, fig_name='samples/data_sample_epoch{}'.format(epoch))
+        viz_sample_data(imgs=xs, labels=ys, fig_name='samples/data_sample_epoch{}_noTF'.format(epoch))
+        viz_sample_data(imgs=model['data_aug'](xs), labels=ys, fig_name='samples/data_sample_epoch{}'.format(epoch))
+    except:
+        print("Couldn't save finals samples")
+        pass
 
     #print("Copy ", countcopy)
     return log