whenever run the script gives "local variable 'X_train' referenced before assignment".

I am interested to use my own dataset so how can I preprocess it?Do kindly elaborate.

Hello, you have a bug in your code, when you use nn.CrossEntropyLoss() it automatically applies softmax function, so you should input just raw outputs,but instead you input vector in softmax layer and then you apply it to nn.CrossEntropyLoss() loss, that is mistake. here is link:

tensorflow.py的命名要换一下, 不能使用"tensorflow", 否则会找不到真正的tensorflow package。
导致各种报错.

Traceback (most recent call last):
File "/Downloads/Deep-learning-activity-recognition-master/tensorflow.py", line 199, in
network(X_train, Y_train, X_test, Y_test)
File "/Downloads/Deep-learning-activity-recognition-master/tensorflow.py", line 154, in network
config = Config(X_train, Y_train)
File "/Downloads/Deep-learning-activity-recognition-master/tensorflow.py", line 102, in init
'wc1': tf.Variable(tf.random_normal([1, self.kernel_size, self.n_channel, self.depth])),
AttributeError: module 'tensorflow' has no attribute 'Variable'

The real data set link is here :
https://archive.ics.uci.edu/ml/machine-learning-databases/00240/

X, Y and keep_prob are three feeds to the network

X = tf.placeholder(tf.float32, shape=[None, config.input_height, config.input_width, config.n_channel])

你好：为何是9呢？视频 切成一帧zhen?

Hi, this is more of a question. Can I use this to make it work in real time? Like take frames from the webcam video and do analysis?
Thanks

Traceback (most recent call last):
File "main_pytorch.py", line 90, in
train(model, optimizer, train_loader, test_loader)
File "main_pytorch.py", line 33, in train
for index, (sample, target) in enumerate(train_loader):
File "/usr/local/lib/python3.5/dist-packages/torch/utils/data/dataloader.py", line 560, in next
batch = self.collate_fn([self.dataset[i] for i in indices])
File "/usr/local/lib/python3.5/dist-packages/torch/utils/data/dataloader.py", line 560, in
batch = self.collate_fn([self.dataset[i] for i in indices])
File "/root/tcxia/Deep-learning-activity-recognition/pytorch/data_preprocess.py", line 93, in getitem
return self.T(sample), target
File "/usr/local/lib/python3.5/dist-packages/torchvision/transforms/transforms.py", line 61, in call
img = t(img)
File "/usr/local/lib/python3.5/dist-packages/torchvision/transforms/transforms.py", line 164, in call
return F.normalize(tensor, self.mean, self.std, self.inplace)
File "/usr/local/lib/python3.5/dist-packages/torchvision/transforms/functional.py", line 208, in normalize
tensor.sub_(mean[:, None, None]).div_(std[:, None, None])

Hello, found a bug in code. In 'data_preprocess.py' line 52,
I believe the code should be
str_folder = data_folder + 'UCI HAR Dataset/'
instead of
str_folder = 'data_folder' + 'UCI HAR Dataset/'

Link: