KervinBill commented 7 years ago

Using Theano backend. Traceback (most recent call last): File "scripts/run_all_pipeline.py", line 8, in from src.data import import_labels ImportError: No module named src.data

albertomontesg commented 7 years ago

To solve this it requires to add the src folder into PYTHONPATH: export PYTHONPATH='$PYTHONPATH:/path/to/src'

KervinBill commented 7 years ago

Thanks， I've solved. But when I try again, I got this: Using Theano backend. Reading Video... Traceback (most recent call last): File "scripts/run_all_pipeline.py", line 188, in args.activity_threshold File "scripts/run_all_pipeline.py", line 22, in run_all_pipeline video_array = video_to_array(input_video, resize=input_size) File "/path/toactivitynet-2016-cvprw-master/venv/local/lib/python2.7/site-packages/src/io.py", line 38, in video_to_array raise Exception('Could not open the video') Exception: Could not open the video

Does it mean I have opencv install inside the virtual environment ? my machine has OPENCV install. Thank u very much.

albertomontesg commented 7 years ago

This means that OpenCV is not able to open the file. The usual setup is to create a virtual environment with --system-site-packages so if you have OpenCV installed on your system, it will be accessible on the virtual environment.

If you have already done this, take a look to the video where this exception is happening and maybe it can be due to incompatibility or file being damaged.

dudtroc commented 7 years ago

(theano3) ailab@ailab-All-Series:~/HAR/activitynet-2016-cvprw-master$ python scripts/run_all_pipeline.py -i data/activitynet/GCtrfXIBbwA.mp4 Using Theano backend. Using gpu device 0: GeForce GTX TITAN X (CNMeM is disabled, cuDNN 5005) Reading Video... 3.2.0 # print(cv2.version) data/activitynet/GCtrfXIBbwA.mp4 # print(video_path) Unable to stop the stream: Inappropriate ioctl for device <VideoCapture 0x7fc870457f90> Traceback (most recent call last): File "scripts/run_all_pipeline.py", line 192, in args.activity_threshold File "scripts/run_all_pipeline.py", line 26, in run_all_pipeline video_array = video_to_array(input_video, resize=input_size) File "./src/io.py", line 42, in video_to_array raise Exception('Could not open the video') Exception: Could not open the video

I also tried about it but it's still not working I'm using the actvitynet dataset and installed opencv by the conda instruction

thomhert commented 7 years ago

Hi, When running run_all_pipeline.py, i got these errors:

Classification:
0.9505  Dodgeball
0.0040  Rope skipping
0.0024  Breakdancing
0.0013  Futsal
0.0011  Belly dance
Traceback (most recent call last):
  File "scripts/run_all_pipeline.py", line 188, in <module>
    args.activity_threshold
  File "scripts/run_all_pipeline.py", line 73, in run_all_pipeline
    activity_threshold
  File "/.../.../data/theano/activitynet-2016-cvprw-master/src/processing.py", line 52, in activity_localization
    scores.append(np.mean(sequence_class_prob[s:e,activity_idx]))
TypeError: slice indices must be integers or None or have an __index__ method

Something wrong for activity localization, do you know why? Thanks

dudtroc commented 7 years ago

I don't know exactly what is something wrong

I guess that keras version is different or uninstalled numpy

this is my result on my computer [image: 본문 이미지 1] I execute this program on keras102 version

so if you want to install keras102 version run this instruction

pip install git+git://github.com/fchollet/keras.git@1.0.2

2017-02-24 19:09 GMT+09:00 thomhert notifications@github.com:

Hi, When running run_all_pipeline.py, i got these errors:

Classification: 0.9505 Dodgeball 0.0040 Rope skipping 0.0024 Breakdancing 0.0013 Futsal 0.0011 Belly dance Traceback (most recent call last): File "scripts/run_all_pipeline.py", line 188, in args.activity_threshold File "scripts/run_all_pipeline.py", line 73, in run_all_pipeline activity_threshold File "/.../.../data/theano/activitynet-2016-cvprw-master/src/processing.py", line 52, in activity_localization scores.append(np.mean(sequence_class_prob[s:e,activity_idx])) TypeError: slice indices must be integers or None or have an index method

Something wrong for activity localization, do you know why? Thanks

— You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/imatge-upc/activitynet-2016-cvprw/issues/5#issuecomment-282254264, or mute the thread https://github.com/notifications/unsubscribe-auth/AYW6W2Nw50efUf1yybQP3FOyHgjRZ2_Cks5rfqxggaJpZM4LV_nU .

yclai1114 commented 7 years ago

Classification: 0.7912 Cleaning sink 0.0615 Knitting 0.0291 Washing dishes 0.0160 Washing hands 0.0120 Peeling potatoes Traceback (most recent call last): File "scripts/run_all_pipeline.py", line 188, in args.activity_threshold File "scripts/run_all_pipeline.py", line 73, in run_all_pipeline activity_threshold File "/home/ubuntu/Desktop/yc/activitynet-2016-cvprw-master/scripts/src/processing.py", line 52, in activity_localization scores.append(np.mean(sequence_class_prob[s:e,activity_idx])) TypeError: slice indices must be integers or None or have an index method

Same problem after run run_all_pipeline.py. Any solution please?

albertomontesg commented 7 years ago

Which version of Numpy are you using? I have checked and with version 1.11.2 should work. If not try to print the values of s, e and activity_idx to console and put here the output please.

Amysiat commented 7 years ago

@albertomontesg hello, I have a question to ask you. I want to use your model to train my own dataset, so i need to get the dataset/video.json . what should i do to get the video.json or dataset? I am looking forward your reply,thank you!

kousik97 commented 7 years ago

I get the following error while trying to execute run_all_pipeline.py:

Traceback (most recent call last): File "scripts/run_all_pipeline.py", line 4, in from keras.layers import (LSTM, BatchNormalization, Convolution3D, Dense, Dropout, Flatten, Input, File "/home2/koushik/venv/local/lib/python2.7/site-packages/keras/init.py", line 3, in from . import backend File "/home2/koushik/venv/local/lib/python2.7/site-packages/keras/backend/init.py", line 54, in from .tensorflow_backend import File "/home2/koushik/venv/local/lib/python2.7/site-packages/keras/backend/tensorflow_backend.py", line 1, in import tensorflow as tf File "/usr/local/lib/python2.7/dist-packages/tensorflow/init.py", line 24, in from tensorflow.python import File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/init.py", line 75, in from tensorflow.core.framework.graph_pb2 import * File "/usr/local/lib/python2.7/dist-packages/tensorflow/core/framework/graph_pb2.py", line 6, in from google.protobuf import descriptor as _descriptor File "/usr/local/lib/python2.7/dist-packages/google/protobuf/init.py", line 37, in import('pkg_resources').declare_namespace(name) File "/home2/koushik/venv/local/lib/python2.7/site-packages/pkg_resources.py", line 22, in import zipfile File "/usr/lib/python2.7/zipfile.py", line 501, in class ZipExtFile(io.BufferedIOBase): AttributeError: 'module' object has no attribute 'BufferedIOBase'

kousik97 commented 7 years ago

I have solved the previous error, but now I am getting a new error: Please help me. Using TensorFlow backend. Reading Video... Duration: 130.6s FPS: 30.0 Number of frames: 3919 Loading C3D network... Traceback (most recent call last): File "scripts/run_all_pipeline.py", line 188, in args.activity_threshold File "scripts/run_all_pipeline.py", line 40, in run_all_pipeline model = C3D_conv_features(True) File "scripts/run_all_pipeline.py", line 99, in C3D_conv_features trainable=False)) File "/usr/local/lib/python2.7/dist-packages/keras/layers/convolutional.py", line 448, in init ' is currently only working with Theano backend.') Exception: Convolution3D is currently only working with Theano backend.

Amysiat commented 7 years ago

I think you should Change your backend,the default backend is tensorflow.

------------------ 原始邮件 ------------------ 发件人: "kousik97";notifications@github.com; 发送时间: 2017年5月31日(星期三) 下午2:08 收件人: "imatge-upc/activitynet-2016-cvprw"activitynet-2016-cvprw@noreply.github.com; 抄送: "0℃的温度"1358584332@qq.com; "Comment"comment@noreply.github.com; 主题: Re: [imatge-upc/activitynet-2016-cvprw] Error when runrun_all_pipeline.py (#5)

I have solved the previous error, but now I am getting a new error: Please help me. Using TensorFlow backend. Reading Video... Duration: 130.6s FPS: 30.0 Number of frames: 3919 Loading C3D network... Traceback (most recent call last): File "scripts/run_all_pipeline.py", line 188, in args.activity_threshold File "scripts/run_all_pipeline.py", line 40, in run_all_pipeline model = C3D_conv_features(True) File "scripts/run_all_pipeline.py", line 99, in C3D_conv_features trainable=False)) File "/usr/local/lib/python2.7/dist-packages/keras/layers/convolutional.py", line 448, in init ' is currently only working with Theano backend.') Exception: Convolution3D is currently only working with Theano backend.

— You are receiving this because you commented. Reply to this email directly, view it on GitHub, or mute the thread.

kousik97 commented 7 years ago

Thank you so much. I have changed that and it is working but I am getting the following error now: I am trying to run it on a CPU. Please help.

Using Theano backend. Reading Video... Duration: 130.6s FPS: 30.0 Number of frames: 3919 Loading C3D network... Traceback (most recent call last): File "scripts/run_all_pipeline.py", line 188, in args.activity_threshold File "scripts/run_all_pipeline.py", line 40, in run_all_pipeline model = C3D_conv_features(True) File "scripts/run_all_pipeline.py", line 99, in C3D_conv_features trainable=False)) File "/usr/local/lib/python2.7/dist-packages/keras/models.py", line 114, in add layer.create_input_layer(batch_input_shape, input_dtype) File "/usr/local/lib/python2.7/dist-packages/keras/engine/topology.py", line 341, in create_input_layer self(x) File "/usr/local/lib/python2.7/dist-packages/keras/engine/topology.py", line 485, in call self.add_inbound_node(inbound_layers, node_indices, tensor_indices) File "/usr/local/lib/python2.7/dist-packages/keras/engine/topology.py", line 543, in add_inbound_node Node.create_node(self, inbound_layers, node_indices, tensor_indices) File "/usr/local/lib/python2.7/dist-packages/keras/engine/topology.py", line 148, in create_node output_tensors = to_list(outbound_layer.call(input_tensors[0], mask=input_masks[0])) File "/usr/local/lib/python2.7/dist-packages/keras/layers/convolutional.py", line 552, in call filter_shape=self.W_shape) File "/usr/local/lib/python2.7/dist-packages/keras/backend/theano_backend.py", line 919, in conv3d conv_out = dnn.dnn_conv3d(x, kernel, border_mode=border_mode) File "/usr/local/lib/python2.7/dist-packages/theano/sandbox/cuda/dnn.py", line 1257, in dnn_conv3d return GpuDnnConv3d(algo=algo)(img, kerns, out, desc) File "/usr/local/lib/python2.7/dist-packages/theano/sandbox/cuda/dnn.py", line 513, in init super(GpuDnnConv3d, self).init(inplace=inplace, algo=algo) File "/usr/local/lib/python2.7/dist-packages/theano/sandbox/cuda/dnn.py", line 328, in init if version() < (3000, 3000): File "/usr/local/lib/python2.7/dist-packages/theano/sandbox/cuda/init.py", line 407, in dnn_version dnn_available.msg) Exception: ("We can't determine the cudnn version as it is not available", 'CUDA not available')

amit309b commented 7 years ago

I am getting error can anyone please solve this : Using Theano backend. Traceback (most recent call last): File "scripts/run_all_pipeline.py", line 4, in from keras.layers import (LSTM, BatchNormalization, Convolution3D, Dense, Dropout, Flatten, Input, File "/usr/local/lib/python2.7/dist-packages/keras/init.py", line 3, in from . import activations File "/usr/local/lib/python2.7/dist-packages/keras/activations.py", line 4, in from . import backend as K File "/usr/local/lib/python2.7/dist-packages/keras/backend/init.py", line 70, in from .theano_backend import File "/usr/local/lib/python2.7/dist-packages/keras/backend/theano_backend.py", line 3, in import theano File "/home/inkers/.local/lib/python2.7/site-packages/theano/init.py", line 70, in from theano.compile import ( File "/home/inkers/.local/lib/python2.7/site-packages/theano/compile/init.py", line 10, in from theano.compile.function_module import File "/home/inkers/.local/lib/python2.7/site-packages/theano/compile/function_module.py", line 21, in import theano.compile.mode File "/home/inkers/.local/lib/python2.7/site-packages/theano/compile/mode.py", line 10, in import theano.gof.vm File "/home/inkers/.local/lib/python2.7/site-packages/theano/gof/vm.py", line 659, in from . import lazylinker_c File "/home/inkers/.local/lib/python2.7/site-packages/theano/gof/lazylinker_c.py", line 125, in args = cmodule.GCC_compiler.compile_args() File "/home/inkers/.local/lib/python2.7/site-packages/theano/gof/cmodule.py", line 2088, in compile_args default_compilation_result, default_execution_result = try_march_flag(GCC_compiler.march_flags) File "/home/inkers/.local/lib/python2.7/site-packages/theano/gof/cmodule.py", line 1856, in try_march_flag flags=cflags, try_run=True) File "/home/inkers/.local/lib/python2.7/site-packages/theano/gof/cmodule.py", line 2188, in try_compile_tmp comp_args) File "/home/inkers/.local/lib/python2.7/site-packages/theano/gof/cmodule.py", line 1756, in _try_compile_tmp fd, path = tempfile.mkstemp(suffix='.c', prefix=tmp_prefix) File "/usr/lib/python2.7/tempfile.py", line 307, in mkstemp dir = gettempdir() File "/usr/lib/python2.7/tempfile.py", line 275, in gettempdir tempdir = _get_default_tempdir() File "/usr/lib/python2.7/tempfile.py", line 200, in _get_default_tempdir with _io.open(fd, 'wb', closefd=False) as fp: AttributeError: 'module' object has no attribute 'open'

amit309b commented 7 years ago

hey @kousik97 how did u solve this error File "/usr/lib/python2.7/zipfile.py", line 501, in class ZipExtFile(io.BufferedIOBase): AttributeError: 'module' object has no attribute 'BufferedIOBase'

kousik97 commented 7 years ago

Yeah, I solved it. The problem is the io.py in src directory. Rename the io.py to io1.py and correspondingly change the places in which io is used. That worked for me. The problem is zipfile is executing the io package in the python library and not the local io.py in our directory.

Meanwhile, are you using GPU to run the demo?

ghost commented 7 years ago

I am getting this error, please help or suggest something Using Theano backend. Reading Video... Duration: 22.2s FPS: 25.0 Number of frames: 555 Loading C3D network... scripts/run_all_pipeline.py:106: UserWarning: Update your Conv3D call to the Keras 2 API: Conv3D(64, (3, 3, 3), name="conv1", activation="relu", trainable=False, input_shape=(3, 16, 11..., padding="same", strides=(1, 1, 1)) trainable=False)) Traceback (most recent call last): File "scripts/run_all_pipeline.py", line 284, in args.activity_threshold) File "scripts/run_all_pipeline.py", line 40, in run_all_pipeline model = C3D_conv_features(True) File "scripts/run_all_pipeline.py", line 106, in C3D_conv_features trainable=False)) File "/home/asif/.virtualenvs/keras/local/lib/python2.7/site-packages/keras/models.py", line 443, in add layer(x) File "/home/asif/.virtualenvs/keras/local/lib/python2.7/site-packages/keras/engine/topology.py", line 596, in call output = self.call(inputs, **kwargs) File "/home/asif/.virtualenvs/keras/local/lib/python2.7/site-packages/keras/layers/convolutional.py", line 172, in call dilation_rate=self.dilation_rate) File "/home/asif/.virtualenvs/keras/local/lib/python2.7/site-packages/keras/backend/theano_backend.py", line 1944, in conv3d conv_out = T.nnet.conv3d(x, kernel, AttributeError: 'module' object has no attribute 'conv3d'

amit309b commented 7 years ago

@mdasifjalal it seems that you written code in tensorflow as shown T and used theano as backened. conv_out = T.nnet.conv3d(x, kernel,

ghost commented 7 years ago

nope, that is not the problem. I think, it was a version mismatch .

kartikeyaSh commented 7 years ago

Duration: 6.6s FPS: 25.0 Number of frames: 164 Loading C3D network... Extracting features... 10/10 [==============================] - 4s
Loading temporal localization network...

Layer (type) Output Shape Param # Connected to

features (InputLayer) (1, 1, 4096) 0

normalization (BatchNormalization) (1, 1, 4096) 8192 features[0][0]

dropout_1 (Dropout) (1, 1, 4096) 0 normalization[0][0]

lsmt1 (LSTM) (1, 1, 512) 9439232 dropout_1[0][0]

dropout_2 (Dropout) (1, 1, 512) 0 lsmt1[0][0]

fc (TimeDistributed) (1, 1, 201) 103113 dropout_2[0][0]

Total params: 9550537

Predicting... Traceback (most recent call last): File "scripts/run_all_pipeline.py", line 287, in args.activity_threshold) File "scripts/run_all_pipeline.py", line 58, in run_all_pipeline Y = Y.reshape(nb_clips, 1, 4096) ValueError: cannot reshape array of size 32112640 into shape (10,1,4096)

any guesses why i get this error and how can i correct it?

wasim-ee37 commented 6 years ago

Predicting... Traceback (most recent call last): File "scripts/run_all_pipeline.py", line 291, in args.activity_threshold) File "scripts/run_all_pipeline.py", line 64, in run_all_pipeline Y = Y.reshape(nb_clips, 1, 4096) ValueError: cannot reshape array of size 9253 into shape (19,1,4096)

Why am I encountering this error? Please somebody help me out in this.

EMCL commented 5 years ago

hi, i am getting below error when running python scripts/run_all_pipeline.py -i test2.avi

Exception: ('The following error happened while compiling the node', GpuDnnConv3d{algo='small', inplace=False}(GpuContiguous.0, GpuContiguous.0, GpuAllocEmpty.0, GpuDnnConvDesc{border_mode=(1, 1, 1), subsample=(1, 1, 1), conv_mode='conv', precision='float32'}.0, Constant{1.0}, Constant{0.0}), '\n', 'nvcc return status', 2, 'for cmd', 'nvcc -shared -O3 -Xlinker -rpath,/usr/local/cuda-8.0/lib64 -arch=sm_35 -m64 -Xcompiler -fno-math-errno,-Wno-unused-label,-Wno-unused-variable,-Wno-write-strings,-DCUDA_NDARRAY_CUH=c72d035fdf91890f3b36710688069b2e,-DNPY_NO_DEPRECATED_API=NPY_1_7_API_VERSION,-fPIC,-fvisibility=hidden -Xlinker -rpath,/home/lanka/.theano/compiledir_Linux-4.4--generic-x86_64-with-debian-stretch-sid-x86_64-2.7.13-64/cuda_ndarray -I/home/lanka/.theano/compiledir_Linux-4.4--generic-x86_64-with-debian-stretch-sid-x86_64-2.7.13-64/cuda_ndarray -I/usr/local/cuda-8.0/include -I/home/lanka/anaconda2/envs/activitynet/lib/python2.7/site-packages/theano/sandbox/cuda -I/home/lanka/anaconda2/envs/activitynet/lib/python2.7/site-packages/numpy/core/include -I/home/lanka/anaconda2/envs/activitynet/include/python2.7 -I/home/lanka/anaconda2/envs/activitynet/lib/python2.7/site-packages/theano/gof -o /home/lanka/.theano/compiledir_Linux-4.4--generic-x86_64-with-debian-stretch-sid-x86_64-2.7.13-64/tmpakYa3E/46fc805ce0bc8d50ab0e937e59958ac5.so mod.cu -L/home/lanka/.theano/compiledir_Linux-4.4--generic-x86_64-with-debian-stretch-sid-x86_64-2.7.13-64/cuda_ndarray -L/home/lanka/anaconda2/envs/activitynet/lib -lcudart -lcublas -lcuda_ndarray -lcudnn -lpython2.7', "[GpuDnnConv3d{algo='small', inplace=False}(<CudaNdarrayType(float32, 5D)>, <CudaNdarrayType(float32, 5D)>, <CudaNdarrayType(float32, 5D)>, <CDataType{cudnnConvolutionDescriptor_t}>, Constant{1.0}, Constant{0.0})]")