ekim-yurtsever / deeptl-lane-change-classification Goto Github PK

Hi, thanks for the nice repository. Could you please let me know where can I find the fleet dataset?

What does each column of data in LCTable.csv mean?

I'm trying to run sample scripts but to be able to run ResNet test script we need to have a "LCTable.csv" file. What should be structure of this csv file?

`Epoch`` 1/10

• 1s - loss: nan - val_loss: 1.1921e-07

D:\anaconda3\envs\myenv\lib\site-packages\keras\engine\sequential.py:251: RuntimeWarning: invalid value encountered in less
if preds.min() < 0. or preds.max() > 1.:
D:\anaconda3\envs\myenv\lib\site-packages\keras\engine\sequential.py:251: RuntimeWarning: invalid value encountered in greater
if preds.min() < 0. or preds.max() > 1.:

Traceback (most recent call last):
File "D:\JetBrains\PyCharm 2021.1\plugins\python\helpers\pydev\pydevd.py", line 1483, in _exec
pydev_imports.execfile(file, globals, locals) # execute the script
File "D:\JetBrains\PyCharm 2021.1\plugins\python\helpers\pydev_pydev_imps_pydev_execfile.py", line 18, in execfile
exec(compile(contents+"\n", file, 'exec'), glob, loc)
File "D:/training/DeepTL-Lane-Change-Classification/test/mask_rcnn/sample_training_maskRCNN_lstm.py", line 34, in
model.train_n_fold_cross_val(Data, label, training_to_all_data_ratio=training_to_all_data_ratio, n=nb_cross_val, print_option=0, plot_option=0, save_option=0)
File "D:\training\DeepTL-Lane-Change-Classification\test\mask_rcnn\models.py", line 127, in train_n_fold_cross_val
self.train_model(X_train, y_train, X_test, y_test, print_option=print_option, verbose=verbose)
File "D:\training\DeepTL-Lane-Change-Classification\test\mask_rcnn\models.py", line 95, in train_model
validation_data=(X_test, y_test), class_weight=self.class_weights, verbose=verbose, callbacks=[self.history])
File "D:\anaconda3\envs\myenv\lib\site-packages\keras\engine\training.py", line 1042, in fit
validation_steps=validation_steps)
File "D:\anaconda3\envs\myenv\lib\site-packages\keras\engine\training_arrays.py", line 219, in fit_loop
callbacks.on_epoch_end(epoch, epoch_logs)
File "D:\anaconda3\envs\myenv\lib\site-packages\keras\callbacks.py", line 77, in on_epoch_end
callback.on_epoch_end(epoch, logs)
File "D:\training\DeepTL-Lane-Change-Classification\test\mask_rcnn\models.py", line 69, in on_epoch_end
self.AUC_train.append(roc_auc_score(self.train_y, y_pred_train))
File "D:\anaconda3\envs\myenv\lib\site-packages\sklearn\utils\validation.py", line 63, in inner_f
return f(*args, **kwargs)
File "D:\anaconda3\envs\myenv\lib\site-packages\sklearn\metrics_ranking.py", line 524, in roc_auc_score
y_score = check_array(y_score, ensure_2d=False)
File "D:\anaconda3\envs\myenv\lib\site-packages\sklearn\utils\validation.py", line 63, in inner_f
return f(*args, **kwargs)
File "D:\anaconda3\envs\myenv\lib\site-packages\sklearn\utils\validation.py", line 664, in check_array
allow_nan=force_all_finite == 'allow-nan')
File "D:\anaconda3\envs\myenv\lib\site-packages\sklearn\utils\validation.py", line 106, in _assert_all_finite
msg_dtype if msg_dtype is not None else X.dtype)
ValueError: Input contains NaN, infinity or a value too large for dtype('float32').`

Requires TensorFlow 1.3+ and Keras 2.0.8+.

model.py has a requirement like this so I don't think it's a Tensorflow version issue.
Whether I train on my own dataset or the original samples, it raises problems like this. It is said that the problem is related to bounding box, but this seems different.

[Only for the MaskRCNN based model] Download MaskRCNN weights* from https://www.dropbox.com/s/n81pagybkj8p5w1/mask_rcnn_coco.h5?dl=0 and move it to /test . Out of work

Thanks for your Mask R-CNN models that I can utilize to predict my own line change. It works well. There's just a little problem you did not mention in readme.md
The function 'detect' in detect_objects.py seems to be used for inference only. If I want to start training Mask R-CNN, what should I do?

When I run either of the Mask R-CNN codes, it raises problems like these:
Traceback (most recent call last):
File "D:\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 498, in _apply_op_helper
values, name=input_arg.name, as_ref=input_arg.is_ref)
File "D:\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\profiler\trace.py", line 163, in wrapped
return func(*args, **kwargs)
File "D:\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\framework\ops.py", line 1540, in convert_to_tensor
ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
File "D:\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\ops\array_ops.py", line 1525, in _autopacking_conversion_function
return _autopacking_helper(v, dtype, name or "packed")
File "D:\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\ops\array_ops.py", line 1460, in _autopacking_helper
constant_op.constant(elem, dtype=dtype, name=str(i)))
File "D:\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\framework\constant_op.py", line 265, in constant
allow_broadcast=True)
File "D:\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\framework\constant_op.py", line 283, in _constant_impl
allow_broadcast=allow_broadcast))
File "D:\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\framework\tensor_util.py", line 445, in make_tensor_proto
raise ValueError("None values not supported.")
ValueError: None values not supported.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "D:\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 536, in _apply_op_helper
values, as_ref=input_arg.is_ref).dtype.name
File "D:\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\profiler\trace.py", line 163, in wrapped
return func(*args, **kwargs)
File "D:\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\framework\ops.py", line 1540, in convert_to_tensor
ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
File "D:\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\ops\array_ops.py", line 1525, in _autopacking_conversion_function
return _autopacking_helper(v, dtype, name or "packed")
File "D:\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\ops\array_ops.py", line 1460, in _autopacking_helper
constant_op.constant(elem, dtype=dtype, name=str(i)))
File "D:\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\framework\constant_op.py", line 265, in constant
allow_broadcast=True)
File "D:\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\framework\constant_op.py", line 283, in _constant_impl
allow_broadcast=allow_broadcast))
File "D:\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\framework\tensor_util.py", line 445, in make_tensor_proto
raise ValueError("None values not supported.")
ValueError: None values not supported.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "sample_training_maskRCNN_lstm.py", line 15, in
masked_image_extraction.save_masked_images()
File "D:\pythonProject\DeepTL-Lane-Change-Classification\test\mask_rcnn\detect_objects.py", line 42, in save_masked_images
model = modellib.MaskRCNN(mode="inference", model_dir=MODEL_DIR, config=config)
File "D:\pythonProject\DeepTL-Lane-Change-Classification\test\mask_rcnn\model.py", line 1735, in init
self.keras_model = self.build(mode=mode, config=config)
File "D:\pythonProject\DeepTL-Lane-Change-Classification\test\mask_rcnn\model.py", line 1918, in build
config.POOL_SIZE, config.NUM_CLASSES)
File "D:\pythonProject\DeepTL-Lane-Change-Classification\test\mask_rcnn\model.py", line 903, in fpn_classifier_graph
mrcnn_bbox = KL.Reshape((s[1], num_classes, 4), name="mrcnn_bbox")(x)
File "D:\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\keras\engine\base_layer.py", line 952, in call
input_list)
File "D:\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\keras\engine\base_layer.py", line 1091, in _functional_construction_call
inputs, input_masks, args, kwargs)
File "D:\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\keras\engine\base_layer.py", line 822, in _keras_tensor_symbolic_call
return self._infer_output_signature(inputs, args, kwargs, input_masks)
File "D:\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\keras\engine\base_layer.py", line 863, in _infer_output_signature
outputs = call_fn(inputs, *args, **kwargs)
File "D:\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\keras\layers\core.py", line 553, in call
inputs, (array_ops.shape(inputs)[0],) + self.target_shape)
File "D:\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\util\dispatch.py", line 201, in wrapper
return target(*args, **kwargs)
File "D:\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\ops\array_ops.py", line 195, in reshape
result = gen_array_ops.reshape(tensor, shape, name)
File "D:\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\ops\gen_array_ops.py", line 8377, in reshape
"Reshape", tensor=tensor, shape=shape, name=name)
File "D:\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 540, in _apply_op_helper
(input_name, err))
ValueError: Tried to convert 'shape' to a tensor and failed. Error: None values not supported.
They are so complicated that I do not know where I should check to solve the problems. I run them based on Python 3.6, tf-gpu 2.4 and Cuda 11.2. By the way, resnet_prediction can run while resnet_training cannot.

I don't want to bother you but I got this error. It happens when I run sample_training_maskRCNN_lstm.py
Traceback (most recent call last):
File "D:/pythonProject/DeepTL-Lane-Change-Classification/test/mask_rcnn/sample_training_maskRCNN_lstm.py", line 15, in
masked_image_extraction.save_masked_images()
File "D:\pythonProject\DeepTL-Lane-Change-Classification\test\mask_rcnn\detect_objects.py", line 42, in save_masked_images
model = modellib.MaskRCNN(mode="training", model_dir=MODEL_DIR, config=config)
File "D:\pythonProject\DeepTL-Lane-Change-Classification\test\mask_rcnn\model.py", line 1737, in init
self.keras_model = self.build(mode=mode, config=config)
File "D:\pythonProject\DeepTL-Lane-Change-Classification\test\mask_rcnn\model.py", line 1877, in build
target_rois, input_gt_class_ids, gt_boxes, input_gt_masks])
File "D:\anaconda3\envs\myenv\lib\site-packages\keras\engine\base_layer.py", line 460, in call
output = self.call(inputs, **kwargs)
File "D:\pythonProject\DeepTL-Lane-Change-Classification\test\mask_rcnn\model.py", line 638, in call
self.config.IMAGES_PER_GPU, names=names)
File "D:\pythonProject\DeepTL-Lane-Change-Classification\test\mask_rcnn\utils.py", line 673, in batch_slice
output_slice = graph_fn(*inputs_slice)
File "D:\pythonProject\DeepTL-Lane-Change-Classification\test\mask_rcnn\model.py", line 637, in
w, x, y, z, self.config),
File "D:\pythonProject\DeepTL-Lane-Change-Classification\test\mask_rcnn\model.py", line 533, in detection_targets_graph
negative_count = int((positive_count / config.ROI_POSITIVE_RATIO) - positive_count)
TypeError: unsupported operand type(s) for /: 'Tensor' and 'float'

positive_count = int(config.TRAIN_ROIS_PER_IMAGE *config.ROI_POSITIVE_RATIO)
positive_count = tf.shape(positive_indices)[0]

negative_count = int((positive_count / config.ROI_POSITIVE_RATIO) - positive_count)

What is the true value of positive_count? The prediction model works well, I just can't start training.