Merge pull request #633 from kwagyeman/kwabena/add_mobilenet_examples

Kwabena/add mobilenet examples
This commit is contained in:
Ibrahim Abd Elkader 2019-10-30 16:24:07 +02:00 committed by GitHub
commit 4100122ef5
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
5 changed files with 144 additions and 24 deletions

View File

@ -0,0 +1,58 @@
# TensorFlow Lite Mobilenet V1 Example
#
# Google's Mobilenet V1 detects 1000 classes of objects
#
# WARNING: Mobilenet is trained on ImageNet and isn't meant to classify anything
# in the real world. It's just designed to score well on the ImageNet dataset.
# This example just shows off running mobilenet on the OpenMV Cam. However, the
# default model is not really usable for anything. You have to use transfer
# learning to apply the model to a target problem by re-training the model.
#
# NOTE: This example only works on the OpenMV Cam H7 Pro (that has SDRAM) and better!
# To get the models please see the CNN Network library in OpenMV IDE under
# Tools -> Machine Vision. The labels are there too.
#
# In this example we slide the detector window over the image and get a list
# of activations. Note that use a CNN with a sliding window is extremely compute
# expensive so for an exhaustive search do not expect the CNN to be real-time.
import sensor, image, time, os, tf
sensor.reset() # Reset and initialize the sensor.
sensor.set_pixformat(sensor.RGB565) # Set pixel format to RGB565 (or GRAYSCALE)
sensor.set_framesize(sensor.QVGA) # Set frame size to QVGA (320x240)
sensor.set_windowing((240, 240)) # Set 240x240 window.
sensor.skip_frames(time=2000) # Let the camera adjust.
mobilenet_version = "1" # 1
mobilenet_width = "0.5" # 1.0, 0.75, 0.50, 0.25
mobilenet_resolution = "128" # 224, 192, 160, 128
mobilenet = "mobilenet_v%s_%s_%s_quant.tflite" % (mobilenet_version, mobilenet_width, mobilenet_resolution)
labels = [line.rstrip('\n') for line in open("mobilenet_labels.txt")]
clock = time.clock()
while(True):
clock.tick()
img = sensor.snapshot()
# net.classify() will run the network on an roi in the image (or on the whole image if the roi is not
# specified). A classification score output vector will be generated for each location. At each scale the
# detection window is moved around in the ROI using x_overlap (0-1) and y_overlap (0-1) as a guide.
# If you set the overlap to 0.5 then each detection window will overlap the previous one by 50%. Note
# the computational work load goes WAY up the more overlap. Finally, for multi-scale matching after
# sliding the network around in the x/y dimensions the detection window will shrink by scale_mul (0-1)
# down to min_scale (0-1). For example, if scale_mul is 0.5 the detection window will shrink by 50%.
# Note that at a lower scale there's even more area to search if x_overlap and y_overlap are small...
# default settings just do one detection... change them to search the image...
for obj in tf.classify(mobilenet, img, min_scale=1.0, scale_mul=0.5, x_overlap=0.0, y_overlap=0.0):
print("**********\nTop 5 Detections at [x=%d,y=%d,w=%d,h=%d]" % obj.rect())
img.draw_rectangle(obj.rect())
# This combines the labels and confidence values into a list of tuples
# and then sorts that list by the confidence values.
sorted_list = sorted(zip(labels, obj.output()), key = lambda x: x[1], reverse = True)
for i in range(5):
print("%s = %f" % (sorted_list[i][0], sorted_list[i][1]))
print(clock.fps(), "fps")

View File

@ -0,0 +1,64 @@
# TensorFlow Lite Mobilenet V1 Example
#
# Google's Mobilenet V1 detects 1000 classes of objects
#
# WARNING: Mobilenet is trained on ImageNet and isn't meant to classify anything
# in the real world. It's just designed to score well on the ImageNet dataset.
# This example just shows off running mobilenet on the OpenMV Cam. However, the
# default model is not really usable for anything. You have to use transfer
# learning to apply the model to a target problem by re-training the model.
#
# NOTE: This example only works on the OpenMV Cam H7 Pro (that has SDRAM) and better!
# To get the models please see the CNN Network library in OpenMV IDE under
# Tools -> Machine Vision. The labels are there too.
#
# In this example we slide the detector window over the image and get a list
# of activations. Note that use a CNN with a sliding window is extremely compute
# expensive so for an exhaustive search do not expect the CNN to be real-time.
import sensor, image, time, os, tf
sensor.reset() # Reset and initialize the sensor.
sensor.set_pixformat(sensor.RGB565) # Set pixel format to RGB565 (or GRAYSCALE)
sensor.set_framesize(sensor.QVGA) # Set frame size to QVGA (320x240)
sensor.set_windowing((240, 240)) # Set 240x240 window.
sensor.skip_frames(time=2000) # Let the camera adjust.
mobilenet_version = "1" # 1
mobilenet_width = "0.5" # 1.0, 0.75, 0.50, 0.25
mobilenet_resolution = "128" # 224, 192, 160, 128
mobilenet = "mobilenet_v%s_%s_%s_quant.tflite" % (mobilenet_version, mobilenet_width, mobilenet_resolution)
labels = [line.rstrip('\n') for line in open("mobilenet_labels.txt")]
clock = time.clock()
while(True):
clock.tick()
img = sensor.snapshot()
# net.classify() will run the network on an roi in the image (or on the whole image if the roi is not
# specified). A classification score output vector will be generated for each location. At each scale the
# detection window is moved around in the ROI using x_overlap (0-1) and y_overlap (0-1) as a guide.
# If you set the overlap to 0.5 then each detection window will overlap the previous one by 50%. Note
# the computational work load goes WAY up the more overlap. Finally, for multi-scale matching after
# sliding the network around in the x/y dimensions the detection window will shrink by scale_mul (0-1)
# down to min_scale (0-1). For example, if scale_mul is 0.5 the detection window will shrink by 50%.
# Note that at a lower scale there's even more area to search if x_overlap and y_overlap are small...
# Setting x_overlap=-1 forces the window to stay centered in the ROI in the x direction always. If
# y_overlap is not -1 the method will search in all vertical positions.
# Setting y_overlap=-1 forces the window to stay centered in the ROI in the y direction always. If
# x_overlap is not -1 the method will serach in all horizontal positions.
# default settings just do one detection... change them to search the image...
for obj in tf.classify(mobilenet, img, min_scale=1.0, scale_mul=0.5, x_overlap=-1, y_overlap=-1):
print("**********\nTop 5 Detections at [x=%d,y=%d,w=%d,h=%d]" % obj.rect())
img.draw_rectangle(obj.rect())
# This combines the labels and confidence values into a list of tuples
# and then sorts that list by the confidence values.
sorted_list = sorted(zip(labels, obj.output()), key = lambda x: x[1], reverse = True)
for i in range(5):
print("%s = %f" % (sorted_list[i][0], sorted_list[i][1]))
print(clock.fps(), "fps")

Binary file not shown.

Binary file not shown.

View File

@ -137,6 +137,7 @@ STATIC mp_obj_t int_py_tf_load(mp_obj_t path_obj, bool mode)
}
fb_alloc_mark();
uint32_t tensor_arena_size;
uint8_t *tensor_arena = fb_alloc_all(&tensor_arena_size, FB_ALLOC_PREFER_SIZE);
@ -153,6 +154,21 @@ STATIC mp_obj_t int_py_tf_load(mp_obj_t path_obj, bool mode)
return tf_model;
}
STATIC mp_obj_t py_tf_load_xalloc(mp_obj_t path_obj)
{
return int_py_tf_load(path_obj, false);
}
STATIC MP_DEFINE_CONST_FUN_OBJ_1(py_tf_load_obj, py_tf_load_xalloc);
STATIC py_tf_model_obj_t *py_tf_load_fb_alloc(mp_obj_t path_obj)
{
if (MP_OBJ_IS_TYPE(path_obj, &py_tf_model_type)) {
return (py_tf_model_obj_t *) path_obj;
} else {
return (py_tf_model_obj_t *) int_py_tf_load(path_obj, true);
}
}
typedef struct py_tf_input_data_callback_data {
image_t *img;
rectangle_t *roi;
@ -286,7 +302,9 @@ STATIC void py_tf_classify_output_data_callback(void *callback_data,
STATIC mp_obj_t py_tf_classify(uint n_args, const mp_obj_t *args, mp_map_t *kw_args)
{
py_tf_model_obj_t *arg_model;
fb_alloc_mark();
py_tf_model_obj_t *arg_model = py_tf_load_fb_alloc(args[0]);
image_t *arg_img = py_helper_arg_to_image_mutable(args[1]);
rectangle_t roi;
@ -304,14 +322,6 @@ STATIC mp_obj_t py_tf_classify(uint n_args, const mp_obj_t *args, mp_map_t *kw_a
float arg_y_overlap = py_helper_keyword_float(n_args, args, 6, kw_args, MP_OBJ_NEW_QSTR(MP_QSTR_y_overlap), 0.0f);
PY_ASSERT_TRUE_MSG(((0.0f <= arg_y_overlap) && (arg_y_overlap < 1.0f)) || (arg_y_overlap == -1.0f), "0 <= y_overlap < 1");
fb_alloc_mark();
if (MP_OBJ_IS_TYPE(args[0], &py_tf_model_type)) {
arg_model = (py_tf_model_obj_t *) args[0];
} else {
arg_model = int_py_tf_load(args[0], true);
}
uint32_t tensor_arena_size;
uint8_t *tensor_arena = fb_alloc_all(&tensor_arena_size, FB_ALLOC_PREFER_SIZE);
@ -404,20 +414,14 @@ STATIC void py_tf_segment_output_data_callback(void *callback_data,
STATIC mp_obj_t py_tf_segment(uint n_args, const mp_obj_t *args, mp_map_t *kw_args)
{
py_tf_model_obj_t *arg_model;
fb_alloc_mark();
py_tf_model_obj_t *arg_model = py_tf_load_fb_alloc(args[0]);
image_t *arg_img = py_helper_arg_to_image_mutable(args[1]);
rectangle_t roi;
py_helper_keyword_rectangle_roi(arg_img, n_args, args, 2, kw_args, &roi);
fb_alloc_mark();
if (MP_OBJ_IS_TYPE(args[0], &py_tf_model_type)) {
arg_model = (py_tf_model_obj_t *) args[0];
} else {
arg_model = int_py_tf_load(args[0], true);
}
uint32_t tensor_arena_size;
uint8_t *tensor_arena = fb_alloc_all(&tensor_arena_size, FB_ALLOC_PREFER_SIZE);
@ -470,12 +474,6 @@ STATIC const mp_obj_type_t py_tf_model_type = {
.locals_dict = (mp_obj_t) &locals_dict
};
STATIC mp_obj_t py_tf_load(mp_obj_t path_obj)
{
return int_py_tf_load(path_obj, false);
}
STATIC MP_DEFINE_CONST_FUN_OBJ_1(py_tf_load_obj, py_tf_load);
#endif // IMLIB_ENABLE_TF
STATIC const mp_rom_map_elem_t globals_dict_table[] = {