def run_model_on_dir():
data_location = os.path.join(DATA_DIR, PREFIX, 'set1')
output_location = os.path.join(RESULTS_DIR, PREFIX)
channel_names = ['phase']
image_size_x, image_size_y = get_image_sizes(data_location, channel_names)
model_name = '2018-06-13_ecoli_kc_polaris_channels_last_sample__0.h5'
weights = os.path.join(MODEL_DIR, PREFIX, model_name)
n_features = 3
window_size = (30, 30)
model_fn = bn_feature_net_61x61 if DATA_OUTPUT_MODE == 'sample' else bn_dense_feature_net
predictions = run_models_on_directory(data_location=data_location,
channel_names=channel_names,
output_location=output_location,
n_features=n_features,
model_fn=model_fn,
list_of_weights=[weights],
image_size_x=image_size_x,
image_size_y=image_size_y,
win_x=window_size[0],
win_y=window_size[1],
split=False)
cyto_weights = os.path.join(trained_network_cyto_directory, cyto_prefix + str(j) + ".h5") list_of_cyto_weights += [cyto_weights] # list_of_nuclear_weights = [] # for j in xrange(1): # nuclear_weights = os.path.join(trained_network_nuclear_directory, nuclear_prefix + str(j) + ".h5") # list_of_nuclear_weights += [nuclear_weights] # print list_of_nuclear_weights """ Run model on directory """ cytoplasm_predictions = run_models_on_directory(data_location, cyto_channel_names, cyto_location, n_features = 4, model_fn = cyto_fn, list_of_weights = list_of_cyto_weights, image_size_x = image_size_x, image_size_y = image_size_y, win_x = win_cyto, win_y = win_cyto, std = True, split = False) # nuclear_predictions = run_models_on_directory(data_location, nuclear_channel_names, nuclear_location, model_fn = nuclear_fn, # list_of_weights = list_of_nuclear_weights, image_size_x = image_size_x, image_size_y = image_size_y, # win_x = win_nuclear, win_y = win_nuclear, std = False, split = False) """ Refine segmentation with active contours """ # nuclear_masks = segment_nuclei(img = None, color_image = True, load_from_direc = nuclear_location, mask_location = mask_location, area_threshold = 100, solidity_threshold = 0, eccentricity_threshold = 1) # cytoplasm_masks = segment_cytoplasm(img = None, load_from_direc = cyto_location, color_image = True, nuclear_masks = nuclear_masks, mask_location = mask_location, smoothing = 1, num_iters = 120) """
nuclear_channel_names = ['nuclear'] trained_network_nuclear_directory = "/data/trained_networks/nuclei_broad/" nuclear_prefix = "2018-01-20_nuclei_broad_same_conv_61x61_bn_dense_feature_net_" win_nuclear = 30 image_size_x, image_size_y = get_image_sizes(data_location, nuclear_channel_names) """ Define model """ list_of_nuclear_weights = [] for j in xrange(1): nuclear_weights = os.path.join(trained_network_nuclear_directory, nuclear_prefix + str(j) + ".h5") list_of_nuclear_weights += [nuclear_weights] print list_of_nuclear_weights """ Run model on directory """ nuclear_predictions = run_models_on_directory(data_location, nuclear_channel_names, nuclear_location, model_fn = nuclear_fn, list_of_weights = list_of_nuclear_weights, image_size_x = image_size_x, image_size_y = image_size_y, win_x = win_nuclear, win_y = win_nuclear, std = False, split = False)