def _test_outputs_gradients(model): x, y, _ = make_data(K.int_shape(model.input), model.layers[2].units) name = model.layers[1].name grads_all = get_gradients(model, name, x, y, mode='outputs') grads_last = get_gradients(model, 2, x, y, mode='outputs') kwargs1 = dict(n_rows=None, show_xy_ticks=[0, 0], show_borders=True, max_timesteps=50, title_mode='grads') kwargs2 = dict(n_rows=2, show_xy_ticks=[1, 1], show_borders=False, max_timesteps=None) features_1D(grads_all[0], **kwargs1) features_1D(grads_all[:1], **kwargs1) features_1D(grads_all, **kwargs2) features_2D(grads_all[0], norm=(-.01, .01), show_colorbar=True, **kwargs1) features_2D(grads_all, norm=None, reflect_half=True, **kwargs2) features_0D(grads_last, marker='o', color=None, title_mode='grads') features_0D(grads_last, marker='x', color='blue', ylims=(-.1, .1)) features_hist(grads_all, bins=100, xlims=(-.01, .01), title="Outs hists") features_hist(grads_all, bins=100, n_rows=4) print('\n') # improve separation
def viz_outs_grads(model, idx=1): x, y, _ = make_data(K.int_shape(model.input), model.layers[2].units) grads = get_gradients(model, idx, x, y) kws = dict(n_rows=8, title='grads') features_1D(grads[0], show_borders=False, **kws) features_2D(grads, norm=(-1e-4, 1e-4), **kws)
def viz(self): data = self._get_data() features_2D(data, tight=True, title=False, cmap='hot', norm=None, show_xy_ticks=[0, 0], w=1.1, h=.55, n_rows=4)
def viz(self): w = self.tg.model.layers[2].get_weights()[0] w = w.reshape(-1, *w.shape[2:]) # flatten along spatial dims w = w.transpose(2, 0, 1) # (out_features, spatial dims x in_features) if not hasattr(self, 'init_norm'): # maintain same norm throughout plots for consistency mx = np.max(np.abs(w)) self.init_norm = (-mx, mx) features_2D(w, tight=True, w=.4, h=.4, title=None, show_xy_ticks=0, norm=self.init_norm)
def viz(self): data = self.get_data() fig, axes = features_2D(data, n_rows=2, cmap='hot', h=.5, w=1.1, title=False, show_xy_ticks=0, tight=True, borderwidth=2, bordercolor='white') if self.save_images: # stream to directory savepath = os.path.join(self.tg.logdir, 'misc', "epoch{}.png".format(self.tg.epoch)) fig.savefig(savepath, pad_inches=0)
def _test_outputs(model): x, *_ = make_data(K.int_shape(model.input), model.layers[2].units) outs = get_outputs(model, 1, x) features_1D(outs[:1], show_y_zero=True) features_1D(outs[0]) features_2D(outs)
def test_misc(): # test miscellaneous functionalities units = 6 batch_shape = (8, 100, 2 * units) reset_seeds(reset_graph_with_backend=K) model = make_model(GRU, batch_shape, activation='relu', recurrent_dropout=0.3, IMPORTS=IMPORTS) x, y, sw = make_data(batch_shape, units) model.train_on_batch(x, y, sw) weights_norm(model, 'gru', omit_names='bias', verbose=1) weights_norm(model, ['gru', 1, (1, 1)], norm_fn=np.abs) stats = weights_norm(model, 'gru') weights_norm(model, 'gru', _dict=stats) grads = get_gradients(model, 1, x, y) get_gradients(model, 1, x, y, as_dict=True) get_gradients(model, ['gru', 1], x, y) get_outputs(model, ['gru', 1], x) features_1D(grads, subplot_samples=True, tight=True, borderwidth=2, share_xy=False) with tempdir() as dirpath: features_0D(grads[0], savepath=os.path.join(dirpath, 'img.png')) with tempdir() as dirpath: features_1D(grads[0], subplot_samples=True, annotations=[1, 'pi'], savepath=os.path.join(dirpath, 'img.png')) features_2D(grads.T, n_rows=1.5, tight=True, borderwidth=2) with tempdir() as dirpath: features_2D(grads.T[:, :, 0], norm='auto', savepath=os.path.join(dirpath, 'img.png')) with tempdir() as dirpath: features_hist(grads, show_borders=False, borderwidth=1, annotations=[0], show_xy_ticks=[0, 0], share_xy=(1, 1), title="grads", savepath=os.path.join(dirpath, 'img.png')) with tempdir() as dirpath: features_hist_v2(list(grads[:, :4, :3]), colnames=list('abcd'), show_borders=False, xlims=(-.01, .01), ylim=100, borderwidth=1, show_xy_ticks=[0, 0], side_annot='row', share_xy=True, title="Grads", savepath=os.path.join(dirpath, 'img.png')) features_hist(grads, center_zero=True, xlims=(-1, 1), share_xy=0) features_hist_v2(list(grads[:, :4, :3]), center_zero=True, xlims=(-1, 1), share_xy=(False, False)) with tempdir() as dirpath: rnn_histogram(model, 1, show_xy_ticks=[0, 0], equate_axes=2, savepath=os.path.join(dirpath, 'img.png')) rnn_histogram(model, 1, equate_axes=False, configs={ 'tight': dict(left=0, right=1), 'plot': dict(color='red'), 'title': dict(fontsize=14), }) rnn_heatmap(model, 1, cmap=None, normalize=True, show_borders=False) rnn_heatmap(model, 1, cmap=None, norm='auto', absolute_value=True) rnn_heatmap(model, 1, norm=None) with tempdir() as dirpath: rnn_heatmap(model, 1, norm=(-.004, .004), savepath=os.path.join(dirpath, 'img.png')) hist_clipped(grads, peaks_to_clip=2) _, ax = plt.subplots(1, 1) hist_clipped(grads, peaks_to_clip=2, ax=ax, annot_kw=dict(fontsize=15)) get_full_name(model, 'gru') get_full_name(model, 1) pass_on_error(get_full_name, model, 'croc') get_weights(model, 'gru', as_dict=False) get_weights(model, 'gru', as_dict=True) get_weights(model, 'gru/bias') get_weights(model, ['gru', 1, (1, 1)]) pass_on_error(get_weights, model, 'gru/goo') get_weights(model, '*') get_gradients(model, '*', x, y) get_outputs(model, '*', x) from see_rnn.utils import _filter_duplicates_by_keys keys, data = _filter_duplicates_by_keys(list('abbc'), [1, 2, 3, 4]) assert keys == ['a', 'b', 'c'] assert data == [1, 2, 4] keys, data = _filter_duplicates_by_keys(list('abbc'), [1, 2, 3, 4], [5, 6, 7, 8]) assert keys == ['a', 'b', 'c'] assert data[0] == [1, 2, 4] and data[1] == [5, 6, 8] from see_rnn.inspect_gen import get_layer, detect_nans get_layer(model, 'gru') get_rnn_weights(model, 1, concat_gates=False, as_tensors=True) rnn_heatmap(model, 1, input_data=x, labels=y, mode='weights') _test_prefetched_data(model) # test NaN/Inf detection nan_txt = detect_nans(np.array([1] * 9999 + [np.nan])).replace('\n', ' ') print(nan_txt) # case: print as quantity data = np.array([np.nan, np.inf, -np.inf, 0]) print(detect_nans(data, include_inf=True)) print(detect_nans(data, include_inf=False)) data = np.array([np.inf, 0]) print(detect_nans(data, include_inf=True)) detect_nans(np.array([0])) K.set_value(model.optimizer.lr, 1e12) train_model(model, iterations=10) rnn_histogram(model, 1) rnn_heatmap(model, 1) del model reset_seeds(reset_graph_with_backend=K) # test SimpleRNN & other _model = make_model(SimpleRNN, batch_shape, units=128, use_bias=False, IMPORTS=IMPORTS) train_model(_model, iterations=1) # TF2-Keras-Graph bug workaround rnn_histogram(_model, 1) # test _pretty_hist K.set_value(_model.optimizer.lr, 1e50) # force NaNs train_model(_model, iterations=20) rnn_heatmap(_model, 1) data = get_rnn_weights(_model, 1) rnn_heatmap(_model, 1, input_data=x, labels=y, data=data) os.environ["TF_KERAS"] = '0' get_rnn_weights(_model, 1, concat_gates=False) del _model assert True cprint("\n<< MISC TESTS PASSED >>\n", 'green')
def viz_outs(model, idx=1): x, y, _ = make_data(K.int_shape(model.input), model.layers[2].units) outs = get_outputs(model, idx, x) features_1D(outs[:1], n_rows=8, show_borders=False) features_2D(outs, n_rows=8, norm=(-1, 1))